4 papers
Continual Learning via Ensemble-Based Depth-Wise Masked Autoencoders for Data Quality Monitoring in High-Energy Physics
Dale Julson, Eric Reinhardt, Andrii Krutsylo +5
Machine learning (ML) techniques have been demonstrated to improve the accuracy and efficiency of anomaly detection (AD) when compared to conventional methods. This has led to the…
Non-Uniform Memory Sampling in Experience Replay
Andrii Krutsylo
Continual learning is the process of training machine learning models on a sequence of tasks where data distributions change over time. A well-known obstacle in this setting is cat…
Scalable Forward-Forward Algorithm
Andrii Krutsylo
We propose a scalable Forward-Forward (FF) algorithm that eliminates the need for backpropagation by training each layer separately. Unlike backpropagation, FF avoids backward grad…
Continually Learn to Map Visual Concepts to Large Language Models in Resource-constrained Environments
Clea Rebillard, Julio Hurtado, Andrii Krutsylo +2
Learning continually from a stream of non-i.i.d. data is an open challenge in deep learning, even more so when working in resource-constrained environments such as embedded devices…