building-babylon.net - Building Babylon – Scribbles on maths and machine learning

home > domains > building-babylon.net

Example domain paragraphs

Scribbles on maths and machine learning

This paper ( arXiv ), authored by Petersen, Borgelt, Kuehne and Deussen, was accepted for NeurIPs 2022. It does one of my favourite things: it learns a discrete structure (in this case, a boolean circuit) via differentiable means. Logic gate networks came up in a recent ZKML discussion as a machine learning paradigm of interest: since boolean circuits are encodable as arithmetic circuits, proving inference runs of a logic gate network can be done without the loss of accuracy that is inherent in the quantiza

A differentiable logic gate network consists of multiple layers of “neurons” with random wiring: Each neuron has precisely two inputs and is a superposition of the possible binary logic gates: where the probabilities (in purple) are learned from the data (using the softmax parameterization ).

Links to building-babylon.net (2)

• moduluslabs.xyz Modulus
• modulus.xyz Modulus