Sign in

Training Neural Networks with Internal State, Unconstrained Connectivity, and Discrete Activations

By Alexander Grushin
Today's most powerful machine learning approaches are typically designed to train stateless architectures with predefined layers and differentiable activation functions. While these approaches have led to unprecedented successes in areas such as natural language processing and image recognition, the trained models are also susceptible to making mistakes that a human... Show more
December 22, 2023
=
0
Loading PDF…
Loading full text...
Similar articles
Loading recommendations...
=
0
x1
Training Neural Networks with Internal State, Unconstrained Connectivity, and Discrete Activations
Click on play to start listening