2 citations · 2 across the 5 of their papers we have counts for
Showing 2020Show all
2 papers · 1 filter
cs.LG2020
The Curious Case of Convex Neural Networks
Sarath Sivaprasad, Ankur Singh, Naresh Manwani +1
In this paper, we investigate a constrained formulation of neural networks where the output is a convex function of the input. We show that the convexity constraints can be enforce…
cs.CV2020
Adversarial Incremental Learning
Ankur Singh
Although deep learning performs really well in a wide variety of tasks, it still suffers from catastrophic forgetting -- the tendency of neural networks to forget previously learne…