Saturday, September 30, 2017

Best Deep Learning Books (Popular)

The Quotes ๐Ÿ“Ÿ

Explaining Metaphysics to the nation–
I wish he would explain his Explanation
๐Ÿ˜‰
~ Lord Byron (Don Juan: Dedication)
Understanding, n. A cerebral secretion that enables one having it to know a house from a horse by the roof on the house. Its nature and laws have been exhaustively expounded by Locke, who rode a house, and Kant, who lived in a horse ๐Ÿ‘ป
~ Ambrose Bierce (The Devil's Dictionary) 
It requires a very unusual mind to undertake the analysis of the obvious ๐Ÿ”ฌ
~ Alfred North Whitehead (English mathematician and philosopher) 


Deep Learning (Popular) Books: The List ๐Ÿ“ฃ ๐Ÿ“ข

And here we have the two stellar books at which we'll soon be taking an opinionated look, in turn:

Extra, extra! ๐Ÿ“ฃ With the pic above as our guide, hold on to the thought that we'll later be taking an exclusive, behind-the-scenes tour of how your blogger went about improvising and capturing the photos—those which adorn the books being reviewed—for this essay. But all that will have to wait till the end of this essay ⏰

Here's the deal: I've received copious feedback from readers to cut to the chase when beginning any given essay. And I am dead serious about honoring the wishes of my readers. So before we get carried away with the inevitable excitement you would expect to accompany an exclusive behind-the-scenes tour, let's settle for a quick metaphor: Think Monty Python's Flying Circus, complete with how a prop—yep, the one bolstered precariously on the revolving chair in the pic above—painfully fell on your blogger's foot. You'll be relieved to know, or maybe not, that your blogger mostly escaped the accident unscathed, though he did cry a bit ๐Ÿ˜ญ Enough said on the whole matter. Let's dive right into some deep learning goodness ๐Ÿ‘ฃ

Preamble ⛱


I'm acutely aware of the gnawing sensation that the purists in the field of deep learning would have me drawn-and-quartered for selecting the two books for this essay: While the phrase "deep learning" does make a handful of appearances in one of the books—in The Master Algorithm to be precise—that phrase doesn't so much as make a single appearance in the other book (Deep Work) ๐Ÿ˜ฑ

So what's up with that? Here's what: Let's remind ourselves that the field of deep learning
  • ...does not exist in a vacuum
  • ...has deep roots in machine learning (ML)
  • ...is not a fad
  • ...is not hype
  • ...has become inextricably enmeshed with every discipline under the sun
  • ...requires a different level of abstraction to comprehend it meaningfully enough
  • ...needs a different mindset in order to run with it and to achieve focused success
I hope the list above suffices to convince you all to rise in unison and thwart all would-be attempts—potentially from purists who would violently demur at my selection of books for this essay—at pillorying your blog's author ๐ŸŽฑ But then again, I only need remind us all that some people can get oh-so-emotional ๐Ÿ˜น

A long time ago, in a galaxy far away, your blogger used to assiduously write programs in the C++ programming language. But that was before he discovered Java, Scala, Python, and indeed the whole world of distributed computing. And yet there come to occsionally haunt him—especially right now since we happen to be talking about the admittedly macabre themes of "violently demurring purists" and of "getting drawn-and-quartered"—remembrance of things past, for example this remembrance of his education while working in the C++ trenches:
As Chair of the working group for the standard C++ library, Mike Vilot was told, "If there isn't a standard string type, there will be blood in the streets!" (Some people get so emotional.) Calm yourself and put away those hatchets and truncheons—the standard C++ library has strings.
~ Scott Meyers in More Effective C++: 35 New Ways to Improve Your Programs and Designs (Addison-Wesley Professional).
Lest we digress too much, I hasten to add that, after bidding farewell to the C++ programming community a long time ago, I did make peace with my fellow, hard-core C++ programmers. That was elsewhere in the context of musing on how all languages inevitably carry some baggage—it's the relative degree of the conceptual burden that a programmer has to bear, when using the model of a given language, and which sets a language apart from others ๐Ÿ‘’

Okay, let's take a deep breath. We're already done with our first and last digression in this essay—most of the rest of digressions will be waiting for you once we get to the end of reviewing two sterling books here ๐Ÿ˜Ž

Introduction ๐Ÿ”Ž


I had initially toyed with the idea of calling this essay "Best Deep Learning Books (Thematic)". But the more I reflected on (the parenthetical use of the) word "thematic", the more I realized that we would be entering the realm of "diplomacy". That realization alone made me cringe and I rushed to replace "thematic" by "popular".

So while this essay is a variation on the theme of deep learning—hence my toying with the title "Best Deep Learning Books (Thematic)"—I feel that the title "Best Deep Learning Books (Popular)" does a better job of reminding us of what exactly we're talking about. So there you have it ๐Ÿ’ญ And that's what you get this time: "Best Deep Learning Books (Popular)" ๐Ÿ

Oh, lest you were confused by this somewhat nitpicky decision—whether to use "thematic" or "popular" in the parenthetical rejoinder of the essay—allow me to explain ever-so-briefly what I had in mind in mentioning the "diplomacy" realization above. So it's been said that
A diplomat is a person who can talk for an hour without saying anything ๐Ÿ˜‰
Enough said ๐Ÿ’‚ That, of course, is decidely not my style; I'm the opposite, in that I do my level best, research, get to the heart of the matter, and formulate it to lay the subject matter bare for you—I assume, and hope, that you probably don't want your blogger to write any other way either ⛳

Refresher ๐ŸŒน


Recap of Past Two Essays (In this Series)

We all—myself prominently incuded—need refreshers every now and then to load the intellectual goods into our working memory ๐Ÿ˜

Since we went over the background for deep learning in detail in the first two installments to this series of essays—this essay of course being the third installment—we won't rehash that context here. At the same time, I cordially invite you to look up those (two) previous essays to refresh you memory on the
  1. Foundational aspects of Deep Learning
  2. Pragmatic aspects of Deep Learning
And should anyone need proof of the bias for action, and the solid pragmatism—never a purist I was, and never I will be—that I bring to my daily work, allow me to point out merely that I've been spending most of my waking hours designing and crafting distributed systems (using Java and Scala). At the same time, though, the fields of Artificial Intelligence, Machine Learning, and of course Deep Learning never wander far from my mind ๐Ÿ’

