Mike Heddes in the Hills of Orange County

Mike Heddes

Machine Learning Researcher

Personal statement

I am Mike Heddes, a Computer Science PhD student researching Machine Learning at the University of California, Irvine with a background in Mechanical Engineering. I enjoy tackling hard problems in an interdisciplinary setting. My work focuses on the intersection of Machine Learning and Embedded Systems. My ambition is to add to the inspiring achievements of humanity and to ensure our longevity. I'm captivated by everything space related in addition to meticulous design and engineering.

Projects

Torchhd: An Open-Source Python Library to Support Hyperdimensional Computing Research

With Torchhd we want to make Hyperdimensional Computing (HDC) more accessible and provide an efficient foundation for research and application development. The easy-to-use and high-performance library builds on top of PyTorch and features state-of-the-art HDC functionality, clear documentation and implementation examples.

View publication →View project →

An Extension to Basis-Hypervectors for Learning from Circular Data in Hyperdimensional Computing

In this work we present a detailed study on basis-hypervector sets, which leads to practical contributions to HDC in general: 1) an improvement for level-hypervectors, used to encode real numbers; 2) a method to learn from circular data, an important type of information never before addressed in machine learning with HDC.

View publication →

Hyperdimensional Hashing: An Efficient and Robust Dynamic Hash Table

Published at Design Automation Conference (DAC) 2022

Most cloud services and distributed applications rely on hashing algorithms that allow dynamic scaling of a robust and efficient hash table. Examples include AWS, Google Cloud and BitTorrent. We propose Hyperdimensional (HD) hashing and show that it has the efficiency to be deployed in large systems.

View publication →
Nominated for Best Paper

GraphHD: Efficient Graph Classification using Hyperdimensional Computing

Published at Design, Automation and Test Europe (DATE) Conference 2022

Graphs are among the most important forms of information representation, yet, to this day, Hyperdimensional Computing algorithms have not been applied to the graph learning problem in a general sense. In this paper, we present GraphHD — a baseline approach for graph classification with HDC.

View publication →

Jet Fighter Ai

Personal project in Reinforcement Learning, 2021

A Reinforcement Learning agent learns to play the two-player Atari game Jet Fighter. Visitors can play against the agent in an Atari-style simulator on the project page.

View project →

EdgeAvatar: An Edge Computing System for Building Virtual Beings

Published in Electronics 2021

We describe EdgeAvatar, a system based on Edge Computing principles for the creation of virtual beings. The objective is to provide a streamlined and modular framework for virtual being applications that are to be deployed in public settings. EdgeAvatar can be adapted to fit different approaches for AI powered conversations.

View publication →View project →

Space Optimization Competition Platform

Project at the European Space Agency 2019

SpOC (Space optimization Competition) is an optimization challenge, hosted on the European Space Agency's Optimize platform, that has experts around the world compete to solve three complex optimization problems wrapped up in a stimulating and exotic space mission scenario.

View project →
Featured in a BBC documentary

Settlers of the Galaxy

Personal project in Animation & Interaction, 2019

Interactive animation of the Milky Way galaxy that includes our Solar System. Based on data from the GTOC X trajectory optimization challenge proposed by NASA's Jet Propulsion Laboratory (JPL).

View project →
Bachelor Thesis

Differentiable Cartesian Genetic Programming Interface

Project at the European Space Agency, 2019

Differentiable Genetic Cartesian Programming (dCGP) is a Machine Learning tool for symbolic regression. DCGP generates explicit formulas that can be understood and studied. Our software thus provides a form of explainable AI, which can be applied to any supervised learning task.

View project →View thesis pdf →

SpaceX Grid Fin Design

Personal project in Animation & Interaction, 2018

Interactive 3D model of the second generation Space X grid fin as flown on the Falcon 9 rocket. The grid fins are made from titanium so that they can be reused.

View project →

Music Production

During high school and college I dreamed of becoming an electronic dance music producer like Martin Garrix, the Swedish House Mafia, or Avicii. Over the years my dream of being a music producer faded away while my interest in science grew. Making music is now a hobby of mine.

Listen on Spotify →Listen on Apple Music →Listen on YouTube →