Boris Hanin

According to our database1, Boris Hanin authored at least 8 papers between 2017 and 2020.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Other 

Links

On csauthors.net:

Bibliography

2020
Finite Depth and Width Corrections to the Neural Tangent Kernel.
Proceedings of the 8th International Conference on Learning Representations, 2020

2019
Nonlinear Approximation and (Deep) ReLU Networks.
CoRR, 2019

Deep ReLU Networks Have Surprisingly Few Activation Patterns.
Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, 2019

Complexity of Linear Regions in Deep Networks.
Proceedings of the 36th International Conference on Machine Learning, 2019

2018
How to Start Training: The Effect of Initialization and Architecture.
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Which Neural Net Architectures Give Rise to Exploding and Vanishing Gradients?
Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

2017
Approximating Continuous Functions by ReLU Nets of Minimal Width.
CoRR, 2017

Universal Function Approximation by Deep Neural Nets with Bounded Width and ReLU Activations.
CoRR, 2017


  Loading...