Now this will be a first! I've never quoted Quora before; notwithstanding the pseudo-alliteration (neologism alert here, having just blithely used the phrase "quoted Quora"!) it's appearing more and more regularly on my radar now. In fact, as a long-time (once-passive) subscriber to Quora, I continue to remain impressed by the high quality of their targeted updates (by way of the intriguing emails that continue to land in my inbox, with pointers to Quora questions-and-answers) ๐Ÿ“ฌ

Something of Quora

With that preamble, I invite you to have a look at an intriguing question which was posted fairly recently to Quora and ably answered by Andrew Ng (co-founder of Coursera and adjunct Professor of Stanford University). Here was the question ๐Ÿ‘ถ
I have a toddler. How should she prepare herself for the job market 15 years from now in the world of AI? (italics mine)
That such questions are even being asked is, to say the least, incredibly encouraging in that this phenomenon underscores the degree to which the quest for harnessing the power of Artificial Intelligence (AI) has permeated the public's consciousness. In turn, as a clearinghouse of sorts for ideas—which the blog you're reading now is all about—I recommend that you look up the full answer via the link that precedes the quote above. At any rate, here is part of the answer (by Andrew Ng) to that question:
Yes, do teach her to code. More importantly, cultivate in her the ability to keep learning
In the CS world, all of us are used to needing to jump every ~5 years onto new technologies and paradigms of thinking (internet -> cloud -> mobile -> AI/machine learning), because new technologies get invented at that pace that obsolete parts of what we were previously doing. So CS people are used to learning new things all the time. 
The thing that’s now changed is that CS has infected pretty much every other industry. So now it’s not just the CS world that has to change every few years. It’s that everyone now needs to change. That’s why being able to keep learning will be the most important career skill you can teach your daughter (italics mine).
Frankly, I was impressed by the delightfully articulate answer by Andrew Ng; again, I encourage to look up the full answer at Quora—it resonates with the theme of this essay in that paradigms don't exist in a vacuum; ideas, and indeed paradigms themselves, evolve ever-so-organically ๐Ÿ˜Ž
Any little song that you want to sing
Little songs that you want to sing
Any song will do
Any little song that you want to sing
Little songs that you want to sing
It's up to you
Little songs that you want to sing
A little song that you want to sing
You're blue ๐ŸŽต
~ Robert Plant (Lyrics from In The Mood)

1. The Master Algorithm: How the Quest for the Ultimate Learning Machine Will Remake Our World (Basic Books) by Pedro Domingos. ๐Ÿณ


One of the Most Fun Books Ever!

This book is proof positive that it's possible to be fun and substantial at the same time. Before we dive into the goodies you can expect to find in the pages of The Master Algorithm, let's first hear from Kirkus Reviews, which probably summed it up the best in noting how this book is
[An] enthusiastic but not dumbed-down introduction to machine learning... lucid and consistently informative... With wit, vision, and scholarship, Domingos describes how these scientists are creating programs that allow a computer to teach itself. Readers...will discover fascinating insights.
So let's please have you squint at the pic above ๐Ÿ” You'll notice that The Master Algorithm is sandwiched between two decidedly popular books. Flanking it on the left-hand side and right-hand side, respectively, are:
  • Seeing What Others Don't: The Remarkable Ways We Gain Insights (PublicAffairs) by Gary Klein
  • Only Humans Need Apply: Winners and Losers in the Age of Smart Machines (HarperBusiness) by Thomas Davenport and Julia Kirby.
I'm resisting the sorely tempting urge to digress into a word or two on the two intriguing books I mentioned above in passing ✊ But this time we're determined to proceed with discipline, with nary a lapse into those digressions. At any rate, if you agree with the basic premise of Carly Fiorina—former president, and chair of Hewlett-Packard—in her observation that "The goal is to turn data into information, and information into insight", then you may find yourself agreeing with my assessment that the themes which these books explore are actually intertwined, and deeply so. Those themes include, but are not limited to
  • Seeing patterns where others don't ๐Ÿ‘€
  • Handling the tension between fostering human creativity and the relentless march of automation ๐Ÿ’ช
  • Figuring out how to best manage the very fabric of business—at least as we know it today—which is undergoing tumultous upheaval ๐Ÿš›
  • Detecting patterns, at both the human and machine level ⛷
  • Dealing with the catalyst that Machine Learning (ML) is, and which is truly fueling the abovementioned upheaval ๐Ÿš€
Allow me to  remind us all—even as I ask that you keep the themes above in mind—that what you want to look for in The Master Algorithm is its unerring focus on teasing out and elaborating how these themes are intertwined.

Plus, having read and re-read The Master Algorithm several times over, I truly felt that its author (Pedro Domingos) did a great job of clearly articulating the book's themes. His narrative style was methodical and discriminating (in the good sense of the word "discriminating", I hasted to add lol, in that the narrative nicely delineates and discriminates between the ambiguities that inevitably lurk at the boundaries of related ideas). In the process, I also felt that The Master Algorithm nicely sidesteps the following devilish defintions that conceivably might be applied to books of a lesser meter. I didn't really say it; just sayin' ๐Ÿ˜‰
Discriminate, v.i. To note the particulars in which one person or thing is, if possible, more objectionable than another.
Discussion, n. A method of confirming others in their errors.
~ Ambrose Bierce (The Devil's Dictionary) 
So that's another cool thing going for The Master Algorithm ๐Ÿ˜Ž

The Joy of Reading this Book

In my mind, The Master Algorithm is to the world of machine learning—and to deep learning in turn—what The Joy of Clojure is to the world of programming, and what Joy of Cooking is (was?!) to the culinary world (I can't definitively judge in the latter matter since my culinary skills barely hover above zero) ๐Ÿ”

Yes, the former is that good, and let me tell you why. For starters, The Master Algorithm blends an infectiously engaging style with the impeccable credentials of a leading researcher in the field of machine learning and AI: Domingos is a professor of computer science at the University of Washington. He is a winner of the SIGKDD Innovation Award, the highest honor in data science.

