Fundamentals_Of_Machine_Learning

This repository contains many of my projects related to machine learning.

• Research Paper Go Through : In this Directory, I have stored different research papers summarised version, written by my self. It is available and beneficial to all those peoples, who wants to go through different research papers rapidly, in summarised way.

• Project: Makemore : In this project: makemore, It takes one text file as input, where each line is assumed to be one training thing, and generates more things like it. To create this project, I implemented various models i.e. Bigram Model, MLP Model, CNN Model, RNN Model, LSTM Model, GRU Model, Transformer Model, and evaluated their accuracy, Transformers are performing best for now. Libraries used are Pytorch, matplotlib.

• OpenCV with CUDA Projects : This Directory contains projects related to Computer Vision and use of OpenCV with Parallel Computing platform - CUDA.

• Project: Food Vision : This Directory contains concepts of CNN, Binary Classification Model Using CNN, Multiple Classification Model Using CNN with TensorFlow. Using CNN concepts and tensorflow, Built a Food Vision project: Computer vision model able to classify 101 different kinds of foods.

• Project: SkimLit : This Directory contains NLP fundamentals in Tensorflow, Built a SkimLit project: Create an NLP model to classify abstract sentences into the role they play (e.g. objective, methods, results, etc) to enable researchers to skim through the literature (hence SkimLit) and dive deeper when necessary. This directory also contains concepts related to binary and multi-class classification using RNNs (recurrent neural networks), LSTMs (long short-term memory cells), GRUs (gated recurrent units), CNNs.

• Image Classification Using Keras : In this, This model used Fashion MNIST dataset to do Multi-Classification.

• Determinants of Earnings : In this, I have used and get experienced with libraries pandas, numpy, seaborn, plotly, matplotlib, scikit-learn and build a simple linear regression and Multivariable Regression model to predict earnings according to the features - years of schooling and years of work experience.

---

Siddharth Mishra.