Results 41 to 50 of about 6,336,923 (296)
Continual learning with hypernetworks
CoRR, 2019 Artificial neural networks suffer from catastrophic forgetting when they are sequentially trained on multiple tasks. To overcome this problem, we present a novel approach based on task-conditioned hypernetworks, i.e., networks that generate the weights of a target model based on task identity. Continual learning (CL) is less difficult for this class of
von Oswald, Johannes +3 more
openaire +5 more sources
Continual Learning for Steganalysis
CoRR, 2022 To detect the existing steganographic algorithms, recent steganalysis methods usually train a Convolutional Neural Network (CNN) model on the dataset consisting of corresponding paired cover/stego-images. However, it is inefficient and impractical for those steganalysis tools to completely retrain the CNN model to make it effective against both the ...
Zihao Yin, Ruohan Meng, Zhili Zhou 0001
openaire +3 more sources
Continual Learning and Fairness Techniques for Pathology Classification of Chest X-ray Images [PDF]
, 2023 openIn recent years, Deep Learning (DL) techniques have been successfully applied to various medical applications, achieving remarkable results. In particular, in the field of medical imaging, Deep Learning models have reached human-level performance ...
CECCON, MARINA
core
Continual learning using Bayesian neural networks [PDF]
, 2020 Continual learning models allow them to learn and adapt to new changes and tasks over time. However, in continual and sequential learning scenarios, in which the models are trained using different data with various distributions, neural networks (NNs ...
Enshaeifar, Shirin +3 more
core +1 more source
Neuro-Symbolic Continual Learning: Knowledge, Reasoning Shortcuts and Concept Rehearsal [PDF]
, 2023 We introduce Neuro-Symbolic Continual Learning, where a model has to solve a sequence of neuro-symbolic tasks, that is, it has to map sub-symbolic inputs to high-level concepts and compute predictions by reasoning consistently with prior knowledge.
Teso S. +5 more
core +1 more source
Metrics and Continuity in Reinforcement Learning
Proceedings of the AAAI Conference on Artificial Intelligence, 2021 In most practical applications of reinforcement learning, it is untenable to maintain direct estimates for individual states; in continuous-state systems, it is impossible. Instead, researchers often leverage {\em state similarity} (whether explicitly or implicitly) to build models that can generalize well from a limited set of samples.
Charline Le Lan +2 more
openaire +3 more sources
Unsupervised Learning to Overcome Catastrophic Forgetting in Neural Networks
IEEE Journal on Exploratory Solid-State Computational Devices and Circuits, 2019 Continual learning is the ability to acquire a new task or knowledge without losing any previously collected information. Achieving continual learning in artificial intelligence (AI) is currently prevented by catastrophic forgetting, where training of a ...
Irene Munoz-Martin +5 more
doaj +1 more source
Gradient-Free Continual Learning
IEEE AccessNeural networks are notorious for forgetting old skills when taught new ones - a problem known as catastrophic forgetting. Standard continual learning techniques try to fix this by saving old data or relying on complex gradient updates, but these methods
Grzegorz Rypesc
doaj +1 more source
Homeostasis-Inspired Continual Learning: Learning to Control Structural Regularization
IEEE Access, 2021 Learning continually without forgetting might be one of the ultimate goals for building artificial intelligence (AI). However, unless there are enough resources equipped, forgetting knowledge acquired in the past is inevitable.
Joonyoung Kim +3 more
doaj +1 more source
Universal Graph Continual Learning [PDF]
, 2023 We address catastrophic forgetting issues in graph learning as the arrival of new data from diverse task distributions often leads graph models to prioritize the current task, causing them to forget valuable insights from previous tasks.
Nguyen, Bao Sinh +5 more
core