Behavioral Experiments for Understanding Catastrophic Forgetting
In this paper we explore whether the fundamental tool of experimental psychology, the behavioral experiment, has the power to generate insight not only into humans and animals, but artificial systems too. We apply the techniques of experimental psychology to investigating catastrophic forgetting in neural networks. We present a series of controlled experiments with two-layer ReLU networks, and exploratory results revealing a new understanding of the behavior of catastrophic forgetting. Alongside our empirical findings, we demonstrate an alternative, behavior-first approach to investigating neural network phenomena.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Does an LSTM forget more than a CNN? An empirical study of catastrophic forgetting in NLP
Catastrophic forgetting {---} whereby a model trained on one task is fine-tuned on a second, and in doing so, suffers a {``}catastrophic{''} drop in performance over the first task {---} is a hurdle in the development of…
Continual LearningTransfer LearningSelfAug: Mitigating Catastrophic Forgetting in Retrieval-Augmented Generation via Distribution Self-Alignment
Recent advancements in large language models (LLMs) have revolutionized natural language processing through their remarkable capabilities in understanding and executing diverse tasks. While supervised fine-tuning, partic…
Catastrophic Forgetting as Accessibility Collapse: A Three-Level Framework for Knowledge Persistence in Continual Learning
Catastrophic forgetting is commonly interpreted as the irreversible erasure of previously acquired knowledge during sequential learning. In this work, we investigate an alternative perspective: that forgetting may arise …
Continual LearningDomain adapted machine translation: What does catastrophic forgetting forget and why?
Neural Machine Translation (NMT) models can be specialized by domain adaptation, often involving fine-tuning on a dataset of interest. This process risks catastrophic forgetting: rapid loss of generic translation quality…
Domain AdaptationMachine TranslationNMTTranslationLearning to Modulate Random Weights: Neuromodulation-inspired Neural Networks For Efficient Continual Learning
Existing Continual Learning (CL) approaches have focused on addressing catastrophic forgetting by leveraging regularization methods, replay buffers, and task-specific components. However, realistic CL solutions must be s…
Computational EfficiencyContinual LearningMeta-Learning