Matt Faulkner’s Blog

A follow-up to my earlier post on programming a Dvorak layout for the Advantage360.

This post shows how to program a Dvorak layout for the wired Kinesis Advantage360 by directly editing a layout file.

A chronological survey of the zkML field, through 2024. 2017 SafetyNets: Verifiable Execution of Deep Neural Networks on an Untrusted Cloud A restricted class of neural nets that can be represented as arithmetic circuits over finite fields.

This post is a high-level recap of the foundational ideas that led to the first practical zk-SNARKs.

The field of zero-knowledge proofs (ZKPs) has seen some amazing advances in the last several years.

In the previous post about autoencoders, we looked at their ability to compress data into a latent space and then reconstruct it with remarkable fidelity.

The previous post trained an autoencoder for the MNIST images of handwritten digits.

Today, I want to kick off a series of posts about Deep Learning.

The internet has been talking about a list of AI papers that Ilya Sutskever, co-founder of OpenAI, recommended to John Carmack: “So I asked Ilya, their chief scientist, for a reading list.

Introducing Zeebra, a Rust library for zero-knowledge cryptography.