Task Agnostic Continual Learning Using Online Variational Bayes

Abstract

Catastrophic forgetting is the notorious vulnerability of neural networks to the change of the data distribution while learning. This phenomenon has long been considered a major obstacle for allowing the use of learning agents in realistic continual learning settings. A large body of continual learning research assumes that task boundaries are known during training. However, research for scenarios in which task boundaries are unknown during training has been lacking. In this paper we present, for the first time, a method for preventing catastrophic forgetting (BGD) for scenarios with task boundaries that are unknown during training --- task-agnostic continual learning. Code of our algorithm is available at https://github.com/igolan/bgd.

References in corpus (20)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Overcoming catastrophic forgetting in neural networks
• Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
• Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
• Weight Uncertainty in Neural Networks
• Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence
• Continual Learning Through Synaptic Intelligence
• Probabilistic Backpropagation for Scalable Learning of Bayesian Neural Networks
• Identifying and attacking the saddle point problem in high-dimensional non-convex optimization
• Optimizing Neural Networks with Kronecker-factored Approximate Curvature
• Variational Continual Learning
• Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselines
• Continual Learning with Deep Generative Replay
• Bayesian Dark Knowledge
• Generative replay with feedback connections as a general strategy for continual learning
• Online Structured Laplace Approximations For Overcoming Catastrophic Forgetting
• Towards Robust Evaluations of Continual Learning
• Fast and Scalable Bayesian Deep Learning by Weight-Perturbation in Adam
• Noisy Natural Gradient as Variational Inference
• Overpruning in Variational Bayesian Neural Networks

Cited by in corpus (30)

• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• A continual learning survey: Defying forgetting in classification tasks
• Three scenarios for continual learning
• Incremental Learning for Semantic Segmentation of Large-Scale Remote Sensing Data
• Continual Learning for Recurrent Neural Networks: an Empirical Evaluation
• Task Agnostic Continual Learning via Meta Learning
• La-MAML: Look-ahead Meta Learning for Continual Learning
• Toward Understanding Catastrophic Forgetting in Continual Learning
• Continual Learning with Adaptive Weights (CLAW)
• Preconditioned training of normalizing flows for variational inference in inverse problems
• Task Agnostic Continual Learning Using Online Variational Bayes with Fixed-Point Updates
• A Generalization Bound for Online Variational Inference
• Hierarchical Indian Buffet Neural Networks for Bayesian Continual Learning
• Encoders and Ensembles for Task-Free Continual Learning
• Supermasks in Superposition
• A Study of Continual Learning Methods for Q-Learning
• Energy-Based Models for Continual Learning
• Pseudo-Rehearsal for Continual Learning with Normalizing Flows
• One step back, two steps forward: interference and learning in recurrent neural networks
• Bayesian Structure Adaptation for Continual Learning
• Layerwise Optimization by Gradient Decomposition for Continual Learning
• Sequoia: A Software Framework to Unify Continual Learning Research
• Posterior Meta-Replay for Continual Learning
• Task-agnostic Continual Learning with Hybrid Probabilistic Models
• Frosting Weights for Better Continual Training
• DIRA: Dynamic Domain Incremental Regularised Adaptation
• Online Continual Learning in Image Classification: An Empirical Survey
• Practical Bayesian Learning of Neural Networks via Adaptive Optimisation Methods
• Better Knowledge Retention through Metric Learning
• Continual Novelty Detection