A Conceptual Framework for Lifelong Learning
arXiv:1911.09704
Abstract
Humans can learn a variety of concepts and skills incrementally over the course of their lives while exhibiting many desirable properties, such as continual learning without forgetting, forward transfer and backward transfer of knowledge, and learning a new concept or task with only a few examples. Several lines of machine learning research, such as lifelong learning, few-shot learning, and transfer learning, attempt to capture these properties. However, most previous approaches can only demonstrate subsets of these properties, often by different complex mechanisms. In this work, we propose a simple yet powerful unified framework that supports almost all of these properties and approaches through one central mechanism. We also draw connections between many peculiarities of human learning (such as memory loss and "rain man") and our framework. While we do not present any state-of-the-art results, we hope that this conceptual framework provides a novel perspective on existing work and proposes many new research directions.
39 pages, 14 figures, 2 tables
References in corpus (27)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- A Survey on Deep Learning in Medical Image Analysis
- Distilling the Knowledge in a Neural Network
- Overcoming catastrophic forgetting in neural networks
- A continual learning survey: Defying forgetting in classification tasks
- The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks
- Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence
- Understanding deep learning requires rethinking generalization
- Continual Learning Through Synaptic Intelligence
- A Survey on Multi-Task Learning
- Efficient Lifelong Learning with A-GEM
- Characterizing Concept Drift
- Gradient Episodic Memory for Continual Learning
- On Tiny Episodic Memories in Continual Learning
- Reinforced Continual Learning
- Generalization Properties of Learning with Random Features
- Online Structured Laplace Approximations For Overcoming Catastrophic Forgetting
- Deep Neural Networks with Random Gaussian Weights: A Universal Classification Strategy?
- Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning
- Pelee: A Real-Time Object Detection System on Mobile Devices
- Don't forget, there is more than forgetting: new metrics for Continual Learning
- Continual Learning via Neural Pruning
- Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting
- Sharing Knowledge in Multi-Task Deep Reinforcement Learning
- Pseudo-Recursal: Solving the Catastrophic Forgetting Problem in Deep Neural Networks
- Meta Continual Learning
- An empirical study of pretrained representations for few-shot classification