RSSAmplifier

Blog

Home on George Chemmala

Recent content in Home on George Chemmala

george.chemmala.comRSS feed ↗46 posts

Latest posts

Doomsday Algorithm

Practice the Doomsday algorithm

FA Designer

Design tool for finite automata

How To Set Up Isabelle On VSCode (Mac)

A quick tutorial to open isabelle on a VSCode style editor

Magic 8 Ball

Ask the Magic 8 Ball a question and get an answer using three.js

Img to ASCII

Convert images to ASCII art

Julia Set Filter

Become the Julia Set with your webcam

Cipher

Crypto tools

Quotes

A collection of quotes over the years that I like

Animation

Hover over the letters to see the animation!

An MNIST Demo Using TensorFlow.js

A simple TensorFlow.js implementation of MNIST

Track Active Users

An experiment in using a serverless cloud function

Cha Cha Slide

‘Now it’s time to get funky’

Bezier

Bezier curve tools

Ball Pit

Playground for your cursor

Gravity

An example of gravity

Colors

Color tools

Dice

A random number generator

NYT Connections Solver

Solving the NYT Connections using graph partitioning and word vectors

whoami

My interests currently center on cryptography, machine learning, and formal proof verification. Some of my recent projects include implementing a cryptographic voting protocol, developing methods for robust estimation in adversarial graph models, and creating a Abstract Algebra Lean game. Unrelated, I’m a big fan of board games, photography, and music. ░░

Cryptographic Voting with Multiple Candidates

Extension of the Helios Voting Protocol to support multiple candidates

Wallpaper Groups and Orbifolds

A brief introduction to wallpaper groups and classification using orbifolds

Unboxing the Black Box

Human-Inspired CNNs for Explainability and Efficiency

Interactive Proofs of Intro Euclidian Geometry

Some Euclidean constructions from Euclid’s Elements

Warping an Image into a Möbius Loop

A simple Python script to warp an image into a Möbius loop

Robust Estimation for the Erdős-Rényi Model

Final project for CSCI 2952Q: Robust Algorithms in Machine Learning

Visualizing Spectral Graph Theory

A Manim project explaining spectral graph theory

Desmos Mandelbrot Set

A couple ways to create the Mandelbrot set in Desmos

Across the Spider-Verse Style Transfer

Recreating the universes of Across the Spider-Verse by using Style Transfer

The NTRU Cryptographic System

Overview of the NTRU cryptographic system

Differential Equations and Eigenvalues

How to use spectral theory to visualize differential equations

Banger xkcd

A banger xkcd idea

Book List

Some nonfiction books that I’ve read

Möbius Transformations

See how Möbius transformations map the complex plane

Fourier Transform Visualization

3b1b’s Fourier Transform visualization in Desmos

Visualizing the Complex Plane

Explore how complex functions transform the plane using Desmos

Newton-Raphson Method

An interactive visualization of Newton’s method for finding roots of equations

Mapping Functions Visual

Visualizing how a function maps points on the number line and its fixed points

Umbral Calculus

How to use umbral calculus to find a closed form for a sequence

Lissajous Figures

Lissajous figures in Desmos

Change of Axis

What if you could bend the x axis?

(untitled)

Page Redirection If you are not redirected automatically, follow the link

(untitled)

MNIST Example Here is a simple TensorFlow.js example that loads the MNIST dataset, trains a model, and allows you to draw digits to see how well the model predicts them. Once the model is trained, you can draw a digit in the box below and it will predict what digit you drew. The model is trained on the MNIST dataset, which consists of 28x28 pixel grayscale images of handwritten digits (0-9).

(untitled)

MNIST Tensorflow.js Demo # You can try out the demo here: MNIST TensorFlow.js Demo This demo uses TensorFlow.js to load the MNIST dataset, train a model, and allow you to draw digits to see how well the model predicts them. Once the model is trained, you can draw a digit in the box below and it will predict what digit you drew. The model is trained on the MNIST dataset, which consists of 28x28…

(untitled)

google-site-verification: google21d0060bd8dc65b8.

·

.

Yo

yo