A "Map" of the Book

Domingos nicely lays out the map of The Master Algorithm in an introductory section (Prologue) of the book by pointing out how
I had a number of different but overlapping audiences in mind when writing this book. If you’re curious what all the hubbub surrounding big data and machine learning is about and suspect that there’s something deeper going on than what you see in the papers, you’re right! This book is your guide to the revolution (italics mine).
You really should look up The Master Algorithm for the details that Domingos immediately goes on to add to the point above—which was to describe one kind of its intended audience—by adding how readers of other diverse backgrounds will find much of value in its pages. In his words, you, too, are the intended audience of The Master Algorithm
  • If your main interest is in the business uses of machine learning, ...
  • If you’re a citizen or policy maker concerned with the social and political issues raised by big data and machine learning, ...
  • If you’re a scientist or engineer, ...
  • If you’re a machine-learning expert, ...
  • If you’re a student of any age—a high schooler wondering what to major in, a college undergraduate deciding whether to go into research, or a seasoned professional considering a career change—, ...
Again, I'm resisting the sorely tempting urge to digress into a word or two on my use of the word "Map"—as in "A Map of the Cat?", and as used by one of my heroes in science, the legendary physicist Richard Feynman—in the heading above ๐Ÿฑ Your blogger's will power is being put to a severe test, you all! ๐ŸŽง


Let's Get Ourselves Acquainted

To acquaint you better with the especially valuable aspects of The Master Algorithm, let's have ourselves a peek at its table of contents ๐Ÿฎ
Prologue
1 The Machine-Learning Revolution
2 The Master Algorithm
3 Hume’s Problem of Induction
4 How Does Your Brain Learn?
5 Evolution: Nature’s Learning Algorithm
6 In the Church of the Reverend Bayes
7 You Are What You Resemble
8 Learning Without a Teacher
9 The Pieces of the Puzzle Fall into Place
10 This Is the World on Machine Learning
Epilogue
Acknowledgments
Further Readings
Index
The Master Algorithm covers a lot of territory, and does it really well!

Get to Know the Larger Context in Which Deep Learning Operates

First let's listen to what one of the world's most distinguished computer scientists has to say about Domingos' The Master Algorithm ๐ŸŒŽ
This book is a sheer pleasure, mixed with education. I am recommending it to all my students, those who studied machine learning, those who are about to do it and those who are about to teach it (italics mine).
~ Judea Pearl, Professor of Computer Science, UCLA and winner of the A. M. Turing Award
Allow me to add this much: The undeniably profound impact of Judea Pearl on our field is writ large in our field's literature. Here, I will refer you to merely two resources: (1) This first resource is a bit diffuse and is on the algorithms side of our field, while (2) this second resource is much more pointed in that a classic in our field—Koller and Friedman's stellar book entitled Probabilistic Graphical Models—has the following glowing words for the inspiring influence of Pearl's work: In particular, to locate the aforementioned classic, head over to the subsection entitled "The Book to Read After Getting Comfortable with Linear Algebra" under our chat about yet another classic—the modern classic on deep learning of course—the inimitable book entitled simply Deep Learning (The MIT Press) by Goodfellow, Bengio and Courville.

But first, we have here Koller and Friedman acknowledging and paying tribute to Pearl's inspiring
work ๐ŸŽ“
Much of our core views on probabilistic models have been influenced by Judea Pearl. Judea through his persuasive writing and vivid presentations inspired us, and many other researchers of our generation, to plunge into research in this field.
~ Daphne Koller and Nir Friedman, in the Acknowledgments section of Probabilistic Graphical Models: Principles and Techniques (The MIT Press)
To paraphrase what one of my programming heroes—the late John Vlissides, who was the "V" in the "GHJV" which was the Gang of Four (GoF)—had to say about legendary programmer Robert “Uncle Bob” Martin's book Agile Software Development, Principles, Patterns, and Practices (Pearson), "When Pearl speaks, better listen up" ๐Ÿ“ฃ 

Having underscored the point that Domingos' The Master Algorithm is "all stuff and no fluff"—otherwise, you wouldn't have a distinguished computer scientist like Judea Pearl profusely praising it—let's return to a more detailed coverage of what The Master Algorithm has to offer you. For one thing, it's replete with engaging, relevant, and simply marvelous anecdotes that inexorably pull the reader deeper into the vortex of the field. Take this endearing anecdote for example in which Domingos tells us about
[Geoff] Hinton, a psychologist turned computer scientist and great-great-grandson of George Boole, the inventor of the logical calculus used in all digital computers, is the world’s leading connectionist. He has tried longer and harder to understand how the brain works than anyone else. He tells of coming home from work one day in a state of great excitement, exclaiming "I did it! I've figured out how the brain works!" His daughter replied, "Oh, Dad, not again!" Hinton’s latest passion is deep learning, which we’ll meet later in this chapter. He was also involved in the development of backpropagation, an even better algorithm than Boltzmann machines for solving the credit-assignment problem that we’ll look at next (italics mine).
I don't know about you, but I re-read that passage several times over to savor the delightful father-daughter moment that must've been ๐Ÿ‘ฑ ๐Ÿ‘ง

Another thing I liked a lot about The Master Algorithm is that Domingos has clearly taken great care to ensure that the narrative flows smoothly. And take it from me, someone who has been known to read a book or two, and even made an international reputation for himself by thinking once or twice a week—much as I noted in response to a reader comment elsewhere—the narrative of The Master Algorithm flows seamlessly, like honey. Not mollasses, but honey, to be sure; not viscous, but easygoing and light ๐Ÿฏ

