| ▲ | kachnuv_ocasek 2 hours ago | |
> A human can do the same by looking at the weights of an MLP trained on mnist Excuse me? | ||
| ▲ | astahlx 2 hours ago | parent | next [-] | |
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. | ||
| ▲ | Imnimo 2 hours ago | parent | prev [-] | |
See for example: https://scikit-learn.org/stable/auto_examples/neural_network... | ||