Home  /  Educational Games  / Digit Recognizer Neural Network on Windows Pc

Digit Recognizer Neural Network on Windows Pc

Developed By: edweenoki

License: Free

Rating: 3,5/5 - 2 votes

Last Updated: December 26, 2023

Download on Windows PC

Compatible with Windows 10/11 PC & Laptop

Game Details

Version 1.2
Size 23.3 MB
Release Date August 01, 18
Category Educational Games

Game Permissions:
Allows applications to open network sockets. [see more (1)]

What's New:
Hopefully fixed scaling issues on different devices [see more]

Description from Developer:
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 comple... [read more]

Game preview ([see all 15 screenshots])

Game preview

About this game

On this page you can download Digit Recognizer Neural Network and play on Windows PC. Digit Recognizer Neural Network is free Educational game, developed by edweenoki. Latest version of Digit Recognizer Neural Network is 1.2, was released on 2018-08-01 (updated on 2023-12-26). Estimated number of the downloads is more than 10. Overall rating of Digit Recognizer Neural Network is 3,5. Generally most of the top apps on Android Store have rating of 4+. This game had been rated by 2 users, 1 users had rated it 5*, 1 users had rated it 1*.

How to play Digit Recognizer Neural Network on Windows?

Instruction on how to play Digit Recognizer Neural Network on Windows 10 Windows 11 PC & Laptop

In this post, I am going to show you how to install Digit Recognizer Neural Network on Windows PC by using Android App Player such as BlueStacks, LDPlayer, Nox, KOPlayer, ...

Before you start, you will need to download the APK/XAPK installer file, you can find download button on top of this page. Save it to easy-to-find location.

[Note] You can also download older versions of this game on bottom of this page.

Below you will find a detailed step-by-step guide, but I want to give you a fast overview of how it works. All you need is an emulator that will emulate an Android device on your Windows PC and then you can install applications and use it - you see you're playing it on Android, but this runs not on a smartphone or tablet, it runs on a PC.

If this doesn't work on your PC, or you cannot install, comment here and we will help you!

Step By Step Guide To Play Digit Recognizer Neural Network using BlueStacks

  1. Download and Install BlueStacks at: https://www.bluestacks.com. The installation procedure is quite simple. After successful installation, open the Bluestacks emulator. It may take some time to load the Bluestacks app initially. Once it is opened, you should be able to see the Home screen of Bluestacks.
  2. Open the APK/XAPK file: Double-click the APK/XAPK file to launch BlueStacks and install the application. If your APK/XAPK file doesn't automatically open BlueStacks, right-click on it and select Open with... Browse to the BlueStacks. You can also drag-and-drop the APK/XAPK file onto the BlueStacks home screen
  3. Once installed, click "Digit Recognizer Neural Network" icon on the home screen to start playing, it'll work like a charm :D

[Note 1] For better performance and compatibility, choose BlueStacks 5 Nougat 64-bit read more

[Note 2] about Bluetooth: At the moment, support for Bluetooth is not available on BlueStacks. Hence, apps that require control of Bluetooth may not work on BlueStacks.

How to play Digit Recognizer Neural Network on Windows PC using NoxPlayer

  1. Download & Install NoxPlayer at: https://www.bignox.com. The installation is easy to carry out.
  2. Drag the APK/XAPK file to the NoxPlayer interface and drop it to install
  3. The installation process will take place quickly. After successful installation, you can find "Digit Recognizer Neural Network" on the home screen of NoxPlayer, just click to open it.

Discussion

(*) is required

Download older versions

Other versions available: 1.2.

Download Digit Recognizer Neural Network 1.2 on Windows PC – 23.3 MB

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
Hopefully fixed scaling issues on different devices
Allows applications to open network sockets.