Related papers: Scalable and Order-robust Continual Learning with …

Neural networks encounter the challenge of Catastrophic Forgetting (CF) in continual learning, where new task learning interferes with previously learned knowledge. Existing data fine-tuning and regularization methods necessitate task…

The advent of high-capacity pre-trained models has revolutionized problem-solving in computer vision, shifting the focus from training task-specific models to adapting pre-trained models. Consequently, effectively adapting large pre-trained…

A central challenge in continual learning is forgetting, the loss of performance on previously learned tasks induced by sequential adaptation to new ones. While forgetting has been extensively studied empirically, rigorous theoretical…

We introduce the technique of adaptive discretization to design an efficient model-based episodic reinforcement learning algorithm in large (potentially continuous) state-action spaces. Our algorithm is based on optimistic one-step value…

Continual learning refers to the ability of a biological or artificial system to seamlessly learn from continuous streams of information while preventing catastrophic forgetting, i.e., a condition in which new incoming information strongly…

Wearable sensors in Internet of Things (IoT) ecosystems increasingly support applications such as remote health monitoring, elderly care, and smart home automation, all of which rely on robust human activity recognition (HAR). Continual…

Unsupervised Anomaly Detection (UAD) with incremental training is crucial in industrial manufacturing, as unpredictable defects make obtaining sufficient labeled data infeasible. However, continual learning methods primarily rely on…

Continual learning algorithms aim to learn from a sequence of tasks. In order to avoid catastrophic forgetting, most existing approaches rely on heuristics and do not provide computable learning guarantees. In this paper, we introduce…

Neural operators generally demonstrate strong predictive performance on in-distribution (ID) problems. However, a critical limitation of existing methods is their significant performance degradation when encountering out-of-distribution…

The problem of Rehearsal-Free Continual Learning (RFCL) aims to continually learn new knowledge while preventing forgetting of the old knowledge, without storing any old samples and prototypes. The latest methods leverage large-scale…

Prototype-based reconstruction methods for unsupervised anomaly detection utilize a limited set of learnable prototypes which only aggregates insufficient normal information, resulting in undesirable reconstruction. However, increasing the…

Modern representation learning methods often struggle to adapt quickly under non-stationarity because they suffer from catastrophic forgetting and decaying plasticity. Such problems prevent learners from fast adaptation since they may…

Edge devices operating in dynamic environments critically need the ability to continually learn without catastrophic forgetting. The strict resource constraints in these devices pose a major challenge to achieve this, as continual learning…

Prompt-based continual learning methods effectively mitigate catastrophic forgetting. However, most existing methods assign a fixed set of prompts to each task, completely isolating knowledge across tasks and resulting in suboptimal…

Multi-objective combinatorial optimization seeks Pareto-optimal solutions over exponentially large discrete spaces, yet existing methods sacrifice generality, scalability, or theoretical guarantees. We reformulate it as an online learning…

Service robots, in general, have to work independently and adapt to the dynamic changes happening in the environment in real-time. One important aspect in such scenarios is to continually learn to recognize newer object categories when they…

Highly distributed training of Deep Neural Networks (DNNs) on future compute platforms (offering 100 of TeraOps/s of computational capacity) is expected to be severely communication constrained. To overcome this limitation, new gradient…

Continual learning empowers models to learn from a continuous stream of data while preserving previously acquired knowledge, effectively addressing the challenge of catastrophic forgetting. In this study, we propose a new approach that…

Continual learning is considered a promising step towards next-generation Artificial Intelligence (AI), where deep neural networks (DNNs) make decisions by continuously learning a sequence of different tasks akin to human learning…

Adaptive networks today rely on overparameterized fixed topologies that cannot break through the statistical conflicts they encounter in the data they are exposed to, and are prone to "catastrophic forgetting" as the network attempts to…