depth first search

“We can only see a short distance ahead, but we can see plenty there that needs to be done."

Applications of Machine Learning

It turns out that optimizing warehouse tasks is hard.

Minds, Brains, and Programs (I)

I’ve been reading a lot of Searle recently. Searle bashing seems to be a popular pastime among young graduate students in AI, but I admit to a certain sympathy with his argument. I recently read about analogue computing in The New Turing Omnibus which reminded me of one of Searle’s central claims, that the locus [...]

Debugging and Machine Learning

As I near completion on my final project for a course on reinforcement learning, I came across the following from Sutton’s page on tile coding: With the code described so far, there is a small probability that unrelated inputs will hash into some of the same tiles. In a group of tilings, usually there will [...]

On Gaussian Processes

The most interesting problems, the task of feature discovery for example, are not ones that Gaussian processes will solve. But maybe multilayer perceptrons can’t solve them either. Perhaps a fresh start is needed, approaching the problem of machine learning from a paradigm different from the supervised feedforward mapping.