English
Related papers

Related papers: Unsupervised Replay Strategies for Continual Learn…

200 papers

This study explores the learnability of memory-less and memory-augmented RNNs, which are theoretically equivalent to Pushdown Automata. Empirical results show that these models often fail to generalize on longer sequences, relying more on…

Computation and Language · Computer Science 2024-10-07 Shrabon Das , Ankur Mali

Deep artificial neural networks famously struggle to learn from non-stationary streams of data. Without dedicated mitigation strategies, continual learning is associated with continuous forgetting of previous tasks and a progressive loss of…

Neurons and Cognition · Quantitative Biology 2025-12-29 Suzanne van der Veldt , Gido M. van de Ven , Sanne Moorman , Guillaume Etter

Artificial neural networks encounter a notable challenge known as continual learning, which involves acquiring knowledge of multiple tasks over an extended period. This challenge arises due to the tendency of previously learned weights to…

Computer Vision and Pattern Recognition · Computer Science 2023-11-28 Yonatan Sverdlov , Shimon Ullman

Recurrent Neural Networks (RNNs) continue to show outstanding performance in sequence modeling tasks. However, training RNNs on long sequences often face challenges like slow inference, vanishing gradients and difficulty in capturing long…

Artificial Intelligence · Computer Science 2018-02-06 Victor Campos , Brendan Jou , Xavier Giro-i-Nieto , Jordi Torres , Shih-Fu Chang

The ability to learn continuously from an incoming data stream without catastrophic forgetting is critical to designing intelligent systems. Many approaches to continual learning rely on stochastic gradient descent and its variants that…

Machine Learning · Computer Science 2023-08-10 Sandeep Madireddy , Angel Yanguas-Gil , Prasanna Balaprakash

The human brain is the gold standard of adaptive learning. It not only can learn and benefit from experience, but also can adapt to new situations. In contrast, deep neural networks only learn one sophisticated but fixed mapping from inputs…

Computer Vision and Pattern Recognition · Computer Science 2021-03-18 Shixian Wen , Amanda Rios , Yunhao Ge , Laurent Itti

Training time budget and size of the dataset are among the factors affecting the performance of a Deep Neural Network (DNN). This paper shows that Neural Architecture Search (NAS), Hyper Parameters Optimization (HPO), and Data Augmentation…

Machine Learning · Computer Science 2023-01-24 Mahdi Zolnouri , Dounia Lakhmiri , Christophe Tribes , Eyyüb Sari , Sébastien Le Digabel

Training Deep Neural Networks (DNNs) is still highly time-consuming and compute-intensive. It has been shown that adapting a pretrained model may significantly accelerate this process. With a focus on classification, we show that current…

Neural and Evolutionary Computing · Computer Science 2020-12-01 Farshid Varno , Lucas May Petry , Lisa Di Jorio , Stan Matwin

Biological neural networks are capable of recruiting different sets of neurons to encode different memories. However, when training artificial neural networks on a set of tasks, typically, no mechanism is employed for selectively producing…

Machine Learning · Computer Science 2023-05-17 Matthew J. Tilley , Michelle Miller , David J. Freedman

The effectiveness of recurrent neural networks can be largely influenced by their ability to store into their dynamical memory information extracted from input sequences at different frequencies and timescales. Such a feature can be…

Machine Learning · Computer Science 2020-07-01 Antonio Carta , Alessandro Sperduti , Davide Bacciu

To survive in the dynamically-evolving world, we accumulate knowledge and improve our skills based on experience. In the process, gaining new knowledge does not disrupt our vigilance to external stimuli. In other words, our learning process…

Machine Learning · Computer Science 2019-02-05 Jung H. Lee

The field of artificial intelligence faces significant challenges in achieving both biological plausibility and computational efficiency, particularly in visual learning tasks. Current artificial neural networks, such as convolutional…

Machine Learning · Computer Science 2024-09-27 Jacobo Ruiz , Manas Gupta

Deep neural networks are used in many state-of-the-art systems for machine perception. Once a network is trained to do a specific task, e.g., bird classification, it cannot easily be trained to do new tasks, e.g., incrementally learning to…

Artificial Intelligence · Computer Science 2017-11-10 Ronald Kemker , Marc McClure , Angelina Abitino , Tyler Hayes , Christopher Kanan

Lifelong learning aims to develop machine learning systems that can learn new tasks while preserving the performance on previous learned tasks. In this paper we present a method to overcome catastrophic forgetting on convolutional neural…

Machine Learning · Computer Science 2018-05-10 Abel S. Zacarias , Luís A. Alexandre

We consider dense, associative neural-networks trained by a teacher (i.e., with supervision) and we investigate their computational capabilities analytically, via statistical-mechanics of spin glasses, and numerically, via Monte Carlo…

Disordered Systems and Neural Networks · Physics 2023-08-16 Elena Agliari , Linda Albanese , Francesco Alemanno , Andrea Alessandrelli , Adriano Barra , Fosca Giannotti , Daniele Lotito , Dino Pedreschi

Artificial neural networks often struggle with catastrophic forgetting when learning multiple tasks sequentially, as training on new tasks degrades the performance on previously learned tasks. Recent theoretical work has addressed this…

Machine Learning · Computer Science 2025-09-10 Francesco Mori , Stefano Sarao Mannelli , Francesca Mignacco

We explore the behavior of a standard convolutional neural net in a continual-learning setting that introduces visual classification tasks sequentially and requires the net to master new tasks while preserving mastery of previously learned…

Machine Learning · Computer Science 2020-04-01 Guy Davidson , Michael C. Mozer

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…

Machine Learning · Computer Science 2022-04-12 Johannes von Oswald , Christian Henning , Benjamin F. Grewe , João Sacramento

Artificial neural networks (ANNs) require tremendous amount of data to train on. However, in classification models, most data features are often similar which can lead to increase in training time without significant improvement in the…

Machine Learning · Computer Science 2023-03-03 Sreelekha Guggilam , Varun Chandola , Abani Patra

Imitation learning considerably simplifies policy synthesis compared to alternative approaches by exploiting access to expert demonstrations. For such imitation policies, errors away from the training samples are particularly critical. Even…

Machine Learning · Computer Science 2024-03-19 Kaustubh Sridhar , Souradeep Dutta , Dinesh Jayaraman , James Weimer , Insup Lee