Engaging Style, Comprehensive Coverage, and a Model of Clarity

I also liked a lot that Domingos liberally sprinkled The Master Algorithm with copious signposts to help the reader navigate the narrative with the greatest of ease; I would be pressed hard to think of another book that has accomplished this with greater finesse! Here, as an example, and much earlier in the book, we have Domingos telling the reader how 
The second goal of this book is thus to enable you to invent the Master Algorithm. You’d think this would require heavy-duty mathematics and severe theoretical work. On the contrary, what it requires is stepping back from the mathematical arcana to see the overarching pattern of learning phenomena; and for this the layman, approaching the forest from a distance, is in some ways better placed than the specialist, already deeply immersed in the study of particular trees. Once we have the conceptual solution, we can fill in the mathematical details; but that is not for this book, and not the most important part (italics mine).
Another terrific feature of The Master Algorithm is that it provides great context for each and every topic as the narrative unfolds over the span of the book. Here, for example, Domingos is enlightening the reader on the delicate connection between the "volume of data available for analysis" and the "corresponding number of hypotheses that survive" ๐Ÿ”Ž
Bottom line: learning is a race between the amount of data you have and the number of hypotheses you consider. More data exponentially reduces the number of hypotheses that survive, but if you start with a lot of them, you may still have some bad ones left at the end... You can even figure out in advance how many examples you’ll need to be pretty sure that the learner’s chosen hypothesis is very close to the true one, provided it fits all the data; in other words, for the hypothesis to be probably approximately correct. Harvard’s Leslie Valiant received the Turing Award, the Nobel Prize of computer science, for inventing this type of analysis, which he describes in his book entitled, appropriately enough, Probably Approximately Correct.
Is that good or what? And oh goodness, I'm yet again resisting the temptation to digress a tad into the rip-roaring fun book that Probably Approximately Correct is—yep, your blogger's will power is being put to the test, yet again, and this is all for you ๐Ÿ‘บ

Great Sense of Humor

While I haven't met Domingos in person, yet, I can clearly tell that he's got a great sense of humor! In a section in The Master Algorithm, where he is regaling us with the crucial role of analogy in machine learning, he begins that section by posing a question to the reader:
Is there anything analogy can’t do? Not according to Douglas Hofstadter, cognitive scientist and author of Gรถdel, Escher, Bach: An Eternal Golden Braid. Hofstadter, who looks a bit like the Grinch’s good twin, is probably the world’s best-known analogizer. In their book Surfaces and Essences: Analogy as the Fuel and Fire of Thinking, Hofstadter and his collaborator Emmanuel Sander argue passionately that all intelligent behavior reduces to analogy. Everything we learn or discover, from the meaning of everyday words like mother and play to the brilliant insights of geniuses like Albert Einstein and ร‰variste Galois, is the result of analogy in action.
My hardcover copy of The Master Algorithm is lit up with highlighter marks; I might as well have dipped the whole book in flourescent highlighter ink ๐Ÿ˜‰ This book has just a ton of great things going for it!

Rejoice

It's all in here, folks. Rejoice ๐ŸŽถ Your search for the resource from which to gently learn all about the larger context for deep learning is now officially over. All we to do now is set up camp and start reading ⛺ And hey, you do know what I mean, don't you? I'm not offering any learning camps—at least not at this time anyway—just mentioning the camping metaphor FWIW ๐ŸŽช

Judgment

I love this delightful book ๐Ÿ’• Don't miss it. It will help you gently learn—at your own pace, at your own time—all about the larger context in which the specialized subject of deep learning operates. It's hard to imagine anyone other than Domingos having the guts to take on such an ambitious goal (i.e. covering the whole expanse of the machine learning field in a comprehensive and engaging style) and then pulling it off as successfully as Domingos clearly has ๐Ÿ†

2. Deep Work: Rules for Focused Success in a Distracted World (Grand Central Publishing) by Cal Newport ๐Ÿ‹


Appreciating the Guts of Learning (and Working) Deeply

Pardon my admittedly visceral choice of words ("guts" and all) in the subheading above; it was just that I wanted to drive the point home ๐Ÿš— (This was visceral alert #1). With that, we now come to the second of the two books in this essay. And much as I said at the outset, I'm acutely aware of the gnawing sensation that purists in the field of deep learning would have me drawn-and-quartered for selecting the books for this essay: While the phrase "deep learning" makes a handful of appearances in of these two books—in The Master Algorithm to be precise—that phrase doesn't so much as make a single appearance in the other book ๐Ÿ˜ฑ

And thus it is that we now come to this next, remarkable book that's entitled Deep Work: Rules for Focused Success in a Distracted World (Grand Central Publishing) by Cal Newport. This would be a great time to remind ourselves that the field of deep learning
  • ...does not exist in a vacuum
  • ...has deep roots in machine learning (ML)
  • ...is not a fad
  • ...is not hype
  • ...has become inextricably enmeshed with every discipline under the sun
Other than the tangential observation that "hope springs eternal in the heart" of your blogger, I trust that the list above suffices to convince you all to rise in unison and thwart all would-be attempts—potentially from purists who would violently demur at my selection of books for this essay—at pillorying your blog's author for not being a purist, I also hope that you're coming to realize the even larger, global context within which human learning itself operates. We truly need to get a good grip on the ideals we want to strive for, or else risk ending up somewhere else, somewhere on a trajectory where we really don't want to be ๐ŸŒ

My choice for selecting Deep Work for this essay, I believe, is justified by the remarkable effectiveness with which it tackles the abovementioned ideas and ideals ⛵ As participants in the community of readers—with me serving as your host on this blog—you are surely not intimidated by taking on some bold and novel explorations, are you? True to the title of Deep Work, to its subtitle, to be precise—Rules for Focused Success in a Distracted World—this remarkable book takes on the ambitious goal of laying bare the gory details of how you, too, can achieve focused success in a distracted world ๐Ÿฉ

I might as well add: Pardon my admittedly visceral choice of words ("gory" and all) above; it was just that I wished, once again, to drive the point home ๐Ÿš™ (And yes, this was visceral alert #2) ๐Ÿ˜‰


