.

Should you went through higher education in India, you will have surely heard the phrase iske fundé clear hain (“Their fundé are clear”) or perhaps more likely said of yourself yaar mere fundé gol hain (“Man, my fundé are tousled”). Should you didn’t undergo higher education in India, I’m sure you’re wondering why all this fuss about fundé. What does it even mean?

Nominally, the word fundé (फ़ंडे, pronounced “fun-day”, like Sunday) is the Hindi plural type of funda (फ़ंडा), which itself is a colloquial contraction of the English word fundamental. Thus fundé means fundamentals. In an academic context, it refers back to the strength of 1’s understanding of the basics of a given subject. Those that have their fundé clear in a subject are sure to do well within the dreaded end-of-semester/12 months exams.

The concept acknowledges that each one subjects have an axiomatic basis that, if mastered, allows one to construct an intensive understanding of the topic. The choice to an axiomatic understanding is rote memorization. Note that either strategy works for getting through exams, but those who have their fundé clear occupy a special place of reverence amongst their peers. Similarly the lament of getting your fundé tousled is the expression of fear that you just’re not prone to do well in the topic.

For most individuals going through higher education in India, discovering the axiomatic foundations of a subject is a torturous process. The pedagogy is just too often convoluted unless one is blessed with a gifted teacher. Those that do eventually get their fundé clear mostly achieve this with some struggle and labor.

Culturally, it goes even beyond exams. It pays homage to the axiomatic principles of life itself. It’s a typical query in lots of every day conversations: iska funda kya hai? (“What’s the funda behind this?”) where the “this” could confer with something as mundane as a toaster knob or as profound because the existential questions in life.

It just isn’t unusual to understand a peer for having a transparent sense of prioritization of their life: iske life ke fundé clear hain (Their fundé of life are clear). There may be a reverence for the final concept that there are fundamental axioms in all facets of life. And further, mastering those fundamentals generally leads to raised things in life and is a desirable frame of mind.

This universality of fundé in life has at all times been an enormous influence on me. If one can derive things from (i.e., the fundé are clear), then the retention of worthless knowledge becomes unnecessary, and life turn into much simpler.

Which brings me to artificial intelligence, and more specifically deep learning.

I first became aware of the rapid progress occurring in deep learning around 2012. A subsequent talk at Indiana University by the then Chief Scientist of Microsoft, Peter Lee, brought my attention to more recent developments. In a short time, I started scouring the literature on the topic, reading anything and every thing I could find on it.

What I discovered was that the majority literature was grounded in anything but first principles. One was (and still mostly is) routinely expected to be proficient in vector calculus, linear algebra, and probability and statistics. In case your fundé in these subjects aren’t clear, you might be fundamentally tousled, because your fundé in deep learning will remain similarly unclear.

On top of that, the pedagogy of the topic reinforces this mindset — almost every book on the topic begins with “mathematical preliminaries” which can be particularly deceptive. They’re condensed and consequently much denser than other higher written books in the themes, so just getting past them is an exercise.

In other words, the pedagogy of deep learning tends to intimidate. It keeps those that haven’t embraced the M in STEM away, and this includes most developers in today’s tech industry.

Things have definitely improved since 2012 and there are newer resources which have tried to bridge this gap, but they often decide to black-box the mathematics right into a code library, quite than bring the mathematical intuition forward and construct it from first principles to point out causal links between the several ideas in the topic.

That brings me to my co-author Daniel P. Friedman, who has been teaching computer science at Indiana University for the last half-century. He is legendary for his Socratic approach to teaching very complex ideas in computer science entirely from first principles. His other books: The Little Lisper, The Little Schemer, The Seasoned Schemer, The Reasoned Schemer, The Little Prover, The Little Typer, and more have laid the groundwork of this kind of pedagogy. Full disclosure: he can be my Ph. D. advisor from way-back-when.

If there was anything that may very well be done to offer a greater pedagogical path to deep learning, it will need to involve him! We bumped into one another on Friday, the thirteenth of April, 2018, on the over-crowded, official opening of the Luddy School of Informatics, Computing, and Engineering and we decided to put in writing a book on machine learning based on this very deep conversation directly following the close of the event.

Anurag: I need to put in writing somewhat book with you.

Dan: Let’s do it!

…

a number of seconds later

…

Dan: What’s the subject?

Anurag: Machine learning

Dan: Now, that will likely be a worthy challenge!

And the remaining of the time we reminisced …

We’ve got since then worked together these last four-plus years to put in writing the newest within the series of “Little” books: The Little Learner: A Straight Line to Deep Learning. It develops the complex ideas in deep learning from first principles without appealing to anything greater than basic highschool algebra and geometry, and a knowledge of programming.

In other words, it’s designed to get your fundé clear and experience the enjoyment of learning about this kind of AI from first principles. We’re glad to announce that the book is now generally available and shipping, through the auspices of MIT Press (Cambridge, MA).

We hope this little foray into deep learning will likely be fun for you, and we hope that it’s as interesting to read as we’ve got found it to put in writing.

Bon appétit, from us — Daniel P. Friedman and Anurag Mendhekar.