12 citations · 24 across the 3 of their papers we have counts for
3 papers
The Training Process of Many Deep Networks Explores the Same Low-Dimensional Manifold
Jialin Mao, Itay Griniasty, Han Kheng Teoh +5
We develop information-geometric techniques to analyze the trajectories of the predictions of deep networks during training. By examining the underlying high-dimensional probabilis…
A picture of the space of typical learnable tasks
Rahul Ramesh, Jialin Mao, Itay Griniasty +5
We develop information geometric techniques to understand the representations learned by deep networks when they are trained on different tasks using supervised, meta-, semi-superv…
Visualizing probabilistic models in Minkowski space with intensive symmetrized Kullback-Leibler embedding
Han Kheng Teoh, Katherine N. Quinn, Jaron Kent-Dobias +3
We show that the predicted probability distributions for any -parameter statistical model taking the form of an exponential family can be explicitly and analytically embedded is…