Infinite Restricted Boltzmanns
Hugo discusses the intriguing concept of infinite restricted Boltzmann machines, exploring how they could adapt their capacity with more data. He shares the mathematical challenges faced during this research and reflects on the potential implications for the community, emphasizing the importance of exploring uncharted territories in modeling. Despite the practical limitations of RBMs today, the journey of discovery remains a valuable pursuit.In this clip
From this podcast
The Gradient
Hugo Larochelle: Deep Learning as Science
Related Questions