# One-shot Learning with Memory-Augmented Neural Networks

arXiv: https://arxiv.org/abs/1605.06065 · HTML: https://mlsanity.com/paper/1605.06065/

## Key facts

- Cited by 60 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 May 2016.

## Built on by (most cited first, 30 of 60)

- [Learning To Count Everything](https://mlsanity.com/paper/2104.08391/) (2021)
- [Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought](https://mlsanity.com/paper/2501.04682/) (2025)
- [Learning from Few Examples: A Summary of Approaches to Few-Shot Learning](https://mlsanity.com/paper/2203.04291/) (2022)
- [Mining Latent Classes for Few-shot Segmentation](https://mlsanity.com/paper/2103.15402/) (2021)
- [Exemplar Free Class Agnostic Counting](https://mlsanity.com/paper/2205.14212/) (2022)
- [Instant One-Shot Word-Learning for Context-Specific Neural Sequence-to-Sequence Speech Recognition](https://mlsanity.com/paper/2107.02268/) (2021)
- [Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey](https://mlsanity.com/paper/2110.01411/) (2021)
- [Learning Kernel-Smoothed Machine Translation with Retrieved Examples](https://mlsanity.com/paper/2109.09991/) (2021)
- [Cross-Domain Video Anomaly Detection without Target Domain Adaptation](https://mlsanity.com/paper/2212.07010/) (2022)
- [Learning to Extrapolate: A Transductive Approach](https://mlsanity.com/paper/2304.14329/) (2023)
- [One Adapter for All Programming Languages? Adapter Tuning for Code Search and Summarization](https://mlsanity.com/paper/2303.15822/) (2023)
- [Traveling Waves Encode the Recent Past and Enhance Sequence Learning](https://mlsanity.com/paper/2309.08045/) (2023)
- [FSPO: Few-Shot Optimization of Synthetic Preferences Personalizes to Real Users](https://mlsanity.com/paper/2502.19312/) (2025)
- [OLED: One-Class Learned Encoder-Decoder Network with Adversarial Context Masking for Novelty Detection](https://mlsanity.com/paper/2103.14953/) (2021)
- [Continuous-Time Meta-Learning with Forward Mode Differentiation](https://mlsanity.com/paper/2203.01443/) (2022)
- [Unsupervised Outlier Detection using Memory and Contrastive Learning](https://mlsanity.com/paper/2107.12642/) (2021)
- [MASTAF: A Model-Agnostic Spatio-Temporal Attention Fusion Network for Few-shot Video Classification](https://mlsanity.com/paper/2112.04585/) (2021)
- [On the Importance of Firth Bias Reduction in Few-Shot Classification](https://mlsanity.com/paper/2110.02529/) (2021)
- [Label-enhanced Prototypical Network with Contrastive Learning for Multi-label Few-shot Aspect Category Detection](https://mlsanity.com/paper/2206.13980/) (2022)
- [Shared Multi-Task Imitation Learning for Indoor Self-Navigation](https://mlsanity.com/paper/1808.04503/) (2018)
- [Grid Cell Path Integration For Movement-Based Visual Object Recognition](https://mlsanity.com/paper/2102.09076/) (2021)
- [Personalizing Pre-trained Models](https://mlsanity.com/paper/2106.01499/) (2021)
- [Rethinking Task-Incremental Learning Baselines](https://mlsanity.com/paper/2205.11367/) (2022)
- [A Flexible Nadaraya-Watson Head Can Offer Explainable and Calibrated Classification](https://mlsanity.com/paper/2212.03411/) (2022)
- [Boosting Few-Shot Text Classification via Distribution Estimation](https://mlsanity.com/paper/2303.16764/) (2023)
- [How to Do Machine Learning with Small Data? -- A Review from an Industrial Perspective](https://mlsanity.com/paper/2311.07126/) (2023)
- [Combat Data Shift in Few-shot Learning with Knowledge Graph](https://mlsanity.com/paper/2101.11354/) (2021)
- [Hierarchical Representation based Query-Specific Prototypical Network for Few-Shot Image Classification](https://mlsanity.com/paper/2103.11384/) (2021)
- [Updatable Siamese Tracker with Two-stage One-shot Learning](https://mlsanity.com/paper/2104.15049/) (2021)
- [Memory-guided Image De-raining Using Time-Lapse Data](https://mlsanity.com/paper/2201.01883/) (2022)

## Abstract (arXiv)

Despite recent breakthroughs in the applications of deep neural networks, one setting that presents a persistent challenge is that of "one-shot learning." Traditional gradient-based networks require a lot of data to learn, often through extensive iterative training. When new data is encountered, the models must inefficiently relearn their parameters to adequately incorporate the new information without catastrophic interference. Architectures with augmented memory capacities, such as Neural Turing Machines (NTMs), offer the ability to quickly encode and retrieve new information, and hence can potentially obviate the downsides of conventional models. Here, we demonstrate the ability of a memory-augmented neural network to rapidly assimilate new data, and leverage this data to make accurate predictions after only a few samples. We also introduce a new method for accessing an external memory that focuses on memory content, unlike previous methods that additionally use memory location-based focusing mechanisms.