# Lifelong Intelligence Beyond the Edge using Hyperdimensional Computing

arXiv: https://arxiv.org/abs/2403.04759 · HTML: https://mlsanity.com/paper/2403.04759/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 67 references that are in the map.
- First posted on arXiv 7 Mar 2024.

## Builds on (most cited first, 28 of 28)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Searching for MobileNetV3](https://mlsanity.com/paper/1905.02244/) (2019)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Progressive Neural Networks](https://mlsanity.com/paper/1606.04671/) (2016)
- [Continual Lifelong Learning with Neural Networks: A Review](https://mlsanity.com/paper/1802.07569/) (2018)
- [MCUNet: Tiny Deep Learning on IoT Devices](https://mlsanity.com/paper/2007.10319/) (2020)
- [Class-incremental Learning via Deep Model Consolidation](https://mlsanity.com/paper/1903.07864/) (2019)
- [On-Device Training Under 256KB Memory](https://mlsanity.com/paper/2206.15472/) (2022)
- [Self-Supervised Models are Continual Learners](https://mlsanity.com/paper/2112.04215/) (2021)
- [A Neural Dirichlet Process Mixture Model for Task-Free Continual Learning](https://mlsanity.com/paper/2001.00689/) (2020)
- [Representational Continuity for Unsupervised Continual Learning](https://mlsanity.com/paper/2110.06976/) (2021)
- [GCR: Gradient Coreset Based Replay Buffer Selection For Continual Learning](https://mlsanity.com/paper/2111.11210/) (2021)
- [MCUNetV2: Memory-Efficient Patch-based Inference for Tiny Deep Learning](https://mlsanity.com/paper/2110.15352/) (2021)
- [TinyOL: TinyML with Online-Learning on Microcontrollers](https://mlsanity.com/paper/2103.08295/) (2021)
- [An Overview of Neural Network Compression](https://mlsanity.com/paper/2006.03669/) (2020)
- [A Theoretical Perspective on Hyperdimensional Computing](https://mlsanity.com/paper/2010.07426/) (2020)
- [Unsupervised Progressive Learning and the STAM Architecture](https://mlsanity.com/paper/1904.02021/) (2019)
- [Mandheling: Mixed-Precision On-Device DNN Training with DSP Offloading](https://mlsanity.com/paper/2206.07509/) (2022)
- [Algorithmic insights on continual learning from fruit flies](https://mlsanity.com/paper/2107.07617/) (2021)
- [Sparse Distributed Memory is a Continual Learner](https://mlsanity.com/paper/2303.11934/) (2023)
- [LifeLearner: Hardware-Aware Meta Continual Learning System for Embedded Computing Platforms](https://mlsanity.com/paper/2311.11420/) (2023)
- [Hyperseed: Unsupervised Learning with Vector Symbolic Architectures](https://mlsanity.com/paper/2110.08343/) (2021)
- [Prive-HD: Privacy-Preserved Hyperdimensional Computing](https://mlsanity.com/paper/2005.06716/) (2020)
- [Stochastic Coherence Over Attention Trajectory For Continuous Learning In Video Streams](https://mlsanity.com/paper/2204.12193/) (2022)

## Built on by (most cited first, 5 of 5)

- [ImageHD: Energy-Efficient On-Device Continual Learning of Visual Representations via Hyperdimensional Computing](https://mlsanity.com/paper/2604.21280/) (2026)
- [Toward Self-Adaptive Physical AI: Can LLM Agents Manage Long-Horizon Physical Tasks?](https://mlsanity.com/paper/2609.13436/) (2026)
- [FedUHD: Unsupervised Federated Learning using In-Memory Hyperdimensional Computing](https://mlsanity.com/paper/2508.12021/) (2025)
- [ConformalHDC: Uncertainty-Aware Hyperdimensional Computing with Application to Neural Decoding](https://mlsanity.com/paper/2602.21446/) (2026)
- [HyperLiDAR: Adaptive Post-Deployment LiDAR Segmentation via Hyperdimensional Computing](https://mlsanity.com/paper/2604.12331/) (2026)

## Abstract (arXiv)

On-device learning has emerged as a prevailing trend that avoids the slow response time and costly communication of cloud-based learning. The ability to learn continuously and indefinitely in a changing environment, and with resource constraints, is critical for real sensor deployments. However, existing designs are inadequate for practical scenarios with (i) streaming data input, (ii) lack of supervision and (iii) limited on-board resources. In this paper, we design and deploy the first on-device lifelong learning system called LifeHD for general IoT applications with limited supervision. LifeHD is designed based on a novel neurally-inspired and lightweight learning paradigm called Hyperdimensional Computing (HDC). We utilize a two-tier associative memory organization to intelligently store and manage high-dimensional, low-precision vectors, which represent the historical patterns as cluster centroids. We additionally propose two variants of LifeHD to cope with scarce labeled inputs and power constraints. We implement LifeHD on off-the-shelf edge platforms and perform extensive evaluations across three scenarios. Our measurements show that LifeHD improves the unsupervised clustering accuracy by up to 74.8% compared to the state-of-the-art NN-based unsupervised lifelong learning baselines with as much as 34.3x better energy efficiency. Our code is available at https://github.com/Orienfish/LifeHD.