paper-with-me

Papers Permuted-MNIST

“Permuted-MNIST” 태그가 달린 논문 37편 · 필터 해제

Preserving Plasticity in Continual Learning with Adaptive Linearity Injection

2025-05-14 · Seyed Roozbeh Razavi Rohani, Khashayar Khajavi, Wesley Chung, Mo Chen 외

Loss of plasticity in deep neural networks is the gradual reduction in a model's capacity to incrementally learn and has been identified as a key obstacle to learning in non-stationary problem settings. Recent work has s…

class-incremental learningClass Incremental LearningContinual LearningIncremental Learning+1

Bayesian continual learning and forgetting in neural networks

2025-04-18 · Djohan Bonnet, Kellian Cottart, Tifenn Hirtzlin, Tarcisius Januel 외

Biological synapses effortlessly balance memory retention and flexibility, yet artificial neural networks still struggle with the extremes of catastrophic forgetting and catastrophic remembering. Here, we introduce Metap…

Bayesian InferenceContinual Learningimage-classificationImage Classification+2

Exploiting Task Relationships for Continual Learning Using Transferability-Aware Task Embeddings

2025-02-17 · Yanru Wu, Xiangyu Chen, Jianning Wang, Enming Zhang 외

Continual learning (CL) has been an essential topic in the contemporary application of deep neural networks, where catastrophic forgetting (CF) can impede a model's ability to acquire knowledge progressively. Existing CL…

Continual LearningPermuted-MNIST

Disentangling and Mitigating the Impact of Task Similarity for Continual Learning

2024-05-30 · Naoki Hiratani

Continual learning of partially similar tasks poses a challenge for artificial neural networks, as task similarity presents both an opportunity for knowledge transfer and a risk of interference and catastrophic forgettin…

Continual LearningPermuted-MNISTTransfer Learning

Bayesian Metaplasticity from Synaptic Uncertainty

2023-12-15 · Djohan Bonnet, Tifenn Hirtzlin, Tarcisius Januel, Thomas Dalgaty 외

Catastrophic forgetting remains a challenge for neural networks, especially in lifelong learning scenarios. In this study, we introduce MEtaplasticity from Synaptic Uncertainty (MESU), inspired by metaplasticity and Baye…

Bayesian InferenceContinual LearningLifelong learningPermuted-MNIST

Artificial Neuronal Ensembles with Learned Context Dependent Gating

2023-01-17 · Matthew J. Tilley, Michelle Miller, David J. Freedman

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 se…

Continual LearningPermuted-MNISTRotated MNIST

Analysis of Catastrophic Forgetting for Random Orthogonal Transformation Tasks in the Overparameterized Regime

2022-06-01 · Daniel Goldfarb, Paul Hand

Overparameterization is known to permit strong generalization performance in neural networks. In this work, we provide an initial theoretical analysis of its effect on catastrophic forgetting in a continual learning setu…

Continual Learningimage-classificationImage ClassificationPermuted-MNIST

Increasing Depth of Neural Networks for Life-long Learning

2022-02-22 · Jędrzej Kozal, Michał Woźniak

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. Met…

Continual LearningPermuted-MNIST

The CLEAR Benchmark: Continual LEArning on Real-World Imagery

2022-01-17 · Zhiqiu Lin, Jia Shi, Deepak Pathak, Deva Ramanan

Continual learning (CL) is widely regarded as crucial challenge for lifelong AI. However, existing CL benchmarks, e.g. Permuted-MNIST and Split-CIFAR, make use of artificial temporal variation and do not align with or ge…

Continual Learningimage-classificationImage ClassificationPermuted-MNIST+1

Mixture-of-Variational-Experts for Continual Learning

2021-10-25 · Heinke Hihn, Daniel A. Braun

One weakness of machine learning algorithms is the poor ability of models to solve new problems without forgetting previously acquired knowledge. The Continual Learning (CL) paradigm has emerged as a protocol to systemat…

Continual LearningDomain-IL Continual LearningPermuted-MNISTreinforcement-learning+4

