2 papers
stat.ML2023
Implicit biases in multitask and continual learning from a backward error analysis perspective
Benoit Dherin
Using backward error analysis, we compute implicit training biases in multitask and continual learning settings for neural networks trained with stochastic gradient descent. In par…
stat.ML2023
Morse Neural Networks for Uncertainty Quantification
Benoit Dherin, Huiyi Hu, Jie Ren +2
We introduce a new deep generative model useful for uncertainty quantification: the Morse neural network, which generalizes the unnormalized Gaussian densities to have modes of hig…