README.md

In-sensor reservoir computing for language learning via two-dimensional memristors

This repository is an implementation of the readout layer in this paper.

Requirements

To install requirements:

pip install -r requirements.txt

A. Data preprocessing

In 'Data_preprocessing.ipynb', you can model neuron output currents with Gaussian distributions of varying standard deviations.

We don't share the data of neuron output currents.

B. Linear classification

You can simulate the linear classification in 'Linear_classification.ipynb'. Supervised learning models like single-layer perceptron, support vector machine, and logistic regression were used for the readout layer.