Riveting Style of Presentation

Deep Work is written in an engaging style and is highy readable. On top of that, it's eminently substantial. Now how about that for a powerful combination? While I haven't met Cal in person, yet, I've followed his work closely for many years. In fact, it's not a coincidence that—and this was many, many moons ago—I had selected Cal for the top spot on my list of top thought leaders. You can read those details elsewhere, but here in a nutshell is how I had introduced Cal:
At the top of my list is Cal Newport, who is just about the most clear-eyed thinker I know of. Cal teaches at Georgetown University in Washington, D.C, where he is an Assistant Professor of Computer Science. What's unique about Cal are his uniquely original insights, which he shares with the world through his Study Hacks Blog: Decoding Patterns of Success. As the name of his blog signals, his posts seek to capture the essence of achieving meaningful success through wide-ranging, engagingly written, and eminently thought-provoking discussions. 
The reason I now mention his academic credentials—he earned his Ph.D. from MIT, and graduated from Dartmouth College—is that some of the most elegantly stellar thinking I've ever come across is regularly on display in his blogs (italics mine—or as the author of the preceding words, did I even need to point that out? Meta-recursion alert, folks!) ๐Ÿ‘ป
At first blush, the connection of Deep Work to the field of deep learning—in as it relates to helping you master deep learning—may strike the casual observer as even more tenuous than the connection which the other book (i.e. The Master Algorithm) has to the same goal. So let's "unwrap" this a bit, as we would unwrap a birthday present ๐ŸŽ

Unwrapping and Unpacking the Idea

And don't worry about getting tangled up in this whole "unwrapping" and "unpacking" business: I'll digress ever so briefly here, and that purely to illustrate a point, hopefully making the point all the more vivid in your mind and hence memorable. So here's the deal—much as we explored in an essay elsewhere—we're going to look at a related metaphor from the Clojure programming language (which just happens to be a Lisp dialect, and I happen to have more than a passing interest in all things Lisp) ๐ŸŽƒ

Remember how sequential "destructuring" represents a sequential data structure as a Clojure vector within a let binding? Or how built-in operations support the deconstruction of a syntax object, the composition of new syntax objects from old ones?

Wait, wait, oh wait! I need to get you a more apt metaphor that truly vivifies the notion I have in mind for the "unpacking" business I mentioned above. So let's rewind a bit and instead refer ourselves to an answer I had offered in response to a reader comment elsewhere ๐Ÿ˜Ž

Likely the greatest hurdle to a deep understanding of what it takes to achieve focused success in a distracted world is that we're actually swimming in that world. We miss, therefore, the proverbial forest for the trees ๐ŸŒฒ๐ŸŒณ๐ŸŒด๐ŸŒฒ๐ŸŒด๐ŸŒณ

Unwrapping and Unpacking the Idea Some More

We need to think at a different level of abstraction, and this is not terribly different from what I think Peter Seibel had in mind when he was explaining in his stellar book entitled Practical Common Lisp (Apress) that grokking macros is impeded, ironically enough, because that they’re so well integrated into the language. Yep, exactly, and so we miss yet again the proverbial forest for the trees ๐ŸŒฒ๐ŸŒณ๐ŸŒด๐ŸŒฒ๐ŸŒด๐ŸŒณ

And rather than leave it dangling, it's worthwhile to bring the preceding thought to closure—not Clojure, mind you (pun intended, for a change)—so let's hear Seibel himself telling the reader in Practical Common Lisp about the notion of how ๐Ÿ˜†
Perhaps the biggest barrier to a proper understanding of macros is, ironically, that they’re so well integrated into the language. In many ways they seem like just a funny kind of function— they’re written in Lisp, they take arguments and return results, and they allow you to abstract away distracting details. Yet despite these many similarities, macros operate at a different level than functions and create a totally different kind of abstraction (italics mine).
And that's precisely where Deep Work comes in, offering in its pages the ideas—or "rules", to use his vernacular—that are at just the right level of abstraction. That, IMHO, is what makes the book click, YMMV ๐Ÿš™

True to its title, to its subtitle, to be precise—Rules for Focused Success in a Distracted WorldDeep Work takes on the ambitious goal of laying bare how you, too, can achieve focused success in a distracted world

Let's Get Ourselves Acquainted

To acquaint you better with the solidly practical aspects of Deep Work, let's take a peek at the table of contents:
Welcome
Introduction
PART 1: The Idea
Chapter 1: Deep Work Is Valuable
Chapter 2: Deep Work Is Rare
Chapter 3: Deep Work Is Meaningful
PART 2: The Rules
Rule #1: Work Deeply
Rule #2: Embrace Boredom
Rule #3: Quit Social Media
Rule #4: Drain the Shallows
Conclusion
Did you see Rule #3—Quit Social Media—and found yourself groaning, and muttering under your breath some select words for your blogger, saying something like, "Akram, you're nothing but trouble. Your digressions notwithstanding, you're now asking us to contemplate (gasp) a life without social media?!" Sorry that I burst the bubble so unceremoniously:  Okay, so I didn't say this was going to be easy ๐Ÿ‘ป

All this after having mentioned elsewhere—in an exploration of algorithms, of all the places—how it is algorithms that power, among many other worldwide software offerings of course, Facebook's News Feed. And how, as much as we may be loathe to admit it, the Facebook News Feed is where many of us love to waste our time ⛱

But guess what? Yep, and while you don't have to go cold turkey, we've got to brace ourselves for cultivating some discipline in there ⛩

Oh, did you also notice Rule #4—Drain the Shallows—and found yourself cringing and reflexively think whether this has got anything to do with "draining the swamp"? Let me assure you, it does not. Again, as a loyal American, I respect the views of readers from all political persuasions; I was simply using poetic license to express mine, and that too in passing ⛷

A Definition and a Hypothesis

You will find in the introductory chapter of Deep Work a definition first ๐ŸŽน
Deep Work: Professional activities performed in a state of distraction-free concentration that push your cognitive capabilities to their limit. These efforts create new value, improve your skill, and are hard to replicate (italics mine).
...and then the hypothesis itself ๐ŸŽถ
The Deep Work Hypothesis: The ability to perform deep work is becoming increasingly rare at exactly the same time it is becoming increasingly valuable in our economy. As a consequence, the few who cultivate this skill, and then make it the core of their working life, will thrive (italics mine).
Finally, Cal points out with gravitas, and very correctly so—methinks that the author of Deep Work is on to something really, really important—what the implications of deep work are, beginning with these stark words, reminding the reader that ๐ŸŠ
Deep work is not, in other words, an old-fashioned skill falling into irrelevance. It’s instead a crucial ability for anyone looking to move ahead in a globally competitive information economy that tends to chew up and spit out those who aren’t earning their keep. The real rewards are reserved not for those who are comfortable using Facebook (a shallow task, easily replicated), but instead for those who are comfortable building the innovative distributed systems that run the service (a decidedly deep task, hard to replicate). Deep work is so important that we might consider it, to use the phrasing of business writer Eric Barker, "the superpower of the 21st century." (italics mine)
It just so happens that the italicized phrase above refers to something I do for a living. And so it is that I can attest to the verity of Cal's assessment.

