4 citations · 10 across the 6 of their papers we have counts for
6 papers
Polarity is all you need to learn and transfer faster
Qingyang Wang, Michael A. Powell, Ali Geisa +2
Natural intelligences (NIs) thrive in a dynamic world - they learn quickly, sometimes with only a few samples. In contrast, artificial intelligences (AIs) typically learn with a pr…
Why do networks have inhibitory/negative connections?
Qingyang Wang, Michael A. Powell, Ali Geisa +3
Why do brains have inhibitory connections? Why do deep networks have negative weights? We propose an answer from the perspective of representation capacity. We believe representing…
Towards a theory of out-of-distribution learning
Jayanta Dey, Ali Geisa, Ronak Mehta +7
Learning is a process wherein a learning agent enhances its performance through exposure of experience or data. Throughout this journey, the agent may encounter diverse learning en…
Inducing a hierarchy for multi-class classification problems
Hayden S. Helm, Weiwei Yang, Sujeeth Bharadwaj +5
In applications where categorical labels follow a natural hierarchy, classification methods that exploit the label structure often outperform those that do not. Un-fortunately, the…
A partition-based similarity for classification distributions
Hayden S. Helm, Ronak D. Mehta, Brandon Duderstadt +5
Herein we define a measure of similarity between classification distributions that is both principled from the perspective of statistical pattern recognition and useful from the pe…
Simple Lifelong Learning Machines
Jayanta Dey, Joshua T. Vogelstein, Hayden S. Helm +13
In lifelong learning, data are used to improve performance not only on the present task, but also on past and future (unencountered) tasks. While typical transfer learning algorith…