paper-with-me

Papers

Recognition of handwritten MNIST digits on low-memory 2 Kb RAM Arduino board using LogNNet reservoir neural network

2021-04-20 · Y. A. Izotov, A. A. Velichko, A. A. Ivshin, R. E. Novitskiy

The presented compact algorithm for recognizing handwritten digits of the MNIST database, created on the LogNNet reservoir neural network, reaches the recognition accuracy of 82%. The algorithm was tested on a low-memory Arduino board with 2 Kb static RAM low-power microcontroller. The dependences of the accuracy and time of image recognition on the number of neurons in the reservoir have been investigated. The memory allocation demonstrates that the algorithm stores all the necessary information in RAM without using additional data storage, and operates with original images without preliminary processing. The simple structure of the algorithm, with appropriate training, can be adapted for wide practical application, for example, for creating mobile biosensors for early diagnosis of adverse events in medicine. The study results are important for the implementation of artificial intelligence on peripheral constrained IoT devices and for edge computing.

📄 PDF Abstract BibTeX arXiv:2105.02953

Code (1)

izotov93/LogNNet_Arduino

Tasks

Edge-computing

Similar Papers 제목 키워드 기반

A Sobel-Gradient MLP Baseline for Handwritten Character Recognition

2025-08-16 · Azam Nouri arxiv

We revisit the classical Sobel operator to ask a simple question: Are first-order edge maps sufficient to drive an all-dense multilayer perceptron (MLP) for handwritten character recognition (HCR), as an alternative to c…

MNIST-MIX: A Multi-language Handwritten Digit Recognition Dataset

2020-04-08 · Weiwei Jiang

In this letter, we contribute a multi-language handwritten digit recognition dataset named MNIST-MIX, which is the largest dataset of the same type in terms of both languages and data samples. With the same data format w…

Handwritten Digit Recognitionimbalanced classification

Handwritten Digits Recognition using Deep Convolutional Neural Network: An Experimental Study using EBlearn

2013-07-14 · Karim M. Mahmoud

In this paper, results of an experimental study of a deep convolution neural network architecture which can classify different handwritten digits using EBLearn library are reported. The purpose of this neural network is …

Effective Handwritten Digit Recognition using Deep Convolution Neural Network

2020-04-30 · International Journal of Advanced Trends in Computer Science and Engineering 2020 4 · Yellapragada SS Bharadwaj, Rajaram P, Sriram V.P, Sudhakar S 외

This paper proposed a simple neural network approach towards handwritten digit recognition using convolution. With machine learning algorithms like KNN, SVM/SOM, recognizing digits is considered as one o…

BIG-bench Machine LearningHandwritten Digit Recognition

Unsupervised Online Learning With Multiple Postsynaptic Neurons Based on Spike-Timing-Dependent Plasticity Using a TFT-Type NOR Flash Memory Array

2018-11-17 · Soochang Lee, Chul-Heung Kim, Seongbin Oh, Byung-Gook Park 외

We present a two-layer fully connected neuromorphic system based on a thin-film transistor (TFT)-type NOR flash memory array with multiple postsynaptic (POST) neurons. Unsupervised online learning by spike-timing-depende…

General Classification