--- tags: PSE --- # ZKML @ Team Novi Click here to know more about [Team Novi](https://0xparc.notion.site/Team-Novi-2d81bc06b0aa4c99b61a9ee06166b3b6) ## Proposed work schedule: 1. [Research and proposal](#1-Research-and-proposal) (2 weeks) 2. [Implementation and benchmark](#2-Implementation-and-benchmark) (5 weeks) 3. [Recommendation and feature requests for Nova](#3-Recommendation-and-feature-requests-for-Nova) (1 week) ## 1. Research and proposal Previously, Nova has been used to fold [models](https://github.com/lyronctk/zator) and [batch inference](https://hackmd.io/@cathie/zkml-folding). What else can we fold? Starting points: * convolutional layer operations? * dense layer operations? * activation layer operations? * ... ## 2. Implementation and benchmark ... ## 3. Recommendation and feature requests for Nova During the process of implementing [Zator](https://github.com/lyronctk/zator), we realized the need to parallelize some operations in [Nova-Scotia](https://github.com/nalinbhardwaj/Nova-Scotia/). After 5 weeks of implementation, we should gain a lot of insights as to what needs to be done to make tools surrounding Nova more user-friendly and effective.
Last changed by  
 
Cathie So
335

Read more

ZKML: Bridging AI/ML and Web3 with Zero-Knowledge Proofs

by drCathieSo.eth

11/9/2023
Folding Circom circuits: a ZKML case study

Zator: Verified inference of a 512-layer neural network using recursive SNARKs 🐊

5/16/2023
ZKML Research Initiatives

ZK-friendly ML paradigms Background For ZK Hack Lisbon, I teamed up with a few ML and cryptography veterans to build Zero Gravity, where we proposed a novel approach to efficiently prove the correctness of machine learning model calculations using Weightless Neural Networks (WNNs), which are combinatorial and do not rely on floating point arithmetic. WNNs learn from input-output pairs using RAM cells as lookup tables, making them more amenable to Zero Knowledge Proofs. The project utilizes Bloom filters to make RAM cells scalable and introduces a new non-cryptographic hash function, the "MishMash", to improve performance. Research Directions/Tasks Implementing the Zero Gravity paradigm in Plonky2/Halo2 Identify and explore other high-accuracy weightless models In particular, evaluate their "ZK-friendliness" by their potential compatibility with ZKP, taking into consideration their computational complexity and performance on real-world datasets. e.g. boolean circuits, binarized neural networks, truth table net, ... Benchmarking (see below)

5/3/2023
Read more from Cathie So
Published on HackMD