Phillip Kuznetsov

Currently a software engineer at Pixie Labs. Previously a Research Assistant in Alyosha Efros's Lab and Data Science consultant through Alinea.AI. I completed my undergraduate in EECS at UC Berkeley in Spring of 2018.

I founded the student org Machine Learning at Berkeley where we developed ML courses, prototyped ML solutions for Bay Area companies, and researched ML with Berkeley labs.

Email: me@ this website dot com

GitHub  /  LinkedIn

Try it out at https://pixielabs.ai/. Acquired by New Relic Dec. 2020

Chapter surveying the field of Adversarial Machine Learning with connections to AI Safety.

Work demonstrating that Universal Adversarial Attacks transfer between child models of Meta-Learned models than from models that are initialized randomly.

Work demonstrating that Universal Adversarial Attacks transfer between child models of Meta-Learned models than from models that are initialized randomly.

Founded UC Berkeley's first Machine Learning student organization. President in Spring Semester of 2018.

One of the sponsored teams entered in the inaugural Alexa Prize competition. Given a $100k research grant and unlimited to AWS to build a conversational chatbot.

We attempt to apply textures automatically to non-textured images of 3d renderings using convolutional neural networks as a final step in a graphics pipeline. Our final product is a system in which you can pass an untextured rendering with a texture cue into a trained convolutional neural network that then outputs a fully textured result.

First Open-source Implementation of Creative Adversarial Networks. Adapts the Generative Adversarial Network objective function to try to maximize the entropy for a style-class distribution, while also minimizing the original adversarial objective.

We propose a method to apply a pre-trained Generative Adversarial Networks to image compression. The proposed method removes significant portions of an image while retaining some assistant information, and fills the gaps using generative model inpainting. We use Plug and Play Generative Networks as our inpainting network, and explore several different ablation schemes in order to determine the most useful information present in an image, according to the quality of the reconstruction.

Asynchronous neural network implementation using Hebbian learning rules. Later adapted to replace local Hebbian rules with RL approach based on DDPG.

Multiple node cluster built out of 32 Raspberry PI B+. Networked together using a standard network switch. Bootstrapped a custom power supply originall intended for Christmas lights. Utilized Erlang to communicate between the compute nodes and run the above algorithm across all machines.

Machine Learning Decal

Workshops