Rajesh Idumalla's Projects
100 Must-Read NLP Papers
Building a Bloom Filter on English dictionary words
In this Cat recognition project I am building the general architecture of a learning algorithm, including: Initializing parameters, Calculating the cost function and its gradient, Using an optimization algorithm (gradient descent), Gather all three functions above into a main model function, in the right order.
To giving names to these dinosaurs using character level language. Major tasks of this project are: How to store text data for processing using an RNN, How to synthesize data by sampling predictions at each time step and passing it to the next RNN-cell unit, How to build a character-level text generation recurrent neural network, Why clipping the gradients is important
This project about the fitting a classification tree to the housing data sing R package rapart.
Implementing a 2-class classification neural network with a single hidden layer. Using units with a non-linear activation function such as tanh. Computing the cross entropy loss. Implementing forward and backward propagation.
A simple movie recommendation system by collaborative filtering based on MovieLens dataset
Hello there! In this repository I will explain how to predict hand written digits using Spark Machine Learning decision tree classifier algorithm which will produce 88% accurate predictions at the depth of 15.
Word vector is a model of multi-dimensional vector representation of words. Similarity in the vector values often accompanies a semantic relation between words. But exploring the vector space further, we can find more interesting and surprising relations. I will shed some light on the mathematical meaning of the word vectors using an interactive visualization. Word2vec is a model of multi dimensional vector representation of words. Exploring the relations in vector space one can find that it surprisingly well preserves semantic analogies between words. In the talk I will use my interactive visualization with pre trained vectors from GloVe to illustrate the examples and relations
Building a machine learning program that can find most frequently buying products in a grocery store.
For this project, I am going to recommend positions where France's goal keeper should kick the ball so that the French team's players can then hit it with their head using deep learning regularisation and dropout methods.
This project about the GBM classification model on spam email data set and model optimisation.
An application to recognise the cat images with the Accuracy of 80 %. From this project, I've learn how to: Build the general architecture of a learning algorithm, including: Initializing parameters Calculating the cost function and its gradient Using an optimization algorithm (gradient descent) Gather all three functions above into a main model function, in the right order. Build and apply a deep neural network to supervised learning.
Implementing a model that uses an LSTM to generate jazz music and will even be able to listen to our own music at the end of this project.
K-means is a least-squares optimization problem, so is PCA. k-means tries to find the least-squares partition of the data. PCA finds the least-squares cluster membership vector.
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
Kernel Versions of various machine learning algorithms. The following algorithms are checked by applying the kernel trick: PCA • KMeans • LASVM • One class SVM • Passive aggressive online algorithm
Machine Learning Interviews from FAANG, Snapchat, LinkedIn. I have offers from Snapchat, Coupang, Stitchfix etc. Blog: mlengineer.io.
This repo is meant to serve as a guide for Machine Learning/AI technical interviews.
Collections of NLP Papers in my to-read list
Building node2vec algorithm
Building PageRank algorithm on Web Graph around Stanford.edu using NetworkX python library
My goal is to build an algorithm capable of recognizing a sign with high accuracy. To do so, I am going to build a tensorflow model with deep learning methods.
Best Practices on Recommendation Systems
Focuses on the application of Deep Q-Learning on different OpenAI environments like CartPole, MsPacman, etc.
Building Spam Email Classifier using NNET. Please read README.md for more info. Thanks
This project is about applying data analysis on Vietnam war data using Spark on google colab environment.