# A Hybrid Edge Classifier: Combining TinyML-Optimised CNN with RRAM-CMOS ACAM for Energy-Efficient Inference

arXiv: https://arxiv.org/abs/2502.10089 · HTML: https://mlsanity.com/paper/2502.10089/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 40 references that are in the map.
- First posted on arXiv 14 Feb 2025.

## Builds on (most cited first, 8 of 8)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [MCUNet: Tiny Deep Learning on IoT Devices](https://mlsanity.com/paper/2007.10319/) (2020)
- [Pruning and Quantization for Deep Neural Network Acceleration: A Survey](https://mlsanity.com/paper/2101.09671/) (2021)
- [A Review of Deep Learning Techniques for Speech Processing](https://mlsanity.com/paper/2305.00359/) (2023)
- [Towards Optimal Compression: Joint Pruning and Quantization](https://mlsanity.com/paper/2302.07612/) (2023)
- [A 9T4R RRAM-Based ACAM for Analogue Template Matching at the Edge](https://mlsanity.com/paper/2410.03414/) (2024)

## Built on by (most cited first, 2 of 2)

- [Embodied Foundation Models at the Edge: A Survey of Deployment Constraints and Mitigation Strategies](https://mlsanity.com/paper/2603.16952/) (2026)
- [An RRAM-based Hardware Implementation of a Radial Basis Function Neuron for Edge Classifiers](https://mlsanity.com/paper/2606.14739/) (2026)

## Abstract (arXiv)

In recent years, the development of smart edge computing systems to process information locally is on the rise. Many near-sensor machine learning (ML) approaches have been implemented to introduce accurate and energy efficient template matching operations in resource-constrained edge sensing systems, such as wearables. To introduce novel solutions that can be viable for extreme edge cases, hybrid solutions combining conventional and emerging technologies have started to be proposed. Deep Neural Networks (DNN) optimised for edge application alongside new approaches of computing (both device and architecture -wise) could be a strong candidate in implementing edge ML solutions that aim at competitive accuracy classification while using a fraction of the power of conventional ML solutions. In this work, we are proposing a hybrid software-hardware edge classifier aimed at the extreme edge near-sensor systems. The classifier consists of two parts: (i) an optimised digital tinyML network, working as a front-end feature extractor, and (ii) a back-end RRAM-CMOS analogue content addressable memory (ACAM), working as a final stage template matching system. The combined hybrid system exhibits a competitive trade-off in accuracy versus energy metric with Efront-end = 96.23 nJ and Eback-end = 1.45 nJ for each classification operation compared with 78.06μJ for the original teacher model, representing a 792-fold reduction, making it a viable solution for extreme edge applications.