Much like the other book that we explored earlier—The Master Algorithm: How the Quest for the Ultimate Learning Machine Will Remake Our World—Cal's book is filled to overflowing with engaging, relevant, and simply delightful anecdotes that inexorably pull the reader deeper into the vortex of the business of learning how to focus meaningfully.

    Standout Feature

    The number one standout feature of Deep Work is that its author speaks from deep experience. I didn't pass this judgment lightly, either; as I said at the outset, I've followed Cal's work closely for many years, which has given me ample time to form my impressions and opinions. I would go so far as to say that Deep Work is his best work yet ๐Ÿ’ฐ

    Another standout feature of Deep Work is its uncompromising commitment to doggedly pursuing the ins and outs of how you, too, can achieve focused success in a distracted world ๐ŸŽช

    It's this uncompromising commitment to help the reader that won me over, many times over!

    You have to check out Deep Work for yourself. Here, I'll merely mention in passing some fascinating anecdotes that can light up your experience of reading it and make the book so engaging:
    • How Cal—a theoretical computer scientist who performed his doctoral training in MIT’s Theory of Computation group—talks about spending a decade cultivating the ability to concentrate on hard things. And his intriguing telling of a MacArthur "genius grant" winner who is not on Twitter and who published sixteen papers last year.
    • The "grand gesture strategy" in which J.K. Rowling took extreme steps to complete The Deathly Hallows, the final book in her Harry Potter series. "As I was finishing Deathly Hallows there came a day where the window cleaner came, the kids were at home, the dogs were barking," Rowling recalled in an interview. And the rest is, as they say, history.
    • Recollections by Cal of his seven years at MIT, when he worked on the site of the institute’s famed Building 20 and how, in MIT lore, "it's generally believed that this haphazard combination of different disciplines, thrown together in a large reconfigurable building, led to chance encounters and a spirit of inventiveness that generated breakthroughs at a fast pace..."

    Judgment

    Dig in to the pages of Deep Work and you'll get a pretty good idea of why I'm babbling excitedly about it! This is a book for someone who is looking for inspiring, practical, gentle—and frankly, sometimes rather stark, bracing, yet salutory—guidance on the crucial theme of mastering the core practices that will enable you to achieve focused success in a distracted world. Don't miss this stellar book ๐Ÿ„


    Connoisseur, n. A specialist who knows everything about something and nothing about anything else ๐ŸŽ“
    ~ Ambrose Bierce (The Devil's Dictionary) 
    I would be most content if my children grew up to be the kind of people who think decorating consists mostly of building enough bookshelves ๐Ÿ“˜
    ~ Anna Quindlen 
    Philosophy, in one of its functions, is the critic of cosmologies. It is its function to harmonise, refashion, and justify divergent intuitions as to the nature of things. It has to insist on the scrutiny of the ultimate ideas, and on the retention of the whole of the evidence in shaping our cosmological scheme. Its business is to render explicit, and—so far as may be—efficient, a process which otherwise is unconsciously performed without rational tests ๐Ÿ”ญ
    ~ Alfred North Whitehead (English mathematician and philosopher)

    An Invitation ๐Ÿ“ฃ

    In the end, I invite your comments—Having now read the brief take each on the books above ๐Ÿ’ค
    • Do you find that your experience of reading any of these popular books was different? ๐Ÿข
    • Did I perhaps not cover some qualities, and which are the ones that you actually found the most helpful as you learned the larger milieu within which (deep) learning operates? ๐ŸŒŽ
    • Did I leave out any of your favorite deep learning popular books? ๐Ÿš›
    My hope is that the two brief vignettes will help you in your journey to grokking (deep) learning!

    Aha, there it is, flanking the left-hand side of the motley crew (or is it crue?!) of a ragtag smattering of books in the pic above—The Master Algorithm—bedecked with a carefully chosen, color-coded army of tape flags ๐ŸŽ‰ Come to look at it a bit more, the neighboring books of The Master Algorithm, too, are lit up with those trusty tape flags ๐Ÿ™‹

    You can read up more on "the method to the madness" elsewhere—specifically in the context of when we had dived into the pages of Algorithm Design and Applications—where I had quoted Elizabeth Dunn (an anthropologist at the University of Colorado–Boulder) who, in turn, had been quoted in the wise and scintillating pages of the book The Distraction Addiction: Getting the Information You Need and the Communication You Want, Without Enraging Your Family, Annoying Your Colleagues, and Destroying Your Soul how
    Consequently, "I do almost all of my labor and thought-intensive reading in print form." For me, serious reading involves marking up, underlining, and annotating books; it’s a martial art, and it requires the material engagement and support that paper can provide and that screens conspicuously lack. Fifty years ago, MIT professor and hypertext pioneer Vannevar Bush imagined we’d do this kind of intensive, interactive, relational reading on the memex, an electronic system he proposed in 1945. Today, people who really have to know their stuff still choose paper (italics mine).
    Oh, I nearly forgot to mention, this, too, in connection with the (four) books in the pic above. Did any of those books grab your attention? If so, do please consider posting your comments to let other readers—and me—know about which one of these gems you would like to hear more about, won't you? At this time, we've already covered one of them (The Master Algorithm) in some depth.

