Twitter | Pretraživanje | |
Jaan Aru
Robust generalization in AI needs good inductive biases. and others discuss several ideas for how neuroscience can guide the search for better inductive biases by providing useful constraints on representations and network architecture.
Artificial neural networks still lag behind brains in their ability to generalize beyond their training conditions. In this review, Sinz et al. discuss several ideas for how neuroscience can guide...
Reply Retweet Označi sa "sviđa mi se" More
Martin Picard 26. ruj
Odgovor korisniku/ci @jaaanaru @danilobzdok @fabiansinz
How do these ideas relate to “visible machine learning”
Reply Retweet Označi sa "sviđa mi se"