A Supervised STDP-based Training Algorithm for Living Neural Networks

TL;DR

This paper introduces a supervised STDP-based training algorithm for living neural networks, demonstrating its potential for machine learning tasks like digit recognition with notable accuracy.

Contribution

It presents a novel supervised learning algorithm tailored for living neural networks, integrating neuron engineering constraints for practical application.

Findings

Achieved 74.7% accuracy on MNIST digit recognition.

Proposed algorithm considers biological neuron constraints.

Demonstrated feasibility of using living neural networks for machine learning.

Abstract

Neural networks have shown great potential in many applications like speech recognition, drug discovery, image classification, and object detection. Neural network models are inspired by biological neural networks, but they are optimized to perform machine learning tasks on digital computers. The proposed work explores the possibilities of using living neural networks in vitro as basic computational elements for machine learning applications. A new supervised STDP-based learning algorithm is proposed in this work, which considers neuron engineering constrains. A 74.7% accuracy is achieved on the MNIST benchmark for handwritten digit recognition.