rposhala Goto Github PK
Name: Rohith Kumar Poshala
Type: User
Bio: Machine Learning Engineer
Location: California
Blog: https://www.linkedin.com/in/rohith-kumar-poshala-396263195/
Name: Rohith Kumar Poshala
Type: User
Bio: Machine Learning Engineer
Location: California
Blog: https://www.linkedin.com/in/rohith-kumar-poshala-396263195/
Child mortality rates for all countries under UNICEF across the years are analysed and visualised using Python.
Deep learning approaches that include building a sequence to sequence MLP and also building an Autoencoder with the help of Dense, LSTM, Conv1D layers individually to reconstruct and detect the anomalies in the benchmark dataset.
Exploring few basic Machine Learning Algorithms
Mapper and Reducer algorithms were implemented for basic wordcount, N-grams, Inverted Index, Relational Join and KNN(K-Nearest Neighbours) using NumPy in Python.
This repository includes implementation of all kinds of SQL queries including recursive SQL on employees DB, Implementation of XQuery on a private books.xml data and a small project on designing and implementing database schema for TinyHub complying to given requirements along with creation of Entity-Relationship Diagram for the designed schema. Additionally, it also has the applications and tools to implement the added .sql or .xq files.
Exploring data visualisations.
Online Retails datasets are joined, analyzed with the help of Pandas (performing all SQL operations) and the resultant dataset was grouped by Stock Description ordered with respect to frequency.
Implementation of decision tree algorithm using NumPy and Bagging concepts of bootstrapping application code using python
This AWS deployed application which recognizes the handwritten digit written by user in front-end with the help of trained Deep learning model in the back-end.
Translation Toolbar with Autocorrect and Autofill features supporting English language used to translate English language to French Language
Examples exploring NumPy and Pandas
Convolutional Neural Networks were built, trained for image classification task for Fashion-MNIST dataset.
GDP prediction using Supervised models in R
Google CodeJam questions from each round are solved and saved
Convolutional Neural Networks were built, trained for image classification task on 20 classes of ImageNet dataset. Data Augmentation tools and CNN models were explored to achieve more than 51% accuracy on Validation data.
Implementation and visualisation of K-Means algorithm from scratch using NumPy
Keras documentation, hosted live at keras.io
Implementation of KNN algorithm using Python from scratch, which for huge datasets gets results faster than existing sk learn KNN.
Linear and Logistic regression algorithm has been implemented from scratch using Python. Polynomial functions of order 1,2,3,4,5 which are equivalent to linear regression were plotting against true cubic relation to demonstrate under fitting and over fitting of the models. For Logistic regression, classifier has been built using Batch gradient descent and Stochastic gradient descent to compare them in terms of accuracy
Matplotlib tutorial for beginner
Collection of iPython notebooks for UB CSE Machine Learning course (CSE 474/574)
Classifier has been built with the help probability theories and Discriminant Analysis using MATLAB
Feature Engineering techniques like Term-Document Matrix, Term Frequency-Inverse Document Frequency (TF- IDF) and Word2vec were tried to get features to implement movie genre prediction machine learned model (Random Forest) using Apache Spark.
Dimension reduction of a dataset using Principal Component Analysis to produce a low dimension dataset using Python
Examples and labs done using python
Random Forest algorithm has been implemented from scratch using NumPy
Knowledge-based, Content-based and Collaborative Recommender systems are built on MovieLens dataset with 100,000 movie ratings. These Recommender systems were built using Pandas operations and by fitting KNN, SVD & deep learning models which use NLP techniques and NN architecture to suggest movies for the users based on similar users and for queries specific to genre, user, movie, rating, popularity.
Task was to output a set of rectangles corresponding to the possible bar locations, given an image and number of bars.
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.