3 citations · 6 across the 3 of their papers we have counts for
3 papers
RDA: Reward Design Agent for Reinforcement Learning
Hojoon Lee, Ajay Subramanian, Ben Abbatematteo +4
Reinforcement learning has enabled the acquisition of impressive robotic skills, but typically requires hand-crafted reward functions that are slow to design and difficult to align…
Spatial-frequency channels, shape bias, and adversarial robustness
Ajay Subramanian, Elena Sizikova, Najib J. Majaj +1
What spatial frequency information do humans and neural networks use to recognize objects? In neuroscience, critical band masking is an established tool that can reveal the frequen…
SATBench: Benchmarking the speed-accuracy tradeoff in object recognition by humans and dynamic neural networks
Ajay Subramanian, Sara Price, Omkar Kumbhar +3
The core of everyday tasks like reading and driving is active object recognition. Attempts to model such tasks are currently stymied by the inability to incorporate time. People sh…