From Neural Activity to Computation: Biological Reservoirs for Pattern Recognition in Digit Classification
Not on the map. Why?
Abstract (arXiv)
In this paper, we present a biologically grounded approach to reservoir computing (RC), in which a network of cultured biological neurons serves as the reservoir substrate. This system, referred to as biological reservoir computing (BRC), replaces artificial recurrent units with the spontaneous and evoked activity of living neurons. A multi-electrode array (MEA) enables simultaneous stimulation and readout across multiple sites: inputs are delivered through a subset of electrodes, while the remaining ones capture the resulting neural responses, mapping input patterns into a high-dimensional biological feature space. We evaluate the system through a case study on digit classification using a custom dataset. Input images are encoded and delivered to the biological reservoir via electrical stimulation, and the corresponding neural activity is used to train a simple linear classifier. To contextualize the performance of the biological system, we also include a comparison with a standard artificial reservoir trained on the same task. The results indicate that the biological reservoir can effectively support classification, highlighting its potential as a viable and interpretable computational substrate. We believe this work contributes to the broader effort of integrating biological principles into machine learning and aligns with the goals of human-inspired vision by exploring how living neural systems can inform the design of efficient and biologically plausible models.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 15 of its 55 references that are in the map. First posted on arXiv 7 Oct 2025.
Builds on
15 of 55 references.
References · 15
- 2016Towards an integration of deep learning and neurosciencecited by 78
- 2022Hebbian Deep Learning Without Feedbackcited by 61
- 2018Unsupervised Learning by Competing Hidden Unitscited by 44
- 2018Reservoir computing approaches for representation and classification of multivariate time seriescited by 38
- 2019Biologically plausible deep learning -- but how far can we go with shallow networks?cited by 25
- 2017Deep Echo State Network (DeepESN): A Brief Surveycited by 22
- 2022FastHebb: Scaling Hebbian Training of Deep Neural Networks to ImageNet Levelcited by 11
- 2021Highlighting the Importance of Reducing Research Bias and Carbon Emissions in CNNscited by 9
- 2021Continual Learning with Echo State Networkscited by 8
- 2023Spiking Neural Networks and Bio-Inspired Supervised Deep Learning: A Surveycited by 8
- 2020Assessing Pattern Recognition Performance of Neuronal Cultures through Accurate Simulationcited by 7
- 2023Synaptic Plasticity Models and Bio-Inspired Unsupervised Deep Learning: A Surveycited by 7
Built on by
Citing papers per year: 2026: 1.
1 paper.