ML’s lament

ML’s Lament 

(to the tune of ‘part of your world‘, from The Little Mermaid)

Screen Shot 2017-07-13 at 1.45.40 PM

Look at this net, isn’t it neat?
Wouldn’t you say that it’s Turing-complete?
Wouldn’t you say that this net
This net can learn anything?
Look at this graph, tensors unfold
How many layers can one network hold?
Lookin’ round here you would think
Sure, it can learn everything

I’ve got ReLUs and batch-norms aplenty
I’ve got convos and poolings galore
You want GPU stacks?
I got twenty
But who cares?
No big deal
I want more

Read more...

Read more

Minsky: “If you’ve done something, you should be ashamed of it instead of proud it.”

Minsky interview at MIT150 Infinite History
Marvin Minsky: “Why bother?”

First, Marvin Minsky on mathematics and being slow:

MINSKY: I think when I was a child I didn’t have the feeling that I could solve problems that other people could solve. On the contrary, I found things were quite difficult. And when I tried to read mathematics it would take an hour a page and I’d get some of the ideas but not others. And usually it would be six months later that suddenly it would click. And so I think I thought of myself as sort of slow. On the other hand, I thought of everyone else as incredibly slow. But I didn’t think of myself as particularly creative.

Read more...

Read more

Probabilistic blindspots in Goodman’s new riddle of induction

Goodman’s Fact, Fiction and Forecast

In Fact, Fiction and Forecast, Nelson Goodman revisits Hume’s problem of induction. The problem Hume wrote about in the 18th century is: can we reliably know anything about the future, given experience of the past? Or alternatively, can we produce generalizable knowledge from observations of particulars?

Goodman breezes through a couple of unworkable solutions (or attempts at dissolutions) of Hume’s problem. He then zones in on the core issue: just as deductive inferences are justified if they conform to the rules of logic, Goodman argues that “predictions are justified if they conform to valid canons of induction.” The problem of induction, then, is the problem of defining the valid rules of induction.

Read more...

Read more

Minsky’s radical school of education

Minsky's Society of Mind
Excerpt from Marvin Minsky’s Society of Mind

Marvin Minsky, MIT professor and artificial intelligence pioneer, passed away last Sunday (January 24, 2016). Minsky is widely celebrated for his diverse scientific contributions to artificial intelligence, computer science, mathematics and even microscopy. Less well known are Minsky’s radical views on education.

Some mathematicians think that learning mathematics is about “reaching the summit and then swiftly burying the path.” Minsky didn’t. He was interested in why mathematics is hard for children to learn and what can be done about it. He thought that the difficulty was partly “caused by starting with the practice and drill of a bunch of skills called Arithmetic”. As a result, “instead of promoting inventiveness, we focus on preventing mistakes.” Some children, frustrated by this negativity, dismiss mathematics as repetitive, boring and punitive.

Read more...

Read more