115 citations · 204 across the 30 of their papers we have counts for
11 papers · 1 filter
To prune or not to prune : A chaos-causality approach to principled pruning of dense neural networks
Rajan Sahu, Shivam Chadha, Nithin Nagaraj +2
Reducing the size of a neural network (pruning) by removing weights without impacting its performance is an important problem for resource-constrained devices. In the past, pruning…
Correcting Model Misspecification via Generative Adversarial Networks
Pronoma Banerjee, Manasi V Gude, Rajvi J Sampat +3
Machine learning models are often misspecified in the likelihood, which leads to a lack of robustness in the predictions. In this paper, we introduce a framework for correcting lik…
Quantile LSTM: A Robust LSTM for Anomaly Detection In Time Series Data
Snehanshu Saha, Jyotirmoy Sarkar, Soma Dhavala +2
Anomalies refer to the departure of systems and devices from their normal behaviour in standard operating conditions. An anomaly in an industrial device can indicate an upcoming fa…
A Swarm Variant for the Schrödinger Solver
Urvil Nileshbhai Jivani, Omatharv Bharat Vaidya, Anwesh Bhattacharya +1
This paper introduces application of the Exponentially Averaged Momentum Particle Swarm Optimization (EM-PSO) as a derivative-free optimizer for Neural Networks. It adopts PSO's ma…
Estimation and Applications of Quantiles in Deep Binary Classification
Anuj Tambwekar, Anirudh Maiya, Soma Dhavala +1
Quantile regression, based on check loss, is a widely used inferential paradigm in Econometrics and Statistics. The conditional quantiles provide a robust alternative to classical…
LALR: Theoretical and Experimental validation of Lipschitz Adaptive Learning Rate in Regression and Neural Networks
Snehanshu Saha, Tejas Prashanth, Suraj Aralihalli +3
We propose a theoretical framework for an adaptive learning rate policy for the Mean Absolute Error loss function and Quantile loss function and evaluate its effectiveness for regr…
Parsimonious Computing: A Minority Training Regime for Effective Prediction in Large Microarray Expression Data Sets
Shailesh Sridhar, Snehanshu Saha, Azhar Shaikh +2
Rigorous mathematical investigation of learning rates used in back-propagation in shallow neural networks has become a necessity. This is because experimental evidence needs to be…
ChaosNet: A Chaos based Artificial Neural Network Architecture for Classification
Harikrishnan Nellippallil Balakrishnan, Aditi Kathpalia, Snehanshu Saha +1
Inspired by chaotic firing of neurons in the brain, we propose ChaosNet -- a novel chaos based artificial neural network architecture for classification tasks. ChaosNet is built us…
LipschitzLR: Using theoretically computed adaptive learning rates for fast convergence
Rahul Yedida, Snehanshu Saha, Tejas Prashanth
Optimizing deep neural networks is largely thought to be an empirical process, requiring manual tuning of several hyper-parameters, such as learning rate, weight decay, and dropout…
SBAF: A New Activation Function for Artificial Neural Net based Habitability Classification
Snehanshu Saha, Archana Mathur, Kakoli Bora +2
We explore the efficacy of using a novel activation function in Artificial Neural Networks (ANN) in characterizing exoplanets into different classes. We call this Saha-Bora Activat…
Predicting the direction of stock market prices using random forest
Luckyson Khaidem, Snehanshu Saha, Sudeepa Roy Dey
Predicting trends in stock market prices has been an area of interest for researchers for many years due to its complex and dynamic nature. Intrinsic volatility in stock market acr…