Sai Prasath Suresh's Projects
An elaborate study to determine the effects of Adversarial ML in ML/DL based Intrusion Detection Systems used in Power Plants.
Graph Augmented Transformer for Text Classification
Compositional Epidemiology of COVID-19
A complete computer science study plan to become a software engineer.
Implemented various CNN models: AlexNet, LeNet, and VGG16 to perform image classification on the CalTech 101 dataset.
Investigate the problem of covariate shift in real-world datasets and propose continual learning based solutions.
Generate optimal policies to control the spread of the virus by performing multi-model simulations using hybrid timed automata.
Master classic RL, deep RL, distributional RL, inverse RL, and more using OpenAI Gym and TensorFlow with extensive Math
Evaluating hallucinations in domain adapted LLMs
An implement of DQfD(Deep Q-learning from Demonstrations) raised by DeepMind:Learning from Demonstrations for Real World Reinforcement Learning
Federated Learning is a distributed machine learning approach which enables model training on a large corpus of decentralised data. The repository tutorial for using PySyft for distributed training of Machine Learning model.
Study the effectiveness of federated learning models to serve as IDS, and their robustness to adversaries.
Predict and and analyse the state of a power plant, and mitigate the effects in case of any emergency
Developing LSTM/GRU for predicting Google Stock prices.
A collection of machine learning examples and tutorials.
Applied generative adversarial networks (GANs) to do anomaly detection for time series data
Analysed various algorithms including greedy, branch and bound, local search - hill climbing, and local search - simulated annealing for solving the minimum vertex cover (MVC) problem.
Understanding various ML classification models.
Understanding various ML regression models.
A CNN based model for classifying digits in the MNIST dataset.
Modular Code Generation from Hybrid Automata
Personal Website - A store house of all acvities
Developed a dual attention based GRU model for pre-emptively detecting anomalies in a power plant control system.
Code and resources for EMNLP 2022 paper on 'Robustness of Fusion-based Multimodal Classifiers to Cross-Modal Content Dilutions'
Analysing the optimal strategy for using expert demonstrations during online RL after bootstrapping.
Assessing Safety Awareness in LLMs
A beautiful, simple, clean, and responsive Jekyll theme for academics
Graph Augmented Transformer Model for Sequential Movie Recommendation