    But how about the rest of those books, the three that remain untouched in their pristine beauty ? Do please keep in mind that we all stand to benefit from ongoing dialogs by way of comments on this blog ๐Ÿ’


    My Passion for Sharing ๐Ÿ’

    Thought I'd mention: I don't make a single cent out of the links such as those that I provide in this essay and elsewhere. For exampe, the two links atop this essay, incidentally, will take you to their respective Amazon.com page each. Similar links, in here and in the other essays elsewhere on this blog, might take you, for example, to The MIT Press, and so on and so forth ๐Ÿ‘ž ๐Ÿ‘ก ๐Ÿ‘Ÿ ๐Ÿ‘ข ๐Ÿ‘ฃ 

    I write purely from my passion for sharing with you what I have learned, and what I continue to learn, about the ever-evolving paradigms in our software development industry. There is, I hasten to add for those so inclined, absolutely nothing wrong with monetizing a blog—I covered this and other related points in some depth in an essay elsewhere on technical blogging—after all, we've all heard countless times how
    The business of America is business๐Ÿ’ฐ
    When it comes to blogging, I'm squarely an explorer of ideas; I share with you what's on my mind at any given point in time; I relish doing so, and want to serve you well ๐ŸŽ

    Remember, too, the wisdom in these words:
    Of making many books there is no end, and much study is a weariness of the flesh
    What I will ask of you is to please consider posting your comments to let other readers—and me—know your thoughts, impressions, observations, anything really: Relax ⛱ We're in the comfortable, unencumbered orbit of programming digressions central ⛳

    After all, and much as I said above, do please keep in mind that we all stand to benefit from ongoing dialogs by way of comments on this blog ๐Ÿš€


    A Digression on the Postage Stamps Theme...

    Hey, did anyone notice the postage stamp theme in the previous installment to this series of deep learning essays? Hmm... Perhaps you're scratching your head, and quizzically wondering aloud, "What's that you just said, Akram?". That's fine, go ahead and please get your coffee—I'll wait for you. Once our caffiene has kicked in, we'll take in this memorable quote ☕
    Neither snow nor rain nor heat nor gloom of night stays these couriers from the swift completion of their appointed rounds.
    Unofficial motto of the of the United States Postal Service (USPS) that's long been associated with the American postman
    So I was once a budding philatelist—that's the million dollar word for a stamp collector—and I paid a tribute of sorts to the theme of stamp collecting by embedding all the pics (which adorned the previous deep learning essay) with postage stamp borders. Woohoo, I sure got a kick out of doing that! ⛹

    Speaking of stamp collecting, I was once also an eager numismatist—now that's the million dollar word for a coin collector—so the theme of coin collecting might crop up as the underlying theme in a future essay. A word to the wise ๐Ÿช Extra brownie points for the first few readers who spot the coin collecting theme in a future essay, and report their observation by way of a comment or two on this blog ๐Ÿ’ฏ

    A Behind-the-scenes Exclusive


    We First Set the Scene ⛑

    Finally, we have here an exclusive behind-the-scenes tour of the props for this essay ๐ŸŽฌ Much as I mentioned at the outset, where I had invited you to settle for a quick metaphor: Think Monty Python's Flying Circus, complete with how a prop—yep, the prop perched perilously on the prodigious revolving chair in the pic above—painfully fell on your blogger's foot, though he escaped unscathed, mostly ๐Ÿ‘ป

    I mean, what's the big deal with a Bandaid here or there, to heal an injury here or there, right? Oh, if only you knew half the things your blogger does to make you—yes, the thousand and thousands of you who come here every month—to keep coming back for even more ⛺

    Well, here we are, having re-emerged from the dark depths of the deep learning ocean, following our dive to retrieve all the deep learning oysters and pearls we could get our hands on, both past and present. Remember how you had been promised at the very outset—and here I nudge your attention to the kludgy props and stuff in the pic above—a sneak peek into how your blogger went about improvising and capturing the various pics? ⛄

    For one thing, the whole prop setup made me think recursion; yeah, leave it to me to cook up the most interesting connections between a variety of seemingly unrelated ideas and themes. The theme of recursion, in turn, got me thinking to a hilarious and inimitable episode from the Monty Python's Flying Circus series. That's where we go next ⛷

    And Then We Dive Right In ๐ŸŠ

    So let's have a look at the hilarious meta-recursion going on in the Monty Python's Flying Circus side-splitting funny episode entitled The Lost World of Roiurama—in particular the segment "Who's filming us?"—from which I'll share the following, ever-so-brief dialog in which our four intrepid explorers find themselves hopelessly lost in a jungle. Here, then, are some of the plaintive and frantic thoughts of those explorers ๐ŸŒณ๐ŸŒณ๐ŸŒณ๐ŸŒณ
    FIRST EXPLORER: Wait a moment!
    FOURTH EXPLORER: What is it?
    FIRST EXPLORER: If we're on film, there must be someone filming us.
    SECOND EXPLORER: My God, Betty, you're right!
    Oh goodness, you really should look that all up for yourself in Monty Python's Flying Circus: Complete and Annotated...All the Bits (Black Dog & Leventhal; Complete and annotated ed edition) by Luke Dempsey or the video itself on YouTube.

    And should you be moved to inquire into the origins of how the name "Python" came to be chosen by Guido van Rossum—the creator of the incredibly popular Python programming language and known to the Python community as its "Benevolent Dictator For Life" (BDFL)—I invite you to check this out as well in the context of whether Python is suitable for Machine Learning, and indeed Deep Learning itself...

    Till we meet next time, you have a great, productive week ๐ŸŽฏ

    Collage of Pics and Lyrics ๐ŸŽธ

    I'm in the mood for a melody
    I'm in the mood for a melody
    I'm in the mood 
    I can make you dance - I can make you sing
    I can make you dance - I can make you sing
    If you want me to 
    Any little song that you want to sing
    Little songs that you want to sing
    Any song will do 
    Any little song that you want to sing
    Little songs that you want to sing
    It's up to you 
    Little songs that you want to sing
    A little song that you want to sing
    You're blue 
    I'm in the mood, I'm in the mood, I'm in the mood
    I can write it on the door - I can put it on the floor
    I can do anything that you want me for
    If you want me to 
    I can do it right - I can do it wrong
    'Cause a matter of fact it'll turn out to be strong
    If you want me to
    ~ Robert Plant (Lyrics from In The Mood)

    4 comments:

    1. - As the one-and-only contributor to this blog's content, format, and presentation, I—as a matter of principle—do not edit my essays after posting them; I will, on occasion, revisit and clean up grammatical mistakes, or perhaps update stale links, but that's about it!

