Singaravelan Neelakandan 's Projects
AIMET is a library that provides advanced quantization and compression techniques for trained neural network models.
180+ Algorithm & Data Structure Problems using C++
Assembly Language Adventures exercises for Yasm on Linux
š¤ Build your own (insert technology here)
My favorite C programming practices.
Folds batch normalisation and the following scale layer into a single scale layer for networks trained in Caffe. This can be done at inference time to reduce memory consumption.
A collection of as simple as possible, modern CMake projects
leetcode.com , algoexpert.io solutions in python and swift
Code for "Quantized Densely Connected U-Nets for Efficient Landmark Localization" (ECCV 2018) and "CU-Net: Coupled U-Nets" (BMVC 2018 oral)
Minimal Deep Q Learning (DQN & DDQN) implementations in Keras
Deformable Convolutional Networks
Low-precision matrix multiplication
Graph Transforms to Quantize and Retrain Deep Neural Nets in TensorFlow.
Ibex is a small 32 bit RISC-V CPU core, previously known as zero-riscy.
Leetcode Solution for Interview Preparation
Visualizer for neural network, deep learning and machine learning models
Configuration files using NVChad for NVim
A simple portfolio website using Bootstrap, CSS, JS and HTML
QKeras: a quantization deep learning library for Tensorflow Keras
RARS -- RISC-V Assembler and Runtime Simulator
Real-Time C++ Companion Code
RISC-V Integration for PYNQ
A Simple RISC-V Emulator in Rust
:books: Learn to write an embedded OS in Rust :crab:
SincNet is a neural architecture for efficiently processing raw audio samples.
My Github landing page