Skip to content

Aste21/Digit-Recognizer-From-Scratch

View on GitHub ↗Related repositories →

A neural network trained to recognize handwritten digit. The neural network is written from scratch in java using only NDArray class in DJL library. The dataset is provided by MNIST. After 500 iterations it got to 83% accuracy.

active 2024-01-242024-01-24 (UTC)

Complete coverage26,566 / 26,566 hourly files (100%) · 2 absent upstream2023-08-152026-08-25 (UTC)
Events
4
Pushes
2
Pull requests
0
Issues
0
Stars
0
Forks
0

Activity over time

Daily event counts in the loaded window

Line chart, 1 days from 2024-01-24 to 2024-01-24. Pushes: 2 total, peak 2 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 0 total, peak 0 in a day. Comments: 0 total, peak 0 in a day. Stars: 0 total, peak 0 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
Aste212200

Recent activity

Latest issues, pull requests and releases

No issue or PR events — this repo's activity is pushes only.

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 0 stars here means stars gained during the window, not the repo's star count.