36 citations · 247 across the 59 of their papers we have counts for
6 papers · 1 filter
Optimizing Learning Rate Schedules for Iterative Pruning of Deep Neural Networks
Shiyu Liu, Rohan Ghosh, John Tan Chong Min +1
The importance of learning rate (LR) schedules on network pruning has been observed in a few recent works. As an example, Frankle and Carbin (2019) highlighted that winning tickets…
Improving Mutual Information based Feature Selection by Boosting Unique Relevance
Shiyu Liu, Mehul Motani
Mutual Information (MI) based feature selection makes use of MI to evaluate each feature and eventually shortlists a relevant feature subset, in order to address issues associated…
AP: Selective Activation for De-sparsifying Pruned Neural Networks
Shiyu Liu, Rohan Ghosh, Dylan Tan +1
The rectified linear unit (ReLU) is a highly successful activation function in neural networks as it allows networks to easily obtain sparse representations, which reduces overfitt…
Towards Better Long-range Time Series Forecasting using Generative Forecasting
Shiyu Liu, Rohan Ghosh, Mehul Motani
Long-range time series forecasting is usually based on one of two existing forecasting strategies: Direct Forecasting and Iterative Forecasting, where the former provides low bias,…
DropNet: Reducing Neural Network Complexity via Iterative Pruning
John Tan Chong Min, Mehul Motani
Modern deep neural networks require a significant amount of computing time and power to train and deploy, which limits their usage on edge devices. Inspired by the iterative weight…
Brick Tic-Tac-Toe: Exploring the Generalizability of AlphaZero to Novel Test Environments
John Tan Chong Min, Mehul Motani
Traditional reinforcement learning (RL) environments typically are the same for both the training and testing phases. Hence, current RL methods are largely not generalizable to a t…