# Continual Learning in Neural Networks

arXiv: https://arxiv.org/abs/1910.02718 · HTML: https://mlsanity.com/paper/1910.02718/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Oct 2019.

## Built on by (most cited first, 23 of 23)

- [Continual Learning for Blind Image Quality Assessment](https://mlsanity.com/paper/2102.09717/) (2021)
- [Continual Learning on Noisy Data Streams via Self-Purified Replay](https://mlsanity.com/paper/2110.07735/) (2021)
- [Continual Object Detection: A review of definitions, strategies, and challenges](https://mlsanity.com/paper/2205.15445/) (2022)
- [How do Quadratic Regularizers Prevent Catastrophic Forgetting: The Role of Interpolation](https://mlsanity.com/paper/2102.02805/) (2021)
- [How well are open sourced AI-generated image detection models out-of-the-box: A comprehensive benchmark study](https://mlsanity.com/paper/2602.07814/) (2026)
- [Persistent Backdoor Attacks in Continual Learning](https://mlsanity.com/paper/2409.13864/) (2024)
- [Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention](https://mlsanity.com/paper/2605.29548/) (2026)
- [IB-DRR: Incremental Learning with Information-Back Discrete Representation Replay](https://mlsanity.com/paper/2104.10588/) (2021)
- [PASS++: A Dual Bias Reduction Framework for Non-Exemplar Class-Incremental Learning](https://mlsanity.com/paper/2407.14029/) (2024)
- [Quantum Continual Learning Overcoming Catastrophic Forgetting](https://mlsanity.com/paper/2108.02786/) (2021)
- [Stable Continual Reinforcement Learning via Diffusion-based Trajectory Replay](https://mlsanity.com/paper/2411.10809/) (2024)
- [Branch-Tuning: Balancing Stability and Plasticity for Continual Self-Supervised Learning](https://mlsanity.com/paper/2403.18266/) (2024)
- [Overcoming Catastrophic Forgetting in Federated Class-Incremental Learning via Federated Global Twin Generator](https://mlsanity.com/paper/2407.11078/) (2024)
- [Predicting Plasticity in Deep Continual Learning: A Theoretical Perspective](https://mlsanity.com/paper/2605.09044/) (2026)
- [Neural Weight Search for Scalable Task Incremental Learning](https://mlsanity.com/paper/2211.13823/) (2022)
- [CLVOS23: A Long Video Object Segmentation Dataset for Continual Learning](https://mlsanity.com/paper/2304.04259/) (2023)
- [Evaluating Fine-Tuning Efficiency of Human-Inspired Learning Strategies in Medical Question Answering](https://mlsanity.com/paper/2408.07888/) (2024)
- [Towards Non-Exemplar Semi-Supervised Class-Incremental Learning](https://mlsanity.com/paper/2403.18291/) (2024)
- [Bridging Neuroscience and AI: Environmental Enrichment as a Model for Forward Knowledge Transfer](https://mlsanity.com/paper/2405.07295/) (2024)
- [Shared and Private VAEs with Generative Replay for Continual Learning](https://mlsanity.com/paper/2105.07627/) (2021)
- [Continual learning-based probabilistic slow feature analysis for multimode dynamic process monitoring](https://mlsanity.com/paper/2202.11295/) (2022)
- [Memory-Efficient Continual Learning Object Segmentation for Long Video](https://mlsanity.com/paper/2309.15274/) (2023)
- [Catastrophic Forgetting Mitigation Through Plateau Phase Activity Profiling](https://mlsanity.com/paper/2507.08736/) (2025)

## Abstract (arXiv)

Artificial neural networks have exceeded human-level performance in accomplishing several individual tasks (e.g. voice recognition, object recognition, and video games). However, such success remains modest compared to human intelligence that can learn and perform an unlimited number of tasks. Humans' ability of learning and accumulating knowledge over their lifetime is an essential aspect of their intelligence. Continual machine learning aims at a higher level of machine intelligence through providing the artificial agents with the ability to learn online from a non-stationary and never-ending stream of data. A key component of such a never-ending learning process is to overcome the catastrophic forgetting of previously seen data, a problem that neural networks are well known to suffer from. The work described in this thesis has been dedicated to the investigation of continual learning and solutions to mitigate the forgetting phenomena in neural networks. To approach the continual learning problem, we first assume a task incremental setting where tasks are received one at a time and data from previous tasks are not stored. Since the task incremental setting can't be assumed in all continual learning scenarios, we also study the more general online continual setting. We consider an infinite stream of data drawn from a non-stationary distribution with a supervisory or self-supervisory training signal. The proposed methods in this thesis have tackled important aspects of continual learning. They were evaluated on different benchmarks and over various learning sequences. Advances in the state of the art of continual learning have been shown and challenges for bringing continual learning into application were critically identified.