Sudoku # is made and published by Jinyang Tang. AppBrain is an independent app data site and isn't affiliated with Jinyang Tang. The app name, icon, screenshots and description belong to Jinyang Tang and are shown as published on the App Store.
AppBrain's verdict
EstablishedLoved by users- Rating on App Store
- 4.66
- 392 ratings
- Last updated
- August 30, 2023
Users love it: 4.7 stars from 392 ratings.
Rankings
App Store top chartsApp Store Rankings for Sudoku #
Competitors
Similar apps and more from Jinyang TangAlternatives to Sudoku #
More from Jinyang Tang
Releases
Updates seen on the App Store- Version
- 7.2
- Launched
- January 2020
No changelog data
User feedback
Ratings and reviews on the App StoreComments on Sudoku # for iOS
We don't have enough comments to show example comments. Please check back later.
Technology
Found in the app by AppBrain- Price
- Free
- App size
- 142.2 MB
- Content rating
- Everyone
Technologies used by Sudoku #
About the app and developer
About Sudoku #
Sudoku # is a games app developed by Jinyang Tang.
User Ratings
Sudoku # is rated 4.66 out of 5 stars. The rating is based on 390 ratings.
App Information
Sudoku # is freely available from the App Store. The app size is 142.23 MB. The latest version available is 7.2. The last update was on August 30, 2023.
Technical Requirements
The app has a content rating of Everyone. The app has been available on the App Store since January 2020.
Developer information for Jinyang Tang
Address:
Store listing
By Jinyang Tang, from the App Store
Description by Jinyang Tang Written by the developer, not by AppBrain. Click to read.
Our Sudoku is one of its own kind in the market. We use AI and Machine Learning to design the levels that bring a unique and fun experience to everyone.
- Exercise your brain, memory and logic reasoning skills
- 5 difficulty options, tons of levels, tons of fun
- Levels designed by AI and Machine Learning
*How to play*
Fill the 9x9 board so that each row, column and 3x3 box contains all digits from 1 to 9.
*Designed by AI*
1. Randomly generate 35,000+ valid board configurations for each difficulty levels
2. Classify “human solvable” boards using non-brute-force algorithms implemented using TensorFlow
3. These algorithms uses the same techniques as human solvers do, to filter out boards almost unsolvable by human
4. Less than 4% of these initial boards passed our AI test
5. Finally we validate the filtered sample with human testing to ensure board quality