Digit Recognizer Neural Network Game icon

Digit Recognizer Neural Network 1.2

23.3 MB / 0+ Downloads / Rating 3.5 - 2 reviews


See previous versions

Digit Recognizer Neural Network, developed and published by edweenoki, has released its latest version, 1.2, on 2018-08-01. This app falls under the Educational category on the Google Play Store and has achieved over 10 installs. It currently holds an overall rating of 3.5, based on 2 reviews.

Digit Recognizer Neural Network APK available on this page is compatible with all Android devices that meet the required specifications (Android 4.1+). It can also be installed on PC and Mac using an Android emulator such as Bluestacks, LDPlayer, and others.

Read More

Game Screenshot

Game Screenshot

Game Details

Package name: com.edweenoki.DigitRecognizerNeuralNetwork

Updated: 7 years ago

Developer Name: edweenoki

Category: Educational

New features: Show more

App Permissions: Show more

Installation Instructions

This article outlines two straightforward methods for installing Digit Recognizer Neural Network on PC Windows and Mac.

Using BlueStacks

  1. Download the APK/XAPK file from this page.
  2. Install BlueStacks by visiting http://bluestacks.com.
  3. Open the APK/XAPK file by double-clicking it. This action will launch BlueStacks and begin the application's installation. If the APK file does not automatically open with BlueStacks, right-click on it and select 'Open with...', then navigate to BlueStacks. Alternatively, you can drag-and-drop the APK file onto the BlueStacks home screen.
  4. Wait a few seconds for the installation to complete. Once done, the installed app will appear on the BlueStacks home screen. Click its icon to start using the application.

Using LDPlayer

  1. Download and install LDPlayer from https://www.ldplayer.net.
  2. Drag the APK/XAPK file directly into LDPlayer.

If you have any questions, please don't hesitate to contact us.

Game Rating

3.5
Total 2 reviews

Reviews

5 ★, on 2018-07-30
Cool!

Previous Versions

Digit Recognizer Neural Network 1.2
2018-08-01 / 23.3 MB / Android 4.1+

About this app

This digit recognition application is able to detect and identify single numerical digits (0-9). It served as a great experiment that tested the skills I've gained after completing Andrew Ng’s Machine Learning course on Coursera. The 3 layered neural network was trained on 5000 training examples (that I have modified) from the MNIST database of handwritten digits on Octave. Then, I transferred over the test pre-trained weights over to Unity3D, where I have just implemented forward propagation using these weights.

In the about section within the app, I have briefly outlined the how the recognizer works while explaining the inner workings of Feedforward Neural Networks if you're curious.

Upon thorough testing (5 minutes), I have come to the conclusion that the digit recognizer I have built is unable to recognize digits at a state of the art performance. I believe this is due to a lack of training data. Considering this project was created from an experimental perspective, I have decided to settle for now. I may decide to add more data from the MNIST data later in my life.

...It may be a little rough around the edges, but I will always love my firstborn.

If you would like to check out the source code:
https://github.com/edweenie123/Digit-Recognition-App

New features

Hopefully fixed scaling issues on different devices

App Permissions

Allows applications to open network sockets.