1 citations · 1 across the 2 of their papers we have counts for
3 papers · 1 filter
OR Else: A Differentiable Trust Region for Policy Optimization
Chinmay Rane, Kanishka Tyagi, Michael Manry
PPO and the GRPO baseline studied here use clipped surrogate objectives whose favorable-direction saturation introduces an abrupt change in the scalar objective's derivative. We as…
Making Sigmoid-MSE Great Again: Output Reset Challenges Softmax Cross-Entropy in Neural Network Classification
Kanishka Tyagi, Chinmay Rane, Ketaki Vaidya +3
This study presents a comparative analysis of two objective functions, Mean Squared Error (MSE) and Softmax Cross-Entropy (SCE) for neural network classification tasks. While SCE c…
Optimizing Performance of Feedforward and Convolutional Neural Networks through Dynamic Activation Functions
Chinmay Rane, Kanishka Tyagi, Michael Manry
Deep learning training training algorithms are a huge success in recent years in many fields including speech, text,image video etc. Deeper and deeper layers are proposed with huge…