rohan-dot Goto Github PK
Type: User
Bio: Ranked in the top 600 on Analytics Vidhya
Blog: https://datahack.analyticsvidhya.com/user/profile/rohan7797
Type: User
Bio: Ranked in the top 600 on Analytics Vidhya
Blog: https://datahack.analyticsvidhya.com/user/profile/rohan7797
pmarcelino.com blog posts
Adversarial Machine Learning
Predicting pneumonia with chest xray scans
conv nets
Convergys_SPEAKER_REC
Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch
Using LSTM cells to generate a purposeful statement. Trained on around 100,000 words, much of the generated work does not make much sense. Purposeful statements can be generated by using a more
Python implementations of machine learning algorithms for motion artifact detection in electrodermal activity (EDA) data
Using transfer learning and Siamese network to try and develop a good and accurate face recognition system
Facebook AI Research Sequence-to-Sequence Toolkit written in Python.
MY first neural network implementation using keras. Predict bike sharing data. Model accuracy can be improved by using time series(Prophet)
Recommend friends to a user based on connections in graph
Using Feature engineering and collaborative filtering to develop a friend recommendation algorithm
This was by far the most interesting project I've worked on in the nano degree We generated fake faces by making neural networks duel against each other. Getting the generator loss down to <1 was my biggest hurdle. I tried training the generator twice and discriminator once and many other optimization techniques to get the loss to <1
Calculates + saves MFCCs for every .wav file in a directory
Who is your doppelgänger and more with Keras face recognition
Automatically transform all categorical, date-time, NLP variables to numeric in a single line of code for any data set any size.
Link prediction in social network - Friend TNS algorithm
:fire: A series of code examples for all sorts of machine learning tasks and applications.
Some of the hackathons i took part in over the summer
Starter kit for getting started in the Music Demixing Challenge.
Jupyter notebooks for the Natural Language Processing with Transformers book
Code used for evaluation and baselines in the PAN shared tasks.
A python wrapper for Speech Signal Processing Toolkit (SPTK).
Interning for convergys as an R&D intern My first job was to create a parser for a chatbot and then subsequently train it on my own training data and examples. I used rasa-nlu and core for this.
Basic News Recommender System
This repository contains a Matlab class and a Python module which implement the methods/functions for the different algorithms of the REpeating Pattern Extraction Technique (REPET) for lead and accompaniment separation, and Matlab GUIs for the original REPET and REPET-SIM.
A python package to analyze and compare voices with deep learning
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.