NeuralNet-MNIST

Digit recognizer

An open-source project that trains a neural network using the MNIST dataset to recognize handwritten digits.

An MNIST handwriting trainer for NeuralNet

GitHub

34 stars
5 watching
12 forks
Language: Swift
last commit: over 9 years ago

Related projects:

RepositoryDescriptionStars
amitshekhariitbhu/androidtensorflowmnistexampleA machine learning project that trains an Android model to recognize handwritten digits using TensorFlow and MNIST dataset.463
davidstutz/matlab-mnist-two-layer-perceptronA Matlab implementation of a two-layer perceptron to recognize handwritten digits from the MNIST dataset.60
swift-ai/neuralnet-handwriting-iosAn iOS app demonstrating handwriting recognition using deep learning and NeuralNet179
joeledenberg/digitrecognitionA simple implementation of a digit recognition system using neural networks96
jdrzj/handwritten-digits-recognitionA handwritten digits recognition system built using neural networks and Ruby6
iwatake2222/pico-mnistRecognizes handwritten digits on an LCD display using Raspberry Pi Pico and TensorFlow Lite60
liushenwenyuan/matlab_orcA Matlab implementation of a handwritten digit recognition system using neural networks.50
matlab-deep-learning/seven-segment-digit-recognitionAutomates digit recognition in images of seven segment displays7
jacopomangiavacchi/mnist-coreml-trainingA demo project to train an ML model on the MNIST dataset using CoreML and SwiftCoreMLTools157
b3ll/swiftygesturerecognitionAn Xcode playground project to simplify UIGestureRecognizers prototyping163
swift-ai/neuralnetA Swift implementation of a fully connected, feed-forward artificial neural network for deep learning and machine learning applications.212
franck-dernoncourt/neuronerNamed-entity recognition using neural networks.1,701
aaronhma/ngconf-2020A repository containing code and slides for a machine learning tutorial on using TensorFlow.js to classify handwritten digits11
didierbrun/dbpathrecognizerA tool for recognizing and matching gestures on touch screens by analyzing sequences of points1,176
ttseng/microbit-mlA gesture recognition tool using machine learning and Microbit's accelerometer data to classify user gestures6