44 citations · 47 across the 5 of their papers we have counts for
7 papers
Reinitializing weights vs units for maintaining plasticity in neural networks
J. Fernando Hernandez-Garcia, Shibhansh Dohare, Jun Luo +1
Loss of plasticity is a phenomenon in which a neural network loses its ability to learn when trained for an extended time on non-stationary data. It is a crucial problem to overcom…
Maintaining Plasticity in Deep Continual Learning
Shibhansh Dohare, J. Fernando Hernandez-Garcia, Parash Rahman +2
Modern deep-learning systems are specialized to problem settings in which training occurs once and then never again, as opposed to continual-learning settings in which training occ…
Automatic Noise Filtering with Dynamic Sparse Training in Deep Reinforcement Learning
Bram Grooten, Ghada Sokar, Shibhansh Dohare +4
Tomorrow's robots will need to distinguish useful information from noise when performing different tasks. A household robot for instance may continuously receive a plethora of info…
Continual Backprop: Stochastic Gradient Descent with Persistent Randomness
Shibhansh Dohare, Richard S. Sutton, A. Rupam Mahmood
The Backprop algorithm for learning in neural networks utilizes two mechanisms: first, stochastic gradient descent and second, initialization with small random weights, where the l…
Gamma-Nets: Generalizing Value Estimation over Timescale
Craig Sherstan, Shibhansh Dohare, James MacGlashan +2
We present -nets, a method for generalizing value function estimation over timescale. By using the timescale as one of the estimator's inputs we can estimate value for arbitrary…
Text Summarization using Abstract Meaning Representation
Shibhansh Dohare, Harish Karnick, Vivek Gupta
With an ever increasing size of text present on the Internet, automatic summary generation remains an important problem for natural language understanding. In this work we explore…
Variational Inference via Transformations on Distributions
Siddhartha Saxena, Shibhansh Dohare, Jaivardhan Kapoor
Variational inference methods often focus on the problem of efficient model optimization, with little emphasis on the choice of the approximating posterior. In this paper, we revie…