Continual Learning with Memory Cascades

2021-09-22 · NeurIPS Workshop ICBINB 2021 12 · David Kappel, Franscesco Negri, Christian Tetzlaff

Continual learning poses an important challenge to machine learning models. Kirkpatrick et al. introduced a model that combats forgetting during continual learning by using a Bayesian prior to transfer knowledge between …

Continual LearningPermuted-MNIST

Shared and Private VAEs with Generative Replay for Continual Learning

2021-05-17 · Subhankar Ghosh

Continual learning tries to learn new tasks without forgetting previously learned ones. In reality, most of the existing artificial neural network(ANN) models fail, while humans do the same by remembering previous works …

Continual LearningPermuted-MNIST

Lifelong Learning with Sketched Structural Regularization

2021-04-17 · Haoran Li, Aditya Krishnan, Jingfeng Wu, Soheil Kolouri 외

Preventing catastrophic forgetting while continually learning new tasks is an essential problem in lifelong learning. Structural regularization (SR) refers to a family of algorithms that mitigate catastrophic forgetting …

Continual LearningLifelong learningPermuted-MNIST

CKConv: Continuous Kernel Convolution For Sequential Data

2021-02-04 · ICLR 2022 4 · David W. Romero, Anna Kuzina, Erik J. Bekkers, Jakub M. Tomczak 외

Conventional neural architectures for sequential data present important limitations. Recurrent networks suffer from exploding and vanishing gradients, small effective memory horizons, and must be trained sequentially. Co…

Permuted-MNISTSequential Image ClassificationTime Series Analysis

Short-Term Memory Optimization in Recurrent Neural Networks by Autoencoder-based Initialization

2020-11-05 · Antonio Carta, Alessandro Sperduti, Davide Bacciu

Training RNNs to learn long-term dependencies is difficult due to vanishing gradients. We explore an alternative solution based on explicit memorization using linear autoencoders for sequences, which allows to maximize t…

MemorizationPermuted-MNIST

HiPPO: Recurrent Memory with Optimal Polynomial Projections

2020-08-17 · NeurIPS 2020 12 · Albert Gu, Tri Dao, Stefano Ermon, Atri Rudra 외

A central problem in learning from sequential data is representing cumulative history in an incremental fashion as more data is processed. We introduce a general framework (HiPPO) for the online compression of continuous…

Permuted-MNISTSequential Image ClassificationTime SeriesTime Series Analysis

Enabling Continual Learning with Differentiable Hebbian Plasticity

2020-06-30 · Vithursan Thangarasa, Thomas Miconi, Graham W. Taylor

Continual learning is the problem of sequentially learning new tasks or knowledge while protecting previously acquired knowledge. However, catastrophic forgetting poses a grand challenge for neural networks performing su…

Continual LearningPermuted-MNISTSplit-MNIST

Multilayer Neuromodulated Architectures for Memory-Constrained Online Continual Learning

2020-06-12 · ICML Workshop LifelongML 2020 7 · Sandeep Madireddy, Angel Yanguas-Gil, Prasanna Balaprakash

We focus on the problem of how to achieve online continual learning under memory-constrained conditions where the input data may not be known \emph{a priori}. These constraints are relevant in edge computing scenarios. W…

Bayesian Optimizationclass-incremental learningClass Incremental LearningContinual Learning+4

Continual Learning with Extended Kronecker-factored Approximate Curvature

2020-04-16 · CVPR 2020 6 · Janghyeon Lee, Hyeong Gwon Hong, Donggyu Joo, Junmo Kim

We propose a quadratic penalty method for continual learning of neural networks that contain batch normalization (BN) layers. The Hessian of a loss function represents the curvature of the quadratic penalty function, and…

Continual LearningGeneral ClassificationPermuted-MNISTvalid

Autoencoder-based Initialization for Recurrent Neural Networks with a Linear Memory

2019-09-25 · Antonio Carta, Alessandro Sperduti, Davide Bacciu

Orthogonal recurrent neural networks address the vanishing gradient problem by parameterizing the recurrent connections using an orthogonal matrix. This class of models is particularly effective to solve tasks that requi…

MemorizationPermuted-MNIST
1–20 / 37 다음 →