36 citations · 76 across the 19 of their papers we have counts for
15 papers · 1 filter
Sparse Autoencoders Can Induce Local Geometry for Mitigating Catastrophic Forgetting
Kamil Faber, Katarzyna Filus, Łukasz Pawela
Catastrophic forgetting remains a challenge in supervised continual learning, as adapting to new tasks causes representation drift and loss of previously learned information. This…
PRISM: Powerful Time Series to Image (TS2I) Representations for Multivariate Anomaly Detection
Mateusz Smendowski, Kamil Faber, Piotr Nawrocki +2
Time series anomaly detection (TSAD) underpins applications in predictive maintenance, finance, and cloud computing, however performance remains sensitive to representation choices…
Towards Principled Continual Anomaly Detection: A Systematic Framework and Benchmark Scenarios
Kamil Faber, Mateusz Smendowski, Roberto Corizzo
Continual anomaly detection (CAD) studies how models can adapt to evolving data distributions while retaining performance on previously observed regimes. CAD benchmarks, however, d…
Lost or Hidden? A Concept-Level Forgetting in Supervised Continual Learning
Katarzyna Filus, Kamil Faber, Roberto Corizzo +1
Continual learning studies how models can adapt to new tasks while retaining previously acquired knowledge. Although a broad spectrum of methods has been proposed to mitigate catas…
TSN-Affinity: Similarity-Driven Parameter Reuse for Continual Offline Reinforcement Learning
Dominik Żurek, Kamil Faber, Marcin Pietron +2
Continual offline reinforcement learning (CORL) aims to learn a sequence of tasks from datasets collected over time while preserving performance on previously learned tasks. This s…
Rethinking the Harmonic Loss via Non-Euclidean Distance Layers
Maxwell Miller-Golub, Collin Coil, Kamil Faber +4
Cross-entropy loss has long been the standard choice for training deep neural networks, yet it suffers from interpretability limitations, unbounded weight growth, and inefficiencie…
xLSTMAD: A Powerful xLSTM-based Method for Anomaly Detection
Kamil Faber, Marcin Pietroń, Dominik Żurek +1
The recently proposed xLSTM is a powerful model that leverages expressive multiplicative gating and residual connections, providing the temporal capacity needed for long-horizon fo…
TinySubNets: An efficient and low capacity continual learning strategy
Marcin Pietroń, Kamil Faber, Dominik Żurek +1
Continual Learning (CL) is a highly relevant setting gaining traction in recent machine learning research. Among CL works, architectural and hybrid strategies are particularly effe…
Towards efficient deep autoencoders for multivariate time series anomaly detection
Marcin Pietroń, Dominik Żurek, Kamil Faber +1
Multivariate time series anomaly detection is a crucial problem in many industrial and research applications. Timely detection of anomalies allows, for instance, to prevent defects…
Ada-QPacknet -- adaptive pruning with bit width reduction as an efficient continual learning method without forgetting
Marcin Pietroń, Dominik Żurek, Kamil Faber +1
Continual Learning (CL) is a process in which there is still huge gap between human and deep learning model efficiency. Recently, many CL algorithms were designed. Most of them hav…
AD-NEV: A Scalable Multi-level Neuroevolution Framework for Multivariate Anomaly Detection
Marcin Pietron, Dominik Zurek, Kamil Faber +1
Anomaly detection tools and methods present a key capability in modern cyberphysical and failure prediction systems. Despite the fast-paced development in deep learning architectur…
From MNIST to ImageNet and Back: Benchmarking Continual Curriculum Learning
Kamil Faber, Dominik Zurek, Marcin Pietron +3
Continual learning (CL) is one of the most promising trends in recent machine learning research. Its goal is to go beyond classical assumptions in machine learning and develop mode…
Lifelong Continual Learning for Anomaly Detection: New Challenges, Perspectives, and Insights
Kamil Faber, Roberto Corizzo, Bartlomiej Sniezynski +1
Anomaly detection is of paramount importance in many real-world domains, characterized by evolving behavior. Lifelong learning represents an emerging trend, answering the need for…
System Design for an Integrated Lifelong Reinforcement Learning Agent for Real-Time Strategy Games
Indranil Sur, Zachary Daniels, Abrar Rahman +16
As Artificial and Robotic Systems are increasingly deployed and relied upon for real-world applications, it is important that they exhibit the ability to continually learn and adap…
Ensemble neuroevolution based approach for multivariate time series anomaly detection
Kamil Faber, Dominik Żurek, Marcin Pietroń +1
Multivariate time series anomaly detection is a very common problem in the field of failure prevention. Fast prevention means lower repair costs and losses. The amount of sensors i…