# Differentiable plasticity: training plastic neural networks with backpropagation

arXiv: https://arxiv.org/abs/1804.02464 · HTML: https://mlsanity.com/paper/1804.02464/

## Key facts

- Cited by 84 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Apr 2018.

## Built on by (most cited first, 30 of 84)

- [Linear Transformers Are Secretly Fast Weight Programmers](https://mlsanity.com/paper/2102.11174/) (2021)
- [Random Feature Attention](https://mlsanity.com/paper/2103.02143/) (2021)
- [Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention](https://mlsanity.com/paper/2404.07143/) (2024)
- [Pretrained Transformers as Universal Computation Engines](https://mlsanity.com/paper/2103.05247/) (2021)
- [Going Beyond Linear Transformers with Recurrent Fast Weight Programmers](https://mlsanity.com/paper/2106.06295/) (2021)
- [Hypernetworks in Meta-Reinforcement Learning](https://mlsanity.com/paper/2210.11348/) (2022)
- [A Modern Self-Referential Weight Matrix That Learns to Modify Itself](https://mlsanity.com/paper/2202.05780/) (2022)
- [Brain-inspired learning in artificial neural networks: a review](https://mlsanity.com/paper/2305.11252/) (2023)
- [Introducing Symmetries to Black Box Meta Reinforcement Learning](https://mlsanity.com/paper/2109.10781/) (2021)
- [Self-Contrastive Forward-Forward Algorithm](https://mlsanity.com/paper/2409.11593/) (2024)
- [Meta-Learning Biologically Plausible Plasticity Rules with Random Feedback Pathways](https://mlsanity.com/paper/2210.16414/) (2022)
- [Eliminating Meta Optimization Through Self-Referential Meta Learning](https://mlsanity.com/paper/2212.14392/) (2022)
- [Adaptive Convolutions with Per-pixel Dynamic Filter Atom](https://mlsanity.com/paper/2108.07895/) (2021)
- [Meta-Learning Bidirectional Update Rules](https://mlsanity.com/paper/2104.04657/) (2021)
- [Meta-learning Spiking Neural Networks with Surrogate Gradient Descent](https://mlsanity.com/paper/2201.10777/) (2022)
- [A Call for Clarity in Beam Search: How It Works and When It Stops](https://mlsanity.com/paper/2204.05424/) (2022)
- [Goal-Conditioned Generators of Deep Policies](https://mlsanity.com/paper/2207.01570/) (2022)
- [Is Bio-Inspired Learning Better than Backprop? Benchmarking Bio Learning vs. Backprop](https://mlsanity.com/paper/2212.04614/) (2022)
- [Stabilizing Elastic Weight Consolidation method in practical ML tasks and using weight importances for neural network pruning](https://mlsanity.com/paper/2109.10021/) (2021)
- [Spiking Neural Networks and Bio-Inspired Supervised Deep Learning: A Survey](https://mlsanity.com/paper/2307.16235/) (2023)
- [Fast weight programming and linear transformers: from machine learning to neurobiology](https://mlsanity.com/paper/2508.08435/) (2025)
- [Position: Modular Memory is the Key to Continual Learning Agents](https://mlsanity.com/paper/2603.01761/) (2026)
- [Gated recurrent neural networks discover attention](https://mlsanity.com/paper/2309.01775/) (2023)
- [Metalearning Continual Learning Algorithms](https://mlsanity.com/paper/2312.00276/) (2023)
- [Fast On-Device Adaptation for Spiking Neural Networks via Online-Within-Online Meta-Learning](https://mlsanity.com/paper/2103.03901/) (2021)
- [Don't Sweep your Learning Rate under the Rug: A Closer Look at Cross-modal Transfer of Pretrained Transformers](https://mlsanity.com/paper/2107.12460/) (2021)
- [Short-Term Plasticity Neurons Learning to Learn and Forget](https://mlsanity.com/paper/2206.14048/) (2022)
- [Conceptual Framework for Autonomous Cognitive Entities](https://mlsanity.com/paper/2310.06775/) (2023)
- [Real-Time Recurrent Reinforcement Learning](https://mlsanity.com/paper/2311.04830/) (2023)
- [Evolving Decomposed Plasticity Rules for Information-Bottlenecked Meta-Learning](https://mlsanity.com/paper/2109.03554/) (2021)

## Abstract (arXiv)

How can we build agents that keep learning from experience, quickly and efficiently, after their initial training? Here we take inspiration from the main mechanism of learning in biological brains: synaptic plasticity, carefully tuned by evolution to produce efficient lifelong learning. We show that plasticity, just like connection weights, can be optimized by gradient descent in large (millions of parameters) recurrent networks with Hebbian plastic connections. First, recurrent plastic networks with more than two million parameters can be trained to memorize and reconstruct sets of novel, high-dimensional 1000+ pixels natural images not seen during training. Crucially, traditional non-plastic recurrent networks fail to solve this task. Furthermore, trained plastic networks can also solve generic meta-learning tasks such as the Omniglot task, with competitive results and little parameter overhead. Finally, in reinforcement learning settings, plastic networks outperform a non-plastic equivalent in a maze exploration task. We conclude that differentiable plasticity may provide a powerful novel approach to the learning-to-learn problem.