alt Hacker News> A human can do the same by looking at the weights of an MLP trained on mnist
Excuse me?
Replies
Imnimo • today at 8:25 PM
See for example:
https://scikit-learn.org/stable/auto_examples/neural_network...
> A human can do the same by looking at the weights of an MLP trained on mnist
Excuse me?
See for example:
https://scikit-learn.org/stable/auto_examples/neural_network...
Yes. Just look at the reasoning logs that are part of the work. The reasoning is clearly about the input layer. At least for the game examples.