LyCIL: A Pytorch-Lightning 2.x Toolbox for Continual/Incremental Learning.

The efficient SMT-based context-bounded model checker (ESBMC)

Train, Evaluate, Optimize, Deploy Computer Vision Models via OpenVINO™

Hazard! is a local "hot-seat" game for two to six players developed using Windows Presentation Foundation (WPF).

Welcome to my GitHub page!

Online Anomaly Detection

Neurapath is specifically tailored for evidence based effective studying with help of evidence based methods such as: spaced repetition (SM2), interleaved practice and incremental reading.

Focuses on parameter isolation methods for continual learning, where each task uses separate parameter masks or subnetworks to prevent forgetting. Implements Hard Attention to the Task (HAT), Supermask Superposition (SupSup), and Piggyback, with visualization tools and metrics for task overlap and capacity usage.

Implements dynamic and expandable architectures for continual learning — where networks grow or prune over tasks to balance plasticity and stability. Includes Progressive Neural Networks, Dynamically Expandable Networks (DEN), and PackNet, with utilities for parameter freez

A replay-based continual learning, where models preserve past knowledge through stored exemplars or pseudo-samples. Implements Experience Replay (ER), Gradient Episodic Memory (GEM), and iCaRL. Provides modular dataset buffering, memory selection policies, and evaluation utilities for reproducible experiments on vision and NLP tasks.

Implements regularization-based continual learning strategies that mitigate catastrophic forgetting by penalizing large parameter changes. Includes reproducible implementations of EWC, Synaptic Intelligence (SI), and Memory Aware Synapses (MAS) with experiment scripts and benchmark evaluations on Split-MNIST, Permuted-MNIST, and CIFAR-100.

This is the official repo of MLLM-CL.

🧠 API with Machine Learning (FastAPI + Scikit-learn + DDD) that learns continuously from user feedback.

🌊 Online machine learning in Python

A fast, secure, and continuously evolving sentiment analysis platform powered by MERN and Machine Learning. Supports incremental learning for real-time accuracy improvements!

A fast, secure, and continuously evolving sentiment analysis platform powered by MERN and Machine Learning. Supports incremental learning for real-time accuracy improvements!

A neural network approach using Soft Elliptical Radial Basis Functions for intelligent non-convex shape classification with incremental learning and real-time visualization.

Integrating Task-Specific and Universal Adapters for Pre-Trained Model-based Class-Incremental Learning (ICCV 2025)

A multi-agent system that is used to search and recommend products based on semantic and keyword search.