cd /news/artificial-intelligence/absl-100-integer-only-neural-network… · home topics artificial-intelligence article
[ARTICLE · art-80282] src=github.com ↗ pub= topic=artificial-intelligence verified=true sentiment=↑ positive

ABSL – 100% Integer-Only Neural Network Training in Rust

A 15-year-old developer in Germany has released ABSL (Adaptive Bit-Shift Learning) v1.0.0, a 100% integer-only neural network training algorithm written in Rust that achieves 91.1% global accuracy on the XOR problem by eliminating floating-point math and using adaptive bit-shifting for weight updates. The algorithm, which runs on ultra-low-power embedded systems without FPUs, improves perfect-run rate from 38.7% in v3 to 70.1% in v5 and is being tuned toward 99%+ accuracy and MNIST scaling.

read2 min views1 publishedJul 30, 2026
ABSL – 100% Integer-Only Neural Network Training in Rust
Image: source

ABSL (Adaptive Bit-Shift Learning) is an experimental, 100% integer-only learning algorithm for neural networks, written from scratch in Rust.

By completely avoiding floating-point math (float

), ABSL eliminates the need for expensive FPUs (Floating Point Units). This makes it natively compatible with ultra-low-power embedded systems, 8-bit/16-bit microcontrollers, and neuromorphic hardware.

Instead of traditional learning rates, ABSL dynamically scales weight updates using an adaptive bit-shifting mechanism based on integer error magnitudes.

Historically, solving the non-linear XOR problem required continuous floating-point gradients. ABSL v1.0.0 completely shatters the myth that integer training is bound to get stuck in local minima due to harsh rounding errors.

By scaling up the hidden layer to a 2-3-1 architecture (2 Inputs, 3 Hidden Neurons, 1 Output), ABSL introduces enough high-dimensional redundancy to bypass integer quantization bottlenecks.

Metric ABSL v3 ABSL v5 (v1.0.0 Core)
Perfect Runs (4/4 Correct)
38.7 % 70.1 % 🔥
Global Accuracy
80.0 % 91.1 %
Avg. Correct Cases per Run
3.20 / 4 3.64 / 4
Total Failures (0, 1, or 2 Correct)
High 0.0 % (Always gets ≥ 3/4)

(0,0): 88.2%(Current tuning target: eliminating low-level integer bias leakage)(0,1): 99.4% ✨**(1,0):** 99.6% ✨**(1,1):** 77.1%(Current tuning target: optimizing negative integer inhibition)

ABSL snaps continuous gradients into a discrete integer grid using native Rust performance:

impl LearningRule for ABSLv5 {
    fn update(&self, error: i32, input: i32, weight: i32, _epoch: u32) -> i32 {
        let shift = Self::calculate_shift(error, weight);
        (((error as i64) * (input as i64)) >> shift) as i32
    }
}

The shift

is dynamically calculated using bit-lengths (ilog2

) of both the error and weight magnitudes, preventing weight explosion while keeping execution blindingly fast.

I am actively working on pushing the success rate from 70.1% to 99%+.

  • Implement a discrete integer damping factor (Momentum equivalent) to prevent weight oscillation.
  • Scale to MNIST.

##About Me:

I'm 15 living in Germany cirrntly in 10th grade and coded al of this on a broken s22 Ultra

In the future i want to study and work even more with this topic

Costum Licene please look in LICENSE

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @absl 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/absl-100-integer-onl…] indexed:0 read:2min 2026-07-30 ·