Name: Ashish Jha
Type: User
Company: Skolkovo Institute of Technology
Bio: I am a Machine Learning Researcher and an applied scientist in the field of Neural Network optimization, model compression and video/image compression.
Location: Moscow, Russia
Blog: https://www.linkedin.com/in/ashish-jha-27b1ba93/
Ashish Jha's Projects
Thesis
BTG: Smart Sampling using Balanced Training Gradients
Bayesian Optimization-Based Global Optimal Rank Selection for Compression of Convolutional Neural Networks, IEEE Access
Parallel Implementation of Crib Drag Attack for One Time Pad Key Reuse.
We use low-level attributes ("bash-history") to classify an attack behavior in a CPTC dataset. This repo is the implementation for the paper Cyber Attacker Profiling for Risk Analysis based on Machine Learning.
Code for coreset selection methods
Code for the CVPR 2018 Oral Paper "Deep Layer Aggregation"
Ready-to-use OCR with 80+ supported languages and all popular writing scripts including Latin, Chinese, Arabic, Devanagari, Cyrillic and etc.
eco2AI is a python library which accumulates statistics about power consumption and CO2 emission during running code.
Image and End to End Video Compression
LibAUC: A Deep Learning Library for X-Risk Optimization
Code for visualizing the loss landscape of neural nets
Approximating neural network loss landscapes in low-dimensional parameter subspaces for PyTorch
Implementation of the Lightweight Attribute Specific Localization Model.
Learn how to design, develop, deploy and iterate on production-grade ML applications.
To Test CIFAR-100
Variance Correction for NN Compression
A simple bash script to automate kali tools.