A Deep Learning Framework for Lifelong Machine Learning
arXiv:2105.00157
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 machine 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 deep learning framework that supports almost all of these properties and approaches through one central mechanism. Experiments on toy examples support our claims. We also draw connections between many peculiarities of human learning (such as memory loss and "rain man") and our framework. As academics, we often lack resources required to build and train, deep neural networks with billions of parameters on hundreds of TPUs. Thus, while our framework is still conceptual, and our experiment results are surely not SOTA, we hope that this unified lifelong learning framework inspires new work towards large-scale experiments and understanding human learning in general. This paper is summarized in two short YouTube videos: https://youtu.be/gCuUyGETbTU (part 1) and https://youtu.be/XsaGI01b-1o (part 2).
27 pages, 19 figures
References in corpus (13)
- Adam: A Method for Stochastic Optimization
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- A Survey on Deep Learning in Medical Image Analysis
- Deep learning in agriculture: A survey
- Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence
- Continual Learning Through Synaptic Intelligence
- A Survey on Multi-Task Learning
- EMNIST: an extension of MNIST to handwritten letters
- On Tiny Episodic Memories in Continual Learning
- Reinforced Continual Learning
- Online Structured Laplace Approximations For Overcoming Catastrophic Forgetting
- Deep Generative Dual Memory Network for Continual Learning
- An empirical study of pretrained representations for few-shot classification