Blog
We have moved from typing syntax to stating intent.
But the ultimate goal of any education is to be surpassed.
The performance of an algorithm is fundamentally intertwined with the hardware and software it runs on.
We have to learn the bitter lesson that building in how we think we think does not work in the long run.
So we need to design neural networks to work with other solutions, not to eradicate.
Excerpts from François Chollet's 2017 essays on deep learning's limitations and its program-like, modular future.
The "analysis-by-synthesis" view of SICP became irrelevant. Nowadays, we do programming by poking.
Don't forget that you're in charge, not the computer.
Though the term statistical learning is fairly new, many of the concepts that underlie the field were developed long ago.
You may learn from others but interpret what you learn in your own way.
When you go too far up, abstraction-wise, you run out of oxygen.
Any physical theory is always provisional, in the sense that it is only a hypothesis: you can never prove it.
Why do so few scientists make significant contributions and so many are forgotten in the long run?
Consequently "known" refers to values that are both available and considered worthwhile to include in model specifications.
The question of whether Machines Can Think, a question of which we now know that it is about as relevant as the question of whether Submarines Can Swim.
Since all models are wrong the scientist cannot obtain a "correct" one by excessive elaboration.
The machine would even encroach upon the activities we now class as 'art'; it is doing so already, via the camera and the radio.
What is contained simultaneously in thought unfolds sequentially in speech.
I heartily wish that the case were otherwise.
The most ignorant person, at a reasonable charge, and with a little bodily labour, might write books in philosophy, poetry, politics, laws, mathematics, and theology, without the least assistance from genius or study.
What the game is, defines what the players do.
Every fall, I explain to a fresh batch of Ph.D. students what a Ph.D. is. It's hard to describe it in words. So, I use pictures.