Kartik Chincholikar's Projects
Artificial Intelligence for Science (AIRS)
An attempt to collect and use data to find a player's "Patterns of Play". These can be exploited in a match.
Broadcasted Residual Learning for Efficient Keyword Spotting
A book about category theory
Equivariant Steerable CNNs Library for Pytorch https://quva-lab.github.io/escnn/
A collection of resources to help beginners get started with geometric deep learning
Training a hill climber to go up any 2d terrain ( finds local peaks ). "Neural Network" of the hill climber classifies between "go left" and "go right" by looking at its surrounding terrain.
š Introduction to Algorithms
Portfolio Website of Kartik Chincholikar, who also goes by the "Kartik C", "Badminton School" and is currently learning Search Engine Optimization :p
Portfolio showcasing works and skills
A parallax mouse move effect featuring the character of The Bride from the film Kill Bill. The effect uses the Parallax.js engine.
PCA is done to reduce the dimensionality of the data. In this notebook, we do PCA using just numpy.
A Google Colab notebook ( where we load a pretrained model ) which connects to the frontend ( Anvil )
Running toy simulations to understand the Statistical Learning Theory framework.
Colab Notebook to understand how neural networks transform the data nonlinearly. I train a very simply neural network using numpy to classify a toy dataset (XOR) - Kartik Chincholikar