ShreJais

2020

Materials for Applied Data Analysis CS-401, fall 2020

500-AI-Machine-learning-Deep-learning-Computer-vision-NLP-Projects-with-code

500 AI Machine learning Deep learning Computer vision NLP Projects with code

Acoustic-direction-finding-using-single-acoustic-vector-sensor-under-high-reverberation

We propose a novel and robust method for acoustic direction finding, which is solely based on acoustic pressure and pressure gradient measurements from single Acoustic Vector Sensor (AVS). We do not make any stochastic and sparseness assumptions regarding the signal source and the environmental characteristics. Hence, our method can be applied to a wide range of wideband acoustic signals including the speech and noise-like signals in various environments. Our method identifies the “clean” time frequency bins that are not distorted by multipath signals and noise, and estimates the 2D-DOA angles at only those identified bins. Moreover, the identification of the clean bins and the corresponding DOA estimation are performed jointly in one framework in a computationally highly efficient manner. We mathematically and experimentally show that the false detection rate of the proposed method is zero, i.e., none of the time-frequency bins with multiple sources are wrongly labeled as single-source, when the source directions do not coincide. Therefore, our method is significantly more reliable and robust compared to the competing state-of-the-art methods that perform the time-frequency bin selection and the DOA estimation separately. The proposed method, for performed simulations, estimates the source direction with high accuracy (less than 1 degree error) even under significantly high reverberation conditions.

ai-school

Various projects and examples for Artificial Intelligence. From Probabilistic Programming to Neural Networks.

all-of-statistics

Self-study on Larry Wasserman's "All of Statistics"

AML-XAI-2

Exploring the creation of explainable AI for the task of Writer verification. Experimenting with techniques such as Probabilistic Graphical Models, Autoencoders, Siamese Networks, and Multi-Task Learning. Probabilistic Graphical modelling involves entropy learning and Sigmoid Structured CPD inference mechanism.

apkit

Audio Processing Kit -- a python library

Applied-Deep-Learning

Applied Deep Learning

applied-ml

📚 Papers & tech blogs by companies sharing their work on data science & machine learning in production.

Grid-less-DOA

Sequential DOA Trajectory Estimation using Deep Complex Network and Residual Signals

ShreJais/Grid-less-DOA

Sequential DOA Trajectory Estimation using Deep Complex Network and Residual Signals

ShreJais/Awesome-Diffusion-Models

A collection of resources and papers on Diffusion Models and Score-based Models, a darkhorse in the field of Generative Models

ShreJais/CenterNet2

Two-stage CenterNet

ShreJais/CLUB

Code for ICML2020 paper - CLUB: A Contrastive Log-ratio Upper Bound of Mutual Information

ShreJais/ConvNeXt

Code release for ConvNeXt model

ShreJais/ddsp

DDSP: Differentiable Digital Signal Processing

ShreJais/Deep-Learning-for-Tracking-and-Detection

Collection of papers, datasets, code and other resources for object tracking and detection using deep learning

ShreJais/deeplearning-models

A collection of various deep learning architectures, models, and tips

ShreJais/DL_Specialization_Coursera

ShreJais/flowpm

Particle Mesh simulation in TensorFlow

ShreJais/Gaussian-Processes-Regression-Tutorial

An Intuitive Tutorial to Gaussian Processes Regression

ShreJais/git_intro

Trying out git and learning how to use it.

ShreJais/GP-VAE

TensorFlow implementation for the GP-VAE model described in https://arxiv.org/abs/1907.04155

ShreJais/icoCNN

Pytorch implementation of the icosahedral CNNs

ShreJais/icoDOA

Code repository for the paper Direction of Arrival Estimation of Sound Sources Using Icosahedral CNNs

ShreJais/KDEpy

Kernel Density Estimation in Python

ShreJais/machine-learning-book

Code Repository for Machine Learning with PyTorch and Scikit-Learn

ShreJais/make-a-pr

Learning git and github.

ShreJais/ml-cvnets

CVNets: A library for training computer vision networks

ShreJais/neural-processes

Pytorch implementation of Neural Processes for functions and images :fireworks:

ShreJais/normalizing-flows

Implementation of normalizing flows in TensorFlow 2 including a small tutorial.

ShreJais/probnum

Probabilistic Numerics in Python.

ShreJais/probtorch

Probabilistic Torch is library for deep generative models that extends PyTorch

ShreJais/project-NN-Pytorch-scripts

ShreJais/pytracking

Visual tracking library based on PyTorch.

ShreJais/Quantus

Quantus is an eXplainable AI toolkit for responsible evaluation of neural network explanations

ShreJais/ShreJais

Config files for my GitHub profile.

ShreJais/shrejais.github.io

Github Pages template for academic personal websites, forked from mmistakes/minimal-mistakes

ShreJais/ssm-jax-refactor

Bayesian learning and inference for state space models (SSMs) using Google Research's JAX as a backend

ShreJais/TextEncodersForSELD

Leveraging Text Encoders for SELD