ABSL v1.0.0: I trained a Neural Network to solve XOR using 100% Integers (No Floats, No FPUs, Written in Rust)
Article summary
Quick briefing — cleaned from the original RSS feed
ABSL or Adaptive bitshift learning v.1.0.0 XOR Is a Integer only learning method for AI wich i developed it performes verry good with 75% of runs being perfekt and a global evaluation accuracy of 92.9% at its best. I'm currently tring to make it perfekt and then try scaling it to MNIST I'm 15 fron germany coding on a S22 Ultra Here you find my repo: https://github.com/Mojo0869/ABSL
1Key Takeaways
- ABSL or Adaptive bitshift learning v.1.0.0 XOR Is a Integer only learning method for AI wich i developed it performes verry good with 75% of runs being perfekt and a global evaluation accuracy of 92.9% at its best.
- I'm currently tring to make it perfekt and then try scaling it to MNIST I'm 15 fron germany coding on a S22 Ultra Here you find my repo: https://github.com/Mojo0869/ABSL.
2AIWedia Score
8.6/10
High relevance — worth your attention today
Based on source trust, recency, category impact, and story depth.
3Why it matters
Coding AI shifts how fast software ships and how much human review each change needs. DEV — ML reports that aBSL or Adaptive bitshift learning v.1.0.0 XOR Is a Integer only learning method for AI wich i developed it performes verry good with 75% of runs being perfekt and a global evaluation accuracy of 92.9% at its best.
Explore related
Browse toolsCoding AI news
Explore curated coding ai tools on AIWedia — compare, rank, and launch from our directory.
Full story on DEV — ML
Read full articleHeadlines aggregated via RSS for discovery on AIWedia. Original content © DEV — ML. We link to the source and do not republish full articles.