Related papers: ProDER: A Continual Learning Approach for Fault Pr…

Learning multiple tasks sequentially without forgetting previous knowledge, called Continual Learning(CL), remains a long-standing challenge for neural networks. Most existing methods rely on additional network capacity or data replay. In…

We investigate the replay buffer in rehearsal-based approaches for graph continual learning (GCL) methods. Existing rehearsal-based GCL methods select the most representative nodes for each class and store them in a replay buffer for later…

Purpose: We propose a novel method for continual learning based on the increasing depth of neural networks. This work explores whether extending neural network depth may be beneficial in a life-long learning setting. Methods: We propose a…

Electricity load forecasting is an essential task within smart grids to assist demand and supply balance. While advanced deep learning models require large amounts of high-resolution data for accurate short-term load predictions,…

Accurate fault detection and localization in electrical distribution systems is crucial, especially with the increasing integration of distributed energy resources (DERs), which inject greater variability and complexity into grid…

Neuromorphic Continual Learning (NCL) paradigm leverages Spiking Neural Networks (SNNs) to enable continual learning (CL) capabilities for AI systems to adapt to dynamically changing environments. Currently, the state-of-the-art employ a…

Smart power grids are one of the most complex cyber-physical systems, delivering electricity from power generation stations to consumers. It is critically important to know exactly the current state of the system as well as its state…

In Continual learning (CL) balancing effective adaptation while combating catastrophic forgetting is a central challenge. Many of the recent best-performing methods utilize various forms of prior task data, e.g. a replay buffer, to tackle…

The area of Smart Power Grids needs to constantly improve its efficiency and resilience, to pro-vide high quality electrical power, in a resistant grid, managing faults and avoiding failures. Achieving this requires high component…

Efficient exploration has presented a long-standing challenge in reinforcement learning, especially when rewards are sparse. A developmental system can overcome this difficulty by learning from both demonstrations and self-exploration.…

A continual learning (CL) algorithm learns from a non-stationary data stream. The non-stationarity is modeled by some schedule that determines how data is presented over time. Most current methods make strong assumptions on the schedule and…

Continual learning is a machine learning sub-field specialized in settings with non-iid data. Hence, the training data distribution is not static and drifts through time. Those drifts might cause interferences in the trained model and…

Power grids play a very important role in delivering electrical energy to homes, industries and other places that require it. Because of this increased demand they are facing a great challenge of voltage variations. This happens due to…

The paradigm shift in the electric power grid necessitates a revisit of existing control methods to ensure the grid's security and resilience. In particular, the increased uncertainties and rapidly changing operational conditions in power…

Growing concerns surrounding AI safety and data privacy have driven the development of Machine Unlearning as a potential solution. However, current machine unlearning algorithms are designed to complement the offline training paradigm. The…

Though deep learning has pushed the boundaries of classification forward, in recent years hints of the limits of standard classification have begun to emerge. Problems such as fooling, adding new classes over time, and the need to retrain…

The emergence of large pre-trained networks has revolutionized the AI field, unlocking new possibilities and achieving unprecedented performance. However, these models inherit a fundamental limitation from traditional Machine Learning…

All-in-One Image Restoration (AiOIR), which addresses diverse degradation types with a unified model, presents significant challenges in designing task-aware prompts that effectively guide restoration across multiple degradation scenarios.…

Binary security has increasingly relied on deep learning to reason about malware behavior and program semantics. However, the performance often degrades as threat landscapes evolve and code representations shift. While continual learning…

Continual learning, also known as lifelong learning or incremental learning, refers to the process by which a model learns from a stream of incoming data over time. A common problem in continual learning is the classification layer's bias…