Sitemap
A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
Pages
Posts
On Monads, Monoids and Endofunctors 1: The monoid
Published:
Spoiler: Category theory has applications in machine learning
Stumbling backwards into np.random.seed through jax.
Published:
Spoiler: We’ve all been using randomness wrong
PyTorch Gradient Manipulation 1
Published:
Spoiler: PyTorch offers about five ways to manipulate gradients.
A Machine Learning oriented introduction to PALISADE, CKKS and pTensor.
Published:
Spoiler: You can do math on encrypted numbers
MAPE Madness
Published:
Spoiler: RTFM
Fundamentals Part 2: Hessians and Jacobians
Published:
Spoiler: “H” is before “J”, which means that it’s the second-derivative. Obviously
Fundamentals Part 1: An intuitive introduction to Calculus and Linear Algebra
Published:
Spoiler: The pre-calc of ML
Pusheen The Limit
Published:
Note: The code can be found here: quitPusheenMeAround
portfolio
Portfolio item number 1
Short description of portfolio item number 1
Portfolio item number 2
Short description of portfolio item number 2
publications
APPLE: Automatic patch pattern labeling for explanation
Published in AAAI 2018 New Orleans, 2018
Summary: We proposed a new method for explainability in Convolutional Neural Network Architectures
Download here
Self-Driving Database Management Systems
Published in Conference on Innovative Data Systems Research, 2020
Summary: We explored constructing a self-driving database management system: Peloton DB
Download here
Openfhe: Open-source fully homomorphic encryption library
Published in WAHC 2022: Workshop on Encrypted Computing & Applied Homomorphic Cryptography, 2022
Summary: I was involved in the engineering and design of the library.
Download here
Fully Homomorphic Encryption for Privacy-Preserving Machine Learning Using the OpenFHE Library
Published in Association for the Advancement of Artificial Intelligence (AAAI), 2024
Summary: The OpenFHE team hosted a tutorial session at AAAI 2024, where we introduced fully-homomorphic encryption, ran through some simple examples, and walked participants through how to create an optimized encrypted logistic regression.
reviews
Fall 2023 Quarter Class Review
Published:
My first quarter at UW! Summary: adapting to life in academia from the tech industry.
Winter 2024 Quarter Class Review
Published:
My second quarter at UW! Summary: grant writing takes longer than you think.
Spring 2024 Quarter Class Review
Published:
My third quarter at UW! Summary: No matter how heavy or light my quarters are, I always find a way to overload. Also, I’m rarely satisfied with my accomplishments, but I can confidently say that I’ve finished my first (school) year of my Ph.D. happy with the progress I’ve made.
Fall 2024 Quarter Class Review
Published:
Wow, has it really been a year since I started the program? Summary: Embracing the feeling of being stuck
talks
Thoughts on the Brain and Machine Learning: Biological Plausibility, SNNs, and beyond
Published:
I covered a bit of Neuroscience, discussed the plausibility of backpropagation in the brain, highlighted spiking neural networks and analyzed the Neural Gradient Representation by Activity Differences (NGRAD) algorithm.
Homomorphic Encryption for Encrypted Machine Learning
Published:
I led the hands-on discussion and code walkthrough where attendees were given a hands-on introduction to FHE-backed Machine Learning. I started with a naive first-pass implementation, then walked them through how they might optimize their own code, leading us to an optimized logistic regression implementation
An Informal Introduction to Monoids, Functors and Monads in the Context of Machine Learning
Published:
I gave an experimental talk where I chatted about how concepts in category theory, primarily monoids functors and monads lead to better, cleaner code.
Encrypted Machine Learning
Published:
I led the hands-on discussion and code walkthrough where attendees were given a hands-on introduction to FHE-backed Machine Learning. I started with a naive first-pass implementation, then walked them through how they might optimize their own code, leading us to an optimized logistic regression implementation
Uncovering Rules For Robustness In Biological Neural Networks
Published:
I gave a 15 minute talk geared towards a general audience about my research.
teaching
Software Carpentry
Workshop, Software Carpentry 2024, eScience Institute, 2024
Assistant for Software Carpentry in Python
Accelerating Python with JAX
Workshop, Special Tutorial, eScience Institute, 2024
Instructor for course on Accelerating Python with Jax. I created all the material: Numpy to Jax, answered questions, and guided participants