research
∙
04/30/2022
Engineering flexible machine learning systems by traversing functionally invariant paths in weight space
Deep neural networks achieve human-like performance on a variety of perc...
share
research
∙
06/05/2021
Solving hybrid machine learning tasks by traversing weight space geodesics
Machine learning problems have an intrinsic geometric structure as centr...
research
∙
12/12/2020
Sparsifying networks by traversing Geodesics
The geometry of weight spaces and functional manifolds of neural network...
research
∙
11/05/2020
Architecture Agnostic Neural Networks
In this paper, we explore an alternate method for synthesizing neural ne...
research
∙
06/12/2020
Self-organization of multi-layer spiking neural networks
Living neural networks in our brains autonomously self-organize into lar...
research
∙
05/23/2020
Geometric algorithms for predicting resilience and recovering damage in neural networks
Biological neural networks have evolved to maintain performance despite ...
research
∙
06/03/2019