7 citations · 14 across the 2 of their papers we have counts for
3 papers
Going Beyond State-Reaching: Learning Abstractions for Intrinsically Motivated Option Discovery
Akhil Bagaria, Anita De Mello Koch, George Konidaris
Temporal abstraction via options can improve exploration in large environments. However, existing option discovery algorithms find subgoals that target all aspects of the state sim…
Why Unsupervised Deep Networks Generalize
Anita de Mello Koch, Ellen de Mello Koch, Robert de Mello Koch
Promising resolutions of the generalization puzzle observe that the actual number of parameters in a deep network is much smaller than naive estimates suggest. The renormalization…
Short sighted deep learning
Ellen de Melllo Koch, Anita de Mello Koch, Nicholas Kastanos +1
A theory explaining how deep learning works is yet to be developed. Previous work suggests that deep learning performs a coarse graining, similar in spirit to the renormalization g…