The Lottery Ticket Hypothesis
Finding Sparse, Trainable Neural Networks
Book •
The Lottery Ticket Hypothesis proposes that within a randomly initialized neural network, there exist smaller subnetworks (winning tickets) that can be trained in isolation to match or exceed the performance of the original network.
This concept has been explored in various research papers but does not appear to be the title of a specific book.
This concept has been explored in various research papers but does not appear to be the title of a specific book.
Mentioned by
Mentioned in 0 episodes
Mentioned during the discussion on the lottery ticket hypothesis and neural network pruning.
Robert Lange on NN Pruning and Collective Intelligence
