2 citations · 2 across the 6 of their papers we have counts for
6 papers
Mechanistic Interpretability of GPT-2: Lexical and Contextual Layers in Sentiment Analysis
Amartya Hatua
We present a mechanistic interpretability study of GPT-2 that causally examines how sentiment information is processed across its transformer layers. Using systematic activation pa…
Machine Unlearning using Forgetting Neural Networks
Amartya Hatua, Trung T. Nguyen, Filip Cano +1
Modern computer systems store vast amounts of personal data, enabling advances in AI and ML but risking user privacy and trust. For privacy reasons, it is sometimes desired for an…
Machine Unlearning using a Multi-GAN based Model
Amartya Hatua, Trung T. Nguyen, Andrew H. Sung
This article presents a new machine unlearning approach that utilizes multiple Generative Adversarial Network (GAN) based models. The proposed method comprises two phases: i) data…
AI-Enhanced Data Processing and Discovery Crowd Sourcing for Meteor Shower Mapping
Siddha Ganju, Amartya Hatua, Peter Jenniskens +3
The Cameras for Allsky Meteor Surveillance (CAMS) project, funded by NASA starting in 2010, aims to map our meteor showers by triangulating meteor trajectories detected in low-ligh…
Claim Verification using a Multi-GAN based Model
Amartya Hatua, Arjun Mukherjee, Rakesh M. Verma
This article describes research on claim verification carried out using a multiple GAN-based model. The proposed model consists of three pairs of generators and discriminators. The…
Optimal Feature Selection from VMware ESXi 5.1 Feature Set
Amartya Hatua
A study of VMware ESXi 5.1 server has been carried out to find the optimal set of parameters which suggest usage of different resources of the server. Feature selection algorithms…