incremental learning experiments

Infrastructure prototype for public security systems with AI integration for automatic anomaly detection in surveillance videos

My personal experimental setups for Continual Learning research. Don't think it'll be useful for anyone, but who knows!

Continual Learning Model for Multi-class Text Classification based on Replay Method

Dive into the forefront of Large Language Models (LLMs) with our concise guide on the top 10 hot topics. Explore bias mitigation, efficient training, multimodal models, and more. Stay abreast of the latest advancements shaping the landscape of LLMs.

Forecasting System for Continual Learning Scenarios based on Hoeffding Trees With Change Point Detection Mechanism

Code with experiments from paper "Continual learning for computer security"

Toward Automated Continual Learning (for fully auto-adaptive learning methods and systems). Here, is a list of materials useful to realize this project.

Bayesian continual learning

Continuous learning applied to the development of a Chatbot based on Sequence-To-Sequence architecture

Task Conditional Neural Networks (TCNN) leverage the probabilistic neural networks to estimate the probability density of the training samples. Then produce the task likelihood during the test state to fire the task-specific neurons correspondin to the test sampels. TCNN can detect and learn the new tasks fully-automatically without informing th…

Stream: A Generalized Continual Learning Benchmark and Baseline

Latent Replay for Continual Learning on Edge devices with Efficient Architectures

Towards Rehearsal-based Continual Learning at Scale: distributed CL with Horovod + PyTorch

Continual learning selective nets algorithms

Variational continual learning of a conditional diffusion model to generate MNIST. Based on 'Conditional Diffusion MNIST'.

Code for CPAL-2024 paper "Continual Learning with Dynamic Sparse Training: Exploring Algorithms for Effective Model Updates"

Repository for my Bachelor Thesis at Karlsruhe Institute of Technology.

The KKP Blood Screening Project is a web application designed for blood analysis using YOLOv5 object detection model deployed with Flask. This application allows users to upload an image and receive a labeled result indicating various blood cell types. The model is trained to detect 11 classes of blood cells

Continual Learning code for SRe2L paper (NeurIPS 2023 spotlight)