# Design Principles for Lifelong Learning AI Accelerators

arXiv: https://arxiv.org/abs/2310.04467 · HTML: https://mlsanity.com/paper/2310.04467/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 130 references that are in the map.
- First posted on arXiv 5 Oct 2023.

## Builds on (most cited first, 30 of 37)

- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [iCaRL: Incremental Classifier and Representation Learning](https://mlsanity.com/paper/1611.07725/) (2016)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Training Deep Nets with Sublinear Memory Cost](https://mlsanity.com/paper/1604.06174/) (2016)
- [Three scenarios for continual learning](https://mlsanity.com/paper/1904.07734/) (2019)
- [Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks](https://mlsanity.com/paper/2102.00554/) (2021)
- [OpenML: networked science in machine learning](https://mlsanity.com/paper/1407.7722/) (2014)
- [PathNet: Evolution Channels Gradient Descent in Super Neural Networks](https://mlsanity.com/paper/1701.08734/) (2017)
- [MLPerf Inference Benchmark](https://mlsanity.com/paper/1911.02549/) (2019)
- [Adversarial Continual Learning](https://mlsanity.com/paper/2003.09553/) (2020)
- [A Neural Dirichlet Process Mixture Model for Task-Free Continual Learning](https://mlsanity.com/paper/2001.00689/) (2020)
- [Don't forget, there is more than forgetting: new metrics for Continual Learning](https://mlsanity.com/paper/1810.13166/) (2018)
- [Photonics for artificial intelligence and neuromorphic computing](https://mlsanity.com/paper/2011.00111/) (2020)
- [Alleviating catastrophic forgetting using context-dependent gating and synaptic stabilization](https://mlsanity.com/paper/1802.01569/) (2018)
- [Continual Learning for Robotics: Definition, Framework, Learning Strategies, Opportunities and Challenges](https://mlsanity.com/paper/1907.00182/) (2019)
- [A Wholistic View of Continual Learning with Deep Neural Networks: Forgotten Lessons and the Bridge to Active and Open World Learning](https://mlsanity.com/paper/2009.01797/) (2020)
- [Replay in Deep Learning: Current Approaches and Missing Biological Elements](https://mlsanity.com/paper/2104.04132/) (2021)
- [Continual evaluation for lifelong learning: Identifying the stability gap](https://mlsanity.com/paper/2205.13452/) (2022)
- [A Statistical Framework for Low-bitwidth Training of Deep Neural Networks](https://mlsanity.com/paper/2010.14298/) (2020)
- [Dissecting the Graphcore IPU Architecture via Microbenchmarking](https://mlsanity.com/paper/1912.03413/) (2019)
- [Towards Verified Artificial Intelligence](https://mlsanity.com/paper/1606.08514/) (2016)
- [ReckOn: A 28nm Sub-mm2 Task-Agnostic Spiking Recurrent Neural Network Processor Enabling On-Chip Learning over Second-Long Timescales](https://mlsanity.com/paper/2208.09759/) (2022)
- [A Modern Primer on Processing in Memory](https://mlsanity.com/paper/2012.03112/) (2020)
- [Synaptic metaplasticity in binarized neural networks](https://mlsanity.com/paper/2101.07592/) (2021)
- [Spiking Neural Network Integrated Circuits: A Review of Trends and Future Directions](https://mlsanity.com/paper/2203.07006/) (2022)
- [Exploring System Performance of Continual Learning for Mobile and Embedded Sensing Applications](https://mlsanity.com/paper/2110.13290/) (2021)
- [Practical Recommendations for Replay-based Continual Learning Methods](https://mlsanity.com/paper/2203.10317/) (2022)
- [Continual Learning for Multivariate Time Series Tasks with Variable Input Dimensions](https://mlsanity.com/paper/2203.06852/) (2022)
- [Deep Positron: A Deep Neural Network Using the Posit Number System](https://mlsanity.com/paper/1812.01762/) (2018)
- [Lifelong Learning Metrics](https://mlsanity.com/paper/2201.08278/) (2022)

## Built on by (most cited first, 9 of 9)

- [Continual Learning and Catastrophic Forgetting](https://mlsanity.com/paper/2403.05175/) (2024)
- [Continual Learning: Applications and the Road Forward](https://mlsanity.com/paper/2311.11908/) (2023)
- [Green Edge AI: A Contemporary Survey](https://mlsanity.com/paper/2312.00333/) (2023)
- [Position: Modular Memory is the Key to Continual Learning Agents](https://mlsanity.com/paper/2603.01761/) (2026)
- [Delta: A Cloud-assisted Data Enrichment Framework for On-Device Continual Learning](https://mlsanity.com/paper/2410.18378/) (2024)
- [Learning to Remember, Learn, and Forget in Attention-Based Models](https://mlsanity.com/paper/2602.09075/) (2026)
- [Minion Gated Recurrent Unit for Continual Learning](https://mlsanity.com/paper/2503.06175/) (2025)
- [Lightweight, error-tolerant edge detection using memristor-enabled stochastic logics](https://mlsanity.com/paper/2402.16908/) (2024)
- [Emulating Brain-like Rapid Learning in Neuromorphic Edge Computing](https://mlsanity.com/paper/2408.15800/) (2024)

## Abstract (arXiv)

Lifelong learning - an agent's ability to learn throughout its lifetime - is a hallmark of biological learning systems and a central challenge for artificial intelligence (AI). The development of lifelong learning algorithms could lead to a range of novel AI applications, but this will also require the development of appropriate hardware accelerators, particularly if the models are to be deployed on edge platforms, which have strict size, weight, and power constraints. Here, we explore the design of lifelong learning AI accelerators that are intended for deployment in untethered environments. We identify key desirable capabilities for lifelong learning accelerators and highlight metrics to evaluate such accelerators. We then discuss current edge AI accelerators and explore the future design of lifelong learning accelerators, considering the role that different emerging technologies could play.