Mardi 13 Avril 2021 – 13h – Salle de conférence 1er étage Pavillon Baudot.
« What does it mean to understand a neural network?».
Timothy P. Lillicrap & Konrad P. Kording
We can dene a neural network that can learn to recognize objects in less than 100 lines
of code. However, after training, it is characterized by millions of weights that contain the
knowledge about many object types across visual scenes. Such networks are thus dramatically
easier to understand in terms of the code that makes them than the resulting properties, such
as tuning or connections. In analogy, we conjecture that rules for development and learning in
brains may be far easier to understand than their resulting properties. The analogy suggests
that neuroscience would benet from a focus on learning and development