The goals of this post are modest. The previous post about chess thinking outlined how humans don’t first generate a list of legal moves that they filter down. It hand-wavingly claimed that moves “pop up” in our minds. This post shows one possible mechanism of such popping up.

The analysis will be based on what I call “situational categories” (or situations, for short), a term I prefer over the overused term pattern. I hope to sidestep the rigid imagery that the term pattern evokes: it makes some people think of assorted pieces arrayed in some specific configuration. By contrast, the…

Chess offers us an interesting window into cognition. Millions of chess games are available for free. Games come labeled with the rough level of expertise (available from rank novices through super-grandmasters) and also the available amount of time (ranging from just three minutes for all moves in bullet chess through a leisurely week or longer per move in correspondence chess). Furthermore, given the strong chess engines today that are magnitudes better than the best human players, it is possible to automatically label blunders (although we cannot accurately identify small mistakes).

In this post, I dwell on one aspect of chess…

What symbols are for Marcus differs from what symbols are for Bengio — and in between those extremes exists another possibility that offers a compromise.

My research lives midway between the two extremes. I want symbols, but I don’t wish them handcrafted: my work has been in obtaining symbols by statistical techniques by reading from tons of data (from web pages while at Google, and from text and graphs at Pinterest). My symbols have a distributed representation and graded evocation, and I am after compositionality and higher level structures. Finally, one key ambition of the cognitive architecture I built for…

PatiencePhoto by Michel Porro on Unsplash

Why is AI Brittle?

What ails AI today is brittleness. Someone unveils this fantastic AI program that shows superhuman performance on some task, but a minor tweak to the input brings it down to its knees. AI systems that are marvelous at recognizing objects in images can be duped by altering a single pixel into seeing a non-existent giraffe. Self-driving cars, which scream “AI!!!” more loudly than all else, are hoodwinked by mere stickers into driving on the wrong side of the road.

What makes AI brittle? I present one overlooked reason that I consider key to this brittleness: a heavy reliance on eager…

I suggest they don’t.

Frederick A. Cook’s picture of Ed Barrill atop a peak claimed to be Denali but actually 15,000 ft lower.

This post may be read by itself or as the second installment of “The Emperor’s New Benchmarks”. That post looked at a benchmark of passing curiosity (pun detection), but now we consider a problem that commands the community’s ongoing veneration.

Recognizing Textual Entailment

Several NLP benchmarks test for semantic understanding. One such is Recognizing Textual Entailment (RTE): Given two sentences, a premise P and a hypothesis H, decide if we can conclude H given P. This comes in two flavors. For binary RTE, the answer may only be yes or no. …

The Dangers of NLP Benchmark Oversimplification

Language is complex. For NLP, we often use simplified benchmarks, relegating phenomena such as metaphor, metonymy, and ungrammatical usage to future work. We also simplify in other ways. Surely an innocuous step — doesn’t science proceed from the simple to the complex?

This post documents damage simplistic benchmarks cause. While I had grand designs for this post, I will scale down to one particular benchmark — pun detection — and follow up with other posts for other benchmarks.

Methodology: To illustrate the dangers I perceive, I use published concrete examples from reputable venues. Singling out papers is not my style…

Just stumbled on a beautiful paragraph in The Savage Mind by Claude Levi-Strauss. This follows discussion of the rich vocabulary the so-called savages have for their flora and fauna, often distinguishing, for instance, over a dozen of species of ants. The witch doctors and shamans freely mix their extensive knowledge of herbs with magic and other unscientific paraphernalia; this has sometimes been presented as a stepping stone to more scientific knowledge by a process of keep-what-works. Levi-Strauss adds nuance to this view (p 13).

I am not however commending a return to the popular belief (although it has some validity…

Adventures in Going Nowhere

All the unhappiness of men arises from one simple fact: that they cannot sit quietly in their chamber. — Blaise Pascal

A travel writer, this somehow seems improbable, has crafted a book extolling the pleasures of going nowhere — of sitting still, and the “real deep entertainment” that calming the mind can bring.

This review must be short. Pico Iyer’s compact book, a mere 48 text-containing pages, deserves nothing less. Paradoxically, despite the brevity, Iyer manages a leisurely pace, never hurried. The medium fits the message well.

Two related ideas unite the book. First, that the world today is full…

It is my dream to create a thesaurus. I have had this desire for at least a decade now, and I have, time and again, dabbled into spelling out what this might look like, how precisely this would be different from, say, Roget’s.

Of course I realize that this is not an easy task — Peter Mark Roget toiled for 47 years before the thesaurus was released to the public in 1852, and I am currently reading The Meaning of Everything: the Story of the Oxford English Dictionary, which depicts that great tome’s 71-year journey from conception to reality. I…

Review of Benedict Carey’s “How We Learn: The Surprising Truth About When, Where, and Why It Happens”.

When you read, does testing help material stick in your head? Suppose you and a friend read a poem for a few minutes, and then shut the book, never re-reading it. One of you tries reciting it from memory soon after, the other doesn’t. A week later, would one of you remember more of the poem?

Suppose you want to perfect three different tennis serves. You have enough time for practicing 3,000 serves. Would you gain more from “blocked practice” — repeating the…

Abhijit Mahabal

I do unsupervised concept discovery at Pinterest (and previously at Google). Twitter: @amahabal

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store