# In-memory Realization of In-situ Few-shot Continual Learning with a Dynamically Evolving Explicit Memory

arXiv: https://arxiv.org/abs/2207.06810 · HTML: https://mlsanity.com/paper/2207.06810/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 13 references that are in the map.
- First posted on arXiv 14 Jul 2022.

## Builds on (most cited first, 5 of 5)

- [Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2004.10956/) (2020)
- [Overcoming Catastrophic Forgetting in Incremental Few-Shot Learning by Finding Flat Minima](https://mlsanity.com/paper/2111.01549/) (2021)
- [Constrained Few-shot Class-incremental Learning](https://mlsanity.com/paper/2203.16588/) (2022)
- [Robust High-dimensional Memory-augmented Neural Networks](https://mlsanity.com/paper/2010.01939/) (2020)
- [In-Memory Nearest Neighbor Search with FeFET Multi-Bit Content-Addressable Memories](https://mlsanity.com/paper/2011.07095/) (2020)

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

- [Training of Physical Neural Networks](https://mlsanity.com/paper/2406.03372/) (2024)
- [Learning from Hypervectors: A Survey on Hypervector Encoding](https://mlsanity.com/paper/2308.00685/) (2023)
- [Vector-Symbolic Architecture for Event-Based Optical Flow](https://mlsanity.com/paper/2405.08300/) (2024)
- [MetaLDC: Meta Learning of Low-Dimensional Computing Classifiers for Fast On-Device Adaption](https://mlsanity.com/paper/2302.12347/) (2023)
- [12 mJ per Class On-Device Online Few-Shot Class-Incremental Learning](https://mlsanity.com/paper/2403.07851/) (2024)
- [Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data](https://mlsanity.com/paper/2505.24852/) (2025)
- [Zero-shot Classification using Hyperdimensional Computing](https://mlsanity.com/paper/2401.16876/) (2024)
- [Layer Ensemble Averaging for Improving Memristor-Based Artificial Neural Network Performance](https://mlsanity.com/paper/2404.15621/) (2024)
- [Learning-to-learn enables rapid learning with phase-change memory-based in-memory computing](https://mlsanity.com/paper/2405.05141/) (2024)

## Abstract (arXiv)

Continually learning new classes from a few training examples without forgetting previous old classes demands a flexible architecture with an inevitably growing portion of storage, in which new examples and classes can be incrementally stored and efficiently retrieved. One viable architectural solution is to tightly couple a stationary deep neural network to a dynamically evolving explicit memory (EM). As the centerpiece of this architecture, we propose an EM unit that leverages energy-efficient in-memory compute (IMC) cores during the course of continual learning operations. We demonstrate for the first time how the EM unit can physically superpose multiple training examples, expand to accommodate unseen classes, and perform similarity search during inference, using operations on an IMC core based on phase-change memory (PCM). Specifically, the physical superposition of a few encoded training examples is realized via in-situ progressive crystallization of PCM devices. The classification accuracy achieved on the IMC core remains within a range of 1.28%--2.5% compared to that of the state-of-the-art full-precision baseline software model on both the CIFAR-100 and miniImageNet datasets when continually learning 40 novel classes (from only five examples per class) on top of 60 old classes.