      - That was just a friendly reminder...

      - I'm here now, following up, to actually add a general comment to my own essay. That sounds a bit recursive, doesn't it? Fancy that :)

      - Anyhow, here's the idea: Having posted this essay a bit earlier (You're all familiar with the routine of how I write most all my essays over the weekends, or else early mornings, say 4:00 AM to 6:00 AM) the thought crossed my mind that perhaps some recruiters might find this blog and think, heaven forbid, that the essays on the blog are perhaps a glorified pitch of my resume! Sheesh!

      - Nothing could be farther from the truth. Yep, exactly! So in a typical essay, I'll routinely clarify up-front my stance on a particular topic, my opinion (personal opinion, which is mine, and mine alone), what my strengths—along with my weaknesses—are, what my background is that gives me credentials to talk about any given topic, and so on and so forth.

      - And goodness gracious, on realizing that, I immediately hasten to add here the unambiguous thought that I already have the best job in the world. I work alongside some of the smartest people on the planet. More importantly, much more importantly, I work for a genuinely caring company—a company that cares deeply for its customers and cares equally passionately for its employees—and there's no lip service going on anywhere. I've been in the industry for a bit over two decades, and know genuineness full well when I see it!

      - I'll add that, all employees here, my coworkers—all the way up to the highest levels of management—sit together at the proverbial table, as it were, like friends. We cheer one another to achieve the very best, every single day, and in the process we seek to usher our industry into higher and higher echelons of excellence and performance. Equally importantly, of course, we doggedly focus on ensuring that our customers benefit from our endless pipeline of innovations, both in the business and technical spheres.

      - Enough said!

      - Now you all enjoy this latest essay. Let's keep the dialog going, so please don't be shy with your comments ;)

      ReplyDelete
      Replies
      1. - Some essays get tons of comments from readers; last time I checked, the essay on the nuts and bolts of working with Big Data had a whopping 72 comments!

        - Others essays make shrinking violets out of you all; evidently, this essay has garnered a grand total of one comment, and that too is a comment from your very own blogger ;)

        - What gives? Well, I dunno... I'm going to chalk this up as one of those abiding mysteries of the universe that one never truly gets to fathom :)

        - Trust me, though, that nobody's going to make a shrinking violet out of me, no Sir and Madam ;)

        - So here we go, tongue planted firmly in cheek... 

        - With that, let's revisit a theme we had touched on, in this very essay. It had all started out innocently enough—plus I'm happy to report that the selfsame innocence remains intact, both of your blogger and of this essay—with a remark in the essay about how there come to occasionally haunt your blogger the admittedly macabre themes of "violently demurring purists" and of "getting drawn-and-quartered". Ah yes, remembrance of things past, ala Marcel Proust ;)

        - Speaking of remembering, um, remembrance of things past got me all excited—I think you are beginning to see the recurring theme on this blog where your blogger gets all excited about making connections between seemingly disparate themes and ideas, both technical and non-technical, and then sharing them with you. This time, I got excited about something from the pages of an often-overlooked gem by Dr. Robert Kegan, who is the Meehan Professor of Adult Learning and Professional Development at the Harvard University Graduate School of Education...

        - ...that superb book by Dr. Kegan is entitled In Over Our Heads: The Mental Demands of Modern Life (Harvard University Press).

        - In a nod to the whole business of "getting drawn-and-quartered", Dr. Kegan shared the following hilarious anecdote in In Over Our Heads, and which is what I wished to share with you today, if only to confirm that I'm in good company when I had worried about hopefully-ill-founded worries from the quarters of "demurring-purists-turned-pugilists" lol ;)

        - So in an introductory section of In Over Our Heads, Dr. Kegan shares the anecdote of how
        'In my thirties I wrote The Evolving Self, proposing a view of human being as meaning-making and exploring  inner experience and outer contours of our transformations in consciousness throughout the lifespan... Some years ago, when I proudly told my father that it was being translated into German and Korean, he said, "That's great! Now when is it going to be translated into English?". And in truth, these fortnightly letters from readers occasionally have a similar theme:

        Dear Dr. Kegan, We had to read your book in our psychology class. I can't believe the publishers let the thing out in this condition. No one in our class understands what you are saying. Not even our teacher, and he assigned it! Who are you trying to impress with all those big words? I got so mad reading your book I wanted to come to Boston and break your teeth.'

        Sincerely,

        [writer's name]

        I appreciated the "sincerely"...

        And that brings us to the end of the anecdote... I don't know about you, but I sure got a kick out of that; I trust that you enjoyed it, too, including any and all demurring purists who gleefully read "Programming Digressions" :) :)

        Delete
    2. Base upon your thorough commentary, I will certainly read one of these books, Akram. Thanks for the post!

      ReplyDelete
      Replies
      1. - Thanks, Jeff, for the great feedback. Comments from readers like you make my day, every day :-)

        - Yes, definitely, that sounds good and I hope you'll enjoy reading the book(s). I'm happy that I was able to bring them to your attention...

        - To that I'll add (for you as well as, of course, the thousands of visitors who come to the Programming Digressions blog every month), and much as I've mentioned elsewhere on this blog, from time to time, I don't make a single cent out of the links such as those that I provide in the blog (as and when I add references to where all those books are available online, or in bricks-and-mortar bookstores, for purchase, be it at The MIT Press, Amazon.com, BarnesAndNoble, etc.) - I write purely from my passion for sharing with you all what I have learned—and continue to learn—about the ever-evolving paradigms in our software development industry, our technological universe, our culture, and everything else in between!!! 

        - When it comes to blogging, I'm squarely an explorer of ideas; I share with you what's on my mind at any given point in time; I relish doing so, and want to serve you well!!!

        - Again, thanks for your comment!

        Delete