Ever since I was a kid, I’ve had a passion for denoising weak signals. I would scream at my parents whenever they would model a Poisson Process wrong or send incorrect motor plans to a multi-agent swarm of robot arms.
(Project Shown: Autonomous Robotic Helper Backpack – CyborgDistro.com)
As a postdoctoral scholar at the University of California, San Diego (UCSD), I currently work in the lab of Prof. Jonathan Sebat on algorithmic methods for analyzing genomic and neural data sets. My short term goal is to use machine learning and robotic methods to help improve signal discrimination in these incredibly noisy, high-dimensional data sets. My long term goal is to use the fundamental science learned from a studied intersection of genomics, machine learning, and neuroscience towards a new “Biologically-Inspired Deep Learning” framework for robots.
Previously, I defended my PhD dissertation work at the Robotics Institute, Carnegie Mellon University (CMU) in July 2015! My PhD thesis was on Bayesian Aggregation, a machine learning framework to conquer tough denoising problems (applied to scientific domains such as radiation spectrometry).
I have an M.S. in Robotics with emphasis on AI/ML/Statistics from CMU, as well as a B.S. in Computer Engineering/Computer Science with emphasis on software and hardware and a Thematic Option Liberal Arts certificate from the University of Southern California (USC).
My research mission is in using science and engineering to fundamentally advance engineering that then, subsequently, fundamentally advances science, the humanities, and makes the world a more delightful place for all humans, robots, and neuro-quantum cyborgs. I strongly believe good parameter optimization, the right statistical conditioning polices, and the right neuro-quantum cyborg computer hardware are the answer to the world’s problems. Parameter optimization can save the world – keep us safe, cure disease, and build better products. One parameter at a time is suboptimal, though, so branch and bound and gradient descent are our robotic overlords.
My research is driven by practical, scalable, cost-effective, and energy-efficient approaches to building Strong AI systems. To that end, I am learning to code in quantum programming languages via instructing a Quantum Robotics Reading Group (quantumrobotics.info). I am helping formulate Biologically-Inspired Deep Learning (Computational Neuroscience applied to Deep Learning). Finally, if you want to hire me for “Big Data,” my interests are in DNA storage with real biological genetic algorithms that analyze zettabytes (10^6 petabytes) of data.
Here are some of my current research topic areas and interests related to Genomics/Robotics/ML/AI (in no particular order):
- Working on building better models of structural variation mutation rate in the human genome as a postdoc in the UCSD Sebat Lab. Poster published at American Society for Human Genetics (ASHG) 2018.
- Worked on improving approaches to pathogenicity prediction of structural variation using machine learning. Poster published at Society for Neuroscience (SfN) 2018.
- Organizer for NIPS Machine Learning for Health (ML4H) Workshop in December 2017. Workshop successfully aggregated clinicians and machine learning experts to discuss healthcare domain applications!
- The Quantum Robotics Group I helped spearhead published a book in January 2017, Quantum Robotics: A Primer on Current Science and Future Perspectives. Book available on Amazon via Morgan Claypool Publishers!
- Deep Learning consultant for UCSF Strigo lab exploring Deep Learning architectures for fMRI of pain representation task. Presented to Siemens Research Group, New Jersey in 2017!
- Explored EMG and EEG signal processing as part of CyborgDistro plans to control multiple robot arms! CyborgDistro was featured on RaspPiPod, Adafruit, as a quarterfinalist in the Hackaday 2015 Prize Contest, and a winner of the Element 14 Halloween Build-A-Thon!
- I defended my PhD Dissertation on Bayesian Aggregation at Robotics Institute, Carnegie Mellon University in July 2015. PhD Awarded!
- Developed general machine learning algorithms for neural data and applications to experimental physics. Posters presented at Big Neuro Data and Aleph workshops at NIPS 2015.
- Developed algorithms for Fault-Tolerant Radiological Threat Detection using Bayesian Reliability Models and Anomaly-Match Bayesian Aggregation (AM-BA) for Efficient Radiation Source Search. Posters presented at IEEE Nuclear Science Symposium 2015.
- Lead developer of Lunar Tabs, an Intelligent, Accessible Guitar Tab Reader. Developed personalized difficulty classifiers for guitar learners using large amounts of guitar tab data online, enabling swarms of humans and robots to autonomously learn guitar. Project poster featured at AAAI 2015.
- Building Biologically-Inspired Deep Learning algorithms that are more pragmatic, realistic, and believable by being more biologically plausible than backpropagation for tasks such as neural hammering. They can also have better optimization properties! Senior thesis on population-coded neural network controlled robots still pending publication after 6 years. When will the world be ready for Biologically-Plausible Deep Learning?