# Autonomous Deep Learning: Continual Learning Approach for Dynamic Environments

arXiv: https://arxiv.org/abs/1810.07348 · HTML: https://mlsanity.com/paper/1810.07348/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Oct 2018.

## Built on by (most cited first, 15 of 15)

- [Catastrophic Forgetting in Deep Learning: A Comprehensive Taxonomy](https://mlsanity.com/paper/2312.10549/) (2023)
- [Unsupervised Continual Learning in Streaming Environments](https://mlsanity.com/paper/2109.09282/) (2021)
- [A Survey on Semi-Supervised Learning for Delayed Partially Labelled Data Streams](https://mlsanity.com/paper/2106.09170/) (2021)
- [Adaptive Online Incremental Learning for Evolving Data Streams](https://mlsanity.com/paper/2201.01633/) (2022)
- [Automatic Online Multi-Source Domain Adaptation](https://mlsanity.com/paper/2109.01996/) (2021)
- [Aux-Drop: Handling Haphazard Inputs in Online Learning Using Auxiliary Dropouts](https://mlsanity.com/paper/2303.05155/) (2023)
- [Online Relational Inference for Evolving Multi-agent Interacting Systems](https://mlsanity.com/paper/2411.01442/) (2024)
- [Scalable Teacher Forcing Network for Semi-Supervised Large Scale Data Streams](https://mlsanity.com/paper/2107.02943/) (2021)
- [A Practical Guide to Streaming Continual Learning](https://mlsanity.com/paper/2603.01677/) (2026)
- [Quantile Online Learning for Semiconductor Failure Analysis](https://mlsanity.com/paper/2303.07062/) (2023)
- [Online Deep Learning based on Auto-Encoder](https://mlsanity.com/paper/2201.07383/) (2022)
- [Dynamic Long-Term Time-Series Forecasting via Meta Transformer Networks](https://mlsanity.com/paper/2401.13968/) (2024)
- [AI-Guided Defect Detection Techniques to Model Single Crystal Diamond Growth](https://mlsanity.com/paper/2404.07306/) (2024)
- [Online-BLS: An Accurate and Efficient Online Broad Learning System for Data Stream Classification](https://mlsanity.com/paper/2501.16932/) (2025)
- [SLeDGe: Semi-Supervised Learning on Data Streams with Graph Structure Learning](https://mlsanity.com/paper/2606.21096/) (2026)

## Abstract (arXiv)

The feasibility of deep neural networks (DNNs) to address data stream problems still requires intensive study because of the static and offline nature of conventional deep learning approaches. A deep continual learning algorithm, namely autonomous deep learning (ADL), is proposed in this paper. Unlike traditional deep learning methods, ADL features a flexible structure where its network structure can be constructed from scratch with the absence of an initial network structure via the self-constructing network structure. ADL specifically addresses catastrophic forgetting by having a different-depth structure which is capable of achieving a trade-off between plasticity and stability. Network significance (NS) formula is proposed to drive the hidden nodes growing and pruning mechanism. Drift detection scenario (DDS) is put forward to signal distributional changes in data streams which induce the creation of a new hidden layer. The maximum information compression index (MICI) method plays an important role as a complexity reduction module eliminating redundant layers. The efficacy of ADL is numerically validated under the prequential test-then-train procedure in lifelong environments using nine popular data stream problems. The numerical results demonstrate that ADL consistently outperforms recent continual learning methods while characterizing the automatic construction of network structures.