anandketan

apollo

An open autonomous driving platform

Efficient_LLM_Fine_Tuning

Fast_Fourier_Transforms

A fast Fourier transform (FFT) is an algorithm that computes the discrete Fourier transform of a sequence. Decomposing an N-point time domain signal into sequence of single points. The N-spectra are synthesized into a single frequency spectrum.

Gait_Modelling_Analysis

The emerging domain of tele-rehabilitation aims to eliminate bulky equipment traditionally used in the rehabilitation of those with motor impairment. Our proposed setup of a compact, simplified module for tele-rehabilitation involves a depth camera which detects the joint coordinates of the subject and generate gait cycle charts.

Graphing_Flight_Paths

The purpose of this project is to solve the shortest path problem, one of the fundamental theoretic problems known in graph theory, and how Dijkstra's algorithm can be used to solve it. Done as part of the final project for MOOC on Graph Theory by UCSD.

Pitch_Control

Pitch of an aircraft is controlled by the elevator which is situated at the rare of the airplane running parallel to the wing that houses the ailerons. Pitch control is a longitudinal problem, and this repository presents the design of an Arduino-based system as a solution.

Single_DoF_Copter_Control

This project presents the design, implementation, and analysis of a modified PID controller to stabilize the angular position of a 1-DOF copter system. The control algorithm was implemented on the ESP32 microcontroller. The controller performed well within the linear operating region of ±30°.

Sparse_CNN_SCALE_Sim

the-algorithm

Source code for Twitter's Recommendation Algorithm

VLM_Social_Navigation

This paper presents an advanced approach to social robot navigation using language-guided instructions to enhance the integration of robots into dynamic human environments. Leveraging the foundational NaviSTAR and the MuSoHu dataset, we utilized Visual-Language Models (VLMs) to interpret high-level textual commands and social cues.

anandketan/Gait_Modelling_Analysis

The emerging domain of tele-rehabilitation aims to eliminate bulky equipment traditionally used in the rehabilitation of those with motor impairment. Our proposed setup of a compact, simplified module for tele-rehabilitation involves a depth camera which detects the joint coordinates of the subject and generate gait cycle charts.

anandketan/the-algorithm

Source code for Twitter's Recommendation Algorithm

anandketan/apollo

An open autonomous driving platform

anandketan/ardupilot

ArduPlane, ArduCopter, ArduRover, ArduSub source

anandketan/CHIP_NeurIPS2021

Code for CHIP: CHannel Independence-based Pruning for Compact Neural Networks (NeruIPS 2021).

anandketan/Efficient_LLM_Fine_Tuning

anandketan/micrograd

A tiny scalar-valued autograd engine and a neural net library on top of it with PyTorch-like API

anandketan/Sparse_CNN_SCALE_Sim

anandketan/VLM_Social_Navigation

This paper presents an advanced approach to social robot navigation using language-guided instructions to enhance the integration of robots into dynamic human environments. Leveraging the foundational NaviSTAR and the MuSoHu dataset, we utilized Visual-Language Models (VLMs) to interpret high-level textual commands and social cues.

anandketan/DALL-E

PyTorch package for the discrete VAE used for DALL·E.

anandketan/DALLE2-pytorch

Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch

anandketan/datasets

🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools

anandketan/dm_control

DeepMind's software stack for physics-based simulation and Reinforcement Learning environments, using MuJoCo.

anandketan/gym

A toolkit for developing and comparing reinforcement learning algorithms.

anandketan/habitat-sim

A flexible, high-performance 3D simulator for Embodied AI research.

anandketan/lazypredict

Lazy Predict help build a lot of basic models without much code and helps understand which models works better without any parameter tuning

anandketan/MineDojo

Building Open-Ended Embodied Agents with Internet-Scale Knowledge

anandketan/mujoco

Multi-Joint dynamics with Contact. A general purpose physics simulator.

anandketan/mujoco-py

MuJoCo is a physics engine for detailed, efficient rigid body simulations with contacts. mujoco-py allows using MuJoCo from Python 3.

anandketan/nn-zero-to-hero

Neural Networks: Zero to Hero

anandketan/nuttx

Apache NuttX is a mature, real-time embedded operating system (RTOS)

anandketan/openmm

OpenMM is a toolkit for molecular simulation using high performance GPU code.

anandketan/openpilot

openpilot is an open source driver assistance system. openpilot performs the functions of Automated Lane Centering and Adaptive Cruise Control for over 200 supported car makes and models.

anandketan/openpose

OpenPose: Real-time multi-person keypoint detection library for body, face, hands, and foot estimation

anandketan/sawIntuitiveResearchKit

cisst/SAW stack for the da Vinci Research Kit (dVRK)

anandketan/spinningup

An educational resource to help anyone learn deep reinforcement learning.

anandketan/starlark

Starlark Language

anandketan/tinygrad

You like pytorch? You like micrograd? You love tinygrad! ❤️

anandketan/transformers

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

anandketan/webull

Unofficial APIs for Webull.