# Short-Term Plasticity Neurons Learning to Learn and Forget

arXiv: https://arxiv.org/abs/2206.14048 · HTML: https://mlsanity.com/paper/2206.14048/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 74 references that are in the map.
- First posted on arXiv 28 Jun 2022.

## Builds on (most cited first, 30 of 34)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Meta-Learning in Neural Networks: A Survey](https://mlsanity.com/paper/2004.05439/) (2020)
- [Deep Reinforcement Learning at the Edge of the Statistical Precipice](https://mlsanity.com/paper/2108.13264/) (2021)
- [Weight Normalization: A Simple Reparameterization to Accelerate Training of Deep Neural Networks](https://mlsanity.com/paper/1602.07868/) (2016)
- [Linear Transformers Are Secretly Fast Weight Programmers](https://mlsanity.com/paper/2102.11174/) (2021)
- [Deep Recurrent Q-Learning for Partially Observable MDPs](https://mlsanity.com/paper/1507.06527/) (2015)
- [Learning to reinforcement learn](https://mlsanity.com/paper/1611.05763/) (2016)
- [Meta-Learning Representations for Continual Learning](https://mlsanity.com/paper/1905.12588/) (2019)
- [Long short-term memory and learning-to-learn in networks of spiking neurons](https://mlsanity.com/paper/1803.09574/) (2018)
- [Using Fast Weights to Attend to the Recent Past](https://mlsanity.com/paper/1610.06258/) (2016)
- [PonderNet: Learning to Ponder](https://mlsanity.com/paper/2107.05407/) (2021)
- [Editable Neural Networks](https://mlsanity.com/paper/2004.00345/) (2020)
- [Can You Learn an Algorithm? Generalizing from Easy to Hard Problems with Recurrent Networks](https://mlsanity.com/paper/2106.04537/) (2021)
- [Meta-Learning with Warped Gradient Descent](https://mlsanity.com/paper/1909.00025/) (2019)
- [Predictive Coding Approximates Backprop along Arbitrary Computation Graphs](https://mlsanity.com/paper/2006.04182/) (2020)
- [Putting An End to End-to-End: Gradient-Isolated Learning of Representations](https://mlsanity.com/paper/1905.11786/) (2019)
- [Differentiable plasticity: training plastic neural networks with backpropagation](https://mlsanity.com/paper/1804.02464/) (2018)
- [Learning to Continually Learn](https://mlsanity.com/paper/2002.09571/) (2020)
- [Eligibility Traces and Plasticity on Behavioral Time Scales: Experimental Support of neoHebbian Three-Factor Learning Rules](https://mlsanity.com/paper/1801.05219/) (2018)
- [Incremental Few-Shot Learning with Attention Attractor Networks](https://mlsanity.com/paper/1810.07218/) (2018)
- [Local plasticity rules can learn deep representations using self-supervised contrastive predictions](https://mlsanity.com/paper/2010.08262/) (2020)
- [Backpropamine: training self-modifying neural networks with differentiable neuromodulated plasticity](https://mlsanity.com/paper/2002.10585/) (2020)
- [Self-Attentive Associative Memory](https://mlsanity.com/paper/2002.03519/) (2020)
- [Equivalence of Equilibrium Propagation and Recurrent Backpropagation](https://mlsanity.com/paper/1711.08416/) (2017)
- [SoftHebb: Bayesian Inference in Unsupervised Hebbian Soft Winner-Take-All Networks](https://mlsanity.com/paper/2107.05747/) (2021)
- [Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks](https://mlsanity.com/paper/1703.10371/) (2017)
- [Kernelized information bottleneck leads to biologically plausible 3-factor Hebbian learning in deep networks](https://mlsanity.com/paper/2006.07123/) (2020)
- [The Uncanny Similarity of Recurrence and Depth](https://mlsanity.com/paper/2102.11011/) (2021)
- [Spiking neurons with short-term synaptic plasticity form superior generative networks](https://mlsanity.com/paper/1709.08166/) (2017)

## Built on by (most cited first, 6 of 6)

- [Hebbian Deep Learning Without Feedback](https://mlsanity.com/paper/2209.11883/) (2022)
- [Brain-inspired learning in artificial neural networks: a review](https://mlsanity.com/paper/2305.11252/) (2023)
- [Self-Contrastive Forward-Forward Algorithm](https://mlsanity.com/paper/2409.11593/) (2024)
- [Hebbian and Gradient-based Plasticity Enables Robust Memory and Rapid Learning in RNNs](https://mlsanity.com/paper/2302.03235/) (2023)
- [Learning to Control Rapidly Changing Synaptic Connections: An Alternative Type of Memory in Sequence Processing Artificial Neural Networks](https://mlsanity.com/paper/2211.09440/) (2022)
- [TFGN: Task-Free, Replay-Free Continual Pre-Training Without Catastrophic Forgetting at LLM Scale](https://mlsanity.com/paper/2605.15053/) (2026)

## Abstract (arXiv)

Short-term plasticity (STP) is a mechanism that stores decaying memories in synapses of the cerebral cortex. In computing practice, STP has been used, but mostly in the niche of spiking neurons, even though theory predicts that it is the optimal solution to certain dynamic tasks. Here we present a new type of recurrent neural unit, the STP Neuron (STPN), which indeed turns out strikingly powerful. Its key mechanism is that synapses have a state, propagated through time by a self-recurrent connection-within-the-synapse. This formulation enables training the plasticity with backpropagation through time, resulting in a form of learning to learn and forget in the short term. The STPN outperforms all tested alternatives, i.e. RNNs, LSTMs, other models with fast weights, and differentiable plasticity. We confirm this in both supervised and reinforcement learning (RL), and in tasks such as Associative Retrieval, Maze Exploration, Atari video games, and MuJoCo robotics. Moreover, we calculate that, in neuromorphic or biological circuits, the STPN minimizes energy consumption across models, as it depresses individual synapses dynamically. Based on these, biological STP may have been a strong evolutionary attractor that maximizes both efficiency and computational power. The STPN now brings these neuromorphic advantages also to a broad spectrum of machine learning practice. Code is available at https://github.com/NeuromorphicComputing/stpn