A Supervised STDP-based Training Algorithm for Living Neural Networks

10/30/2017
by   Yuan Zeng, et al.
0

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 MNIST benchmark for handwritten digit recognition.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/28/2019

Inference with Hybrid Bio-hardware Neural Networks

To understand the learning process in brains, biologically plausible alg...
research
06/30/2022

Bio-inspired Machine Learning: programmed death and replication

We analyze algorithmic and computational aspects of biological phenomena...
research
04/08/2021

Classification, Slippage, Failure and Discovery

This text argues for the potential of machine learning infused classific...
research
06/20/2017

Chemception: A Deep Neural Network with Minimal Chemistry Knowledge Matches the Performance of Expert-developed QSAR/QSPR Models

In the last few years, we have seen the transformative impact of deep le...
research
03/03/2022

A photonic chip-based machine learning approach for the prediction of molecular properties

Machine learning methods have revolutionized the discovery process of ne...
research
03/06/2017

Computational Eco-Systems for Handwritten Digits Recognition

Inspired by the importance of diversity in biological system, we built a...
research
09/15/2016

A Tutorial about Random Neural Networks in Supervised Learning

Random Neural Networks (RNNs) are a class of Neural Networks (NNs) that ...

Please sign up or login with your details

Forgot password? Click here to reset