# The brain as an efficient and robust adaptive learner

arXiv: https://arxiv.org/abs/1705.08031 · HTML: https://mlsanity.com/paper/1705.08031/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 May 2017.

## Built on by (most cited first, 11 of 11)

- [Training Spiking Neural Networks Using Lessons From Deep Learning](https://mlsanity.com/paper/2109.12894/) (2021)
- [Credit Assignment in Neural Networks through Deep Feedback Control](https://mlsanity.com/paper/2106.07887/) (2021)
- [The least-control principle for local learning at equilibrium](https://mlsanity.com/paper/2207.01332/) (2022)
- [Minimizing Control for Credit Assignment with Strong Feedback](https://mlsanity.com/paper/2204.07249/) (2022)
- [Do Large Language Models Mirror Cognitive Language Processing?](https://mlsanity.com/paper/2402.18023/) (2024)
- [A Normative and Biologically Plausible Algorithm for Independent Component Analysis](https://mlsanity.com/paper/2111.08858/) (2021)
- [Supervised training of spiking neural networks for robust deployment on mixed-signal neuromorphic processors](https://mlsanity.com/paper/2102.06408/) (2021)
- [A Unified and Biologically-Plausible Relational Graph Representation of Vision Transformers](https://mlsanity.com/paper/2206.11073/) (2022)
- [An Extension to Basis-Hypervectors for Learning from Circular Data in Hyperdimensional Computing](https://mlsanity.com/paper/2205.07920/) (2022)
- [Closed-form control with spike coding networks](https://mlsanity.com/paper/2212.12887/) (2022)
- [BioLeaF: A Bio-plausible Learning Framework for Training of Spiking Neural Networks](https://mlsanity.com/paper/2111.13188/) (2021)

## Abstract (arXiv)

Understanding how the brain learns to compute functions reliably, efficiently and robustly with noisy spiking activity is a fundamental challenge in neuroscience. Most sensory and motor tasks can be described as dynamical systems and could presumably be learned by adjusting connection weights in a recurrent biological neural network. However, this is greatly complicated by the credit assignment problem for learning in recurrent network, e.g. the contribution of each connection to the global output error cannot be determined based only on locally accessible quantities to the synapse. Combining tools from adaptive control theory and efficient coding theories, we propose that neural circuits can indeed learn complex dynamic tasks with local synaptic plasticity rules as long as they associate two experimentally established neural mechanisms. First, they should receive top-down feedbacks driving both their activity and their synaptic plasticity. Second, inhibitory interneurons should maintain a tight balance between excitation and inhibition in the circuit. The resulting networks could learn arbitrary dynamical systems and produce irregular spike trains as variable as those observed experimentally. Yet, this variability in single neurons may hide an extremely efficient and robust computation at the population level.