Is this skill compatible with standard neural networks?

While designed for ternary and quantized networks, the discrete optimization principles can be applied to any parameter-based system where traditional backpropagation fails.

What is Discrete Backprop?

Discrete Backprop is a gradient-free learning method that estimates parameter updates using discrete perturbations—specifically trits {-1, 0, +1}—instead of continuous floating-point gradients.

Why use trit-based learning?

Trit-based learning is highly efficient for hardware because it replaces complex multiplications with simple additions and subtractions, and it works on functions that aren't mathematically differentiable.

Can this skill handle high-dimensional models?

Yes, it includes a Simultaneous Perturbation implementation (similar to SPSA) that can estimate gradients for all dimensions using only two loss evaluations per step.

Discrete Backprop

Name: Discrete Backprop
Author: plurigrid

byplurigrid

•

Data Science & ML

Implements gradient-free optimization and ternary learning using discrete trit-based perturbations for non-differentiable systems.

The Discrete Backprop skill enables Claude to perform machine learning and optimization in environments where traditional continuous gradients are unavailable or computationally expensive. By utilizing a trit-based approach {-1, 0, +1}, it facilitates the training of quantized ternary neural networks, optimizes non-differentiable functions like hash lookups or conditional logic, and solves complex combinatorial problems. This skill is ideal for developers working on hardware-efficient AI, neuromorphic computing, or GF(3) systems that require native discrete learning patterns.

Key Features

012 GitHub stars

02Gradient-free optimization for non-differentiable and discrete functions

03Native GF(3) conservation logic for balanced parameter updates

04Ternary Neural Network (TNN) implementation for multiplier-less inference

05Simultaneous Perturbation (SPSA) for efficient high-dimensional gradient estimation

06Support for quantized learning in binary and ternary systems

Use Cases

01Optimizing software logic involving branching and non-differentiable conditionals

02Training ultra-low-power AI models for FPGA or edge hardware deployment

03Solving discrete combinatorial optimization problems in search and logistics

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add plurigrid/asi discrete-backprop

For use in Claude.ai and ChatGPT

Download Skill