Neural Network Parameters
Francois and Keith discuss the importance of building better priors or gaining more experience to enhance neural networks. They explore the idea of storing object permanence prior in neural network parameters for easier transferability. The conversation delves into the potential of generative models like Gamegan in incorporating various tasks and the role of regularization in achieving generalization.In this clip
From this podcast
Machine Learning Street Talk (MLST)
Francois Chollet - On the Measure of Intelligence
Related Questions