Continual learning using hash-routed convolutional neural networks

Abstract

Continual learning could shift the machine learning paradigm from data centric to model centric. A continual learning model needs to scale efficiently to handle semantically different datasets, while avoiding unnecessary growth. We introduce hash-routed convolutional neural networks: a group of convolutional units where data flows dynamically. Feature maps are compared using feature hashing and similar data is routed to the same units. A hash-routed network provides excellent plasticity thanks to its routed nature, while generating stable features through the use of orthogonal feature hashing. Each unit evolves separately and new units can be added (to be used only when necessary). Hash-routed networks achieve excellent performance across a variety of typical continual learning benchmarks without storing raw data and train using only gradient descent. Besides providing a continual learning framework for supervised tasks with encouraging results, our model can be used for unsupervised or reinforcement learning.

References in corpus (11)

• Distilling the Knowledge in a Neural Network
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Continual Learning Through Synaptic Intelligence
• Compressing Neural Networks with the Hashing Trick
• FearNet: Brain-Inspired Model for Incremental Learning
• Overcoming catastrophic forgetting with hard attention to the task
• Continual Learning with Deep Generative Replay
• Reinforced Continual Learning
• Generative replay with feedback connections as a general strategy for continual learning
• Lifelong Learning with Dynamically Expandable Networks
• Deep Generative Dual Memory Network for Continual Learning