Papers Split-MNIST
“Split-MNIST” 태그가 달린 논문 28편 · 필터 해제
A Neural Network Model of Complementary Learning Systems: Pattern Separation and Completion for Continual Learning
Learning new information without forgetting prior knowledge is central to human intelligence. In contrast, neural network models suffer from catastrophic forgetting: a significant degradation in performance on previously…
Continual LearningSplit-MNISTTask-conditioned Ensemble of Expert Models for Continuous Learning
One of the major challenges in machine learning is maintaining the accuracy of the deployed model (e.g., a classifier) in a non-stationary environment. The non-stationary environment results in distribution shifts and, c…
Split-MNISTOn Sequential Loss Approximation for Continual Learning
We introduce for continual learning Autodiff Quadratic Consolidation (AQC), which approximates the previous loss function with a quadratic function, and Neural Consolidation (NC), which approximates the previous loss fun…
class-incremental learningClass Incremental LearningContinual LearningIncremental Learning+1Active Dendrites Enable Efficient Continual Learning in Time-To-First-Spike Neural Networks
While the human brain efficiently adapts to new tasks from a continuous stream of information, neural network models struggle to learn from sequential information without catastrophically forgetting previously learned ta…
Continual LearningSplit-MNISTHard ASH: Sparsity and the right optimizer make a continual learner
In class incremental learning, neural networks typically suffer from catastrophic forgetting. We show that an MLP featuring a sparse activation function and an adaptive learning rate optimizer can compete with establishe…
class-incremental learningClass Incremental LearningIncremental LearningSplit-MNISTAutomating Continual Learning
General-purpose learning systems should improve themselves in open-ended fashion in ever-changing environments. Conventional learning algorithms for neural networks, however, suffer from catastrophic forgetting (CF) -- p…
Continual Learningimage-classificationImage ClassificationMeta-Learning+1Negotiated Representations to Prevent Forgetting in Machine Learning Applications
Catastrophic forgetting is a significant challenge in the field of machine learning, particularly in neural networks. When a neural network learns to perform well on a new task, it often forgets its previously acquired k…
Continual LearningImage ClassificationSplit-CIFAR-10Split-MNISTElephant Neural Networks: Born to Be a Continual Learner
Catastrophic forgetting remains a significant challenge to continual learning for decades. While recent works have proposed effective methods to mitigate this problem, they mainly focus on the algorithmic side. Meanwhile…
class-incremental learningClass Incremental LearningContinual LearningIncremental Learning+1Towards Robust Continual Learning with Bayesian Adaptive Moment Regularization
The pursuit of long-term autonomy mandates that machine learning models must continuously adapt to their changing environments and learn to solve new tasks. Continual learning seeks to overcome the challenge of catastrop…
Continual LearningSplit-MNISTImproving Performance in Continual Learning Tasks using Bio-Inspired Architectures
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 i…
Continual LearningSplit-CIFAR-10Split-MNISTBio-Inspired, Task-Free Continual Learning through Activity Regularization
The ability to sequentially learn multiple tasks without forgetting is a key skill of biological brains, whereas it represents a major challenge to the field of deep learning. To avoid catastrophic forgetting, various co…
Continual LearningSplit-MNISTMixture-of-Variational-Experts for Continual Learning
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+4Dendritic Self-Organizing Maps for Continual Learning
Current deep learning architectures show remarkable performance when trained in large-scale, controlled datasets. However, the predictive ability of these architectures significantly decreases when learning new classes i…
Continual LearningSplit-CIFAR-10Split-MNISTTask-agnostic Continual Learning with Hybrid Probabilistic Models
Learning new tasks continuously without forgetting on a constantly changing data distribution is essential for real-world problems but extremely challenging for modern deep learning. In this work we propose HCL, a Hybrid…
Anomaly DetectionContinual LearningSplit-MNISTContinual Competitive Memory: A Neural System for Online Task-Free Lifelong Learning
In this article, we propose a novel form of unsupervised learning, continual competitive memory (CCM), as well as a computational framework to unify related neural models that operate under the principles of competition.…
Lifelong learningSplit-MNISTSelf-Attention Meta-Learner for Continual Learning
Continual learning aims to provide intelligent agents capable of learning multiple tasks sequentially with neural networks. One of its main challenging, catastrophic forgetting, is caused by the neural networks non-optim…
Continual LearningSplit-CIFAR-10Split-MNISTLearning Invariant Representation for Continual Learning
Continual learning aims to provide intelligent agents that are capable of learning continually a sequence of tasks, building on previously learned knowledge. A key challenge in this learning paradigm is catastrophically …
class-incremental learningClass Incremental LearningContinual LearningIncremental Learning+2Conditional Input Gated Low-Rank Perturbations for Continual Learning
We address the problem of learning convolution neural networks (CNN) in the continual setting when tasks arrive sequentially, and only the data of the current task is available. In this setting CNNs are prone to reduce t…
Continual LearningSplit-MNISTNeuromodulated Neural Architectures with Local Error Signals for Memory-Constrained Online Continual Learning
The ability to learn continuously from an incoming data stream without catastrophic forgetting is critical for designing intelligent systems. Many existing approaches to continual learning rely on stochastic gradient des…
Bayesian OptimizationClass Incremental LearningContinual LearningEdge-computing+3SpaceNet: Make Free Space For Continual Learning
The continual learning (CL) paradigm aims to enable neural networks to learn tasks continually in a sequential fashion. The fundamental challenge in this learning paradigm is catastrophic forgetting previously learned ta…
class-incremental learningClass Incremental LearningContinual LearningIncremental Learning+1