sshivang Goto Github PK

besafe

Apple native application for displaying local crime data

blackjackgame

This is a black jack game I developed to learn the java swing library as well as learn about the java UI.

bulk-historical-stock-data-retriever

This program is designed to use Python's PANDAS data analytics libraries to generate a csv file for the specified range of years given by the user. This was designed to make thousands of pairwise comparisons to analysze the correlation between stock price and the percent increase the stock saw. The report is attached bellow.

classical-piano-composer

crashmonkey

CrashMonkey: tools for testing file-system reliability (OSDI 18)

crystalreport

This is an implementation of reporting tools in the .NET based web application which I developed during my internship at FacetoFace technologies.

cs378nlp-sp20-fp

Final project starter code for CS378 NLP, Spring 2020

cyberpatriot_windows_bash

Cyberpatriot is a competition in which teams compete to make the system more secure. This bash was used in cyber patriot 2016-2017 season

datahack2019

Python program to take bcycle data and describe the flow of people throughout the day

datahackstartercode

Code for Datahack

embryoalignmenttool

This is my personal research project that I did during the course of the year. This project revolves around the alignment of embryo stages among 4 species of animal.

fractals

Currently Mandelbulb fractal

google_app_scripts

Google App Script for automating the procedure of keeping track of NHS hours. Sends emails after checking.

housingindextrading

in-time-over-parameterization

[ICML 2021] "Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training" by Shiwei Liu, Lu Yin, Decebal Constantin Mocanu, Mykola Pechenizkiy

musictimeperiodclassification

This project explores the use of sequence modeling to do time period classification for classical music. We explore the use of a long short-term memory (LSTM) network to model music. We do this in two steps. (1) In the first step, we design an upstream task that takes in input sequences of music notes. (2) Secondly, we use this model to classify music sequences into musical time periods. We derive this set of mappings through finding lists of time periods and the respective pieces that correspond to the period. We show that by first training a language model on a set of unlabeled data and then fine tuning on a smaller set of labeled data, we are able to improve performance. Through this modeling, we hope to learn what factors and features are the most useful in delineating between time periods. Furthermore, we would like to explore the model that we build through probing to learn more about musical time periods.

places365

The Places365-CNNs for Scene Classification

python-course

Tutorial and introduction into programming with Python for the humanities and social sciences

pytorch-transformers

👾 A library of state-of-the-art pretrained models for Natural Language Processing (NLP)

pytorch-yolov3

Minimal PyTorch implementation of YOLOv3

speechmodeltutorial

speechrecognitionneuralmodel

This project is designed to model and predict the response of the human brain (activation of particular voxels) given a particular stimuli (sequences of words).

sshivang.github.io

The source code for my website: www.shivangsingh.com

textclassifier

urbanheatislandappengine

This urban heat island program included an android as well as a web application component which kept track of urban heatislands

voiceassistant

webspider