Picture for Snehanshu Saha

Snehanshu Saha

A Granger-Causal Perspective on Gradient Descent with Application to Pruning

Add code
Dec 04, 2024
Viaarxiv icon

Quantile Activation: departing from single point estimation for better generalization across distortions

Add code
May 19, 2024
Viaarxiv icon

Can Tree Based Approaches Surpass Deep Learning in Anomaly Detection? A Benchmarking Study

Add code
Feb 26, 2024
Viaarxiv icon

Strong convexity-guided hyper-parameter optimization for flatter losses

Add code
Feb 07, 2024
Viaarxiv icon

DeliverAI: Reinforcement Learning Based Distributed Path-Sharing Network for Food Deliveries

Add code
Nov 03, 2023
Figure 1 for DeliverAI: Reinforcement Learning Based Distributed Path-Sharing Network for Food Deliveries
Figure 2 for DeliverAI: Reinforcement Learning Based Distributed Path-Sharing Network for Food Deliveries
Figure 3 for DeliverAI: Reinforcement Learning Based Distributed Path-Sharing Network for Food Deliveries
Figure 4 for DeliverAI: Reinforcement Learning Based Distributed Path-Sharing Network for Food Deliveries
Viaarxiv icon

To prune or not to prune : A chaos-causality approach to principled pruning of dense neural networks

Add code
Aug 19, 2023
Viaarxiv icon

Decoupling Quantile Representations from Loss Functions

Add code
Apr 25, 2023
Viaarxiv icon

Correcting Model Misspecification via Generative Adversarial Networks

Add code
Apr 07, 2023
Viaarxiv icon

Quantile LSTM: A Robust LSTM for Anomaly Detection In Time Series Data

Add code
Feb 17, 2023
Viaarxiv icon

Investigation of a Machine learning methodology for the SKA pulsar search pipeline

Add code
Sep 09, 2022
Figure 1 for Investigation of a Machine learning methodology for the SKA pulsar search pipeline
Figure 2 for Investigation of a Machine learning methodology for the SKA pulsar search pipeline
Figure 3 for Investigation of a Machine learning methodology for the SKA pulsar search pipeline
Figure 4 for Investigation of a Machine learning methodology for the SKA pulsar search pipeline
Viaarxiv icon