Various projects Related to Machine Learning Masters Course.
-
Logistic Regression for Two Class Classification Problem in Python
-
The project is to implement neural network and convolutional neural network for the task of classification. The classification task will be that of recognizing an image and identify it as one of ten classes. You are required to train the classifiers using Fashion-MNIST clothing images. Following are the three tasks performed: a. Build a Neural Network with one hidden layer to be trained and tested on Fashion-MNIST dataset. Code from scratch in Python. b. Build multi-layer Neural Network with open-source neural-network library, Keras on FashionMNIST dataset. c. Build Convolutional Neural Network (CNN) with open-source neural-network library, Keras on Fashion-MNIST dataset.
-
The project will be that of clustering images and identify it as one of many clusters. We traned the unsupervised model using Fashion-MNIST clothing images. Following are the three tasks performed:
a. Use KMeans algorithm to cluster original data space of Fashion-MNIST dataset using Sklearns library. b. Build an Auto-Encoder based K-Means clustering model to cluster the condensed representation of the unlabeled fashion MNIST dataset using Keras and Sklearns library. c. Build an Auto-Encoder based Gaussian Mixture Model clustering model to cluster the condensed representation of the unlabeled fashion MNIST dataset using Keras and Sklearns library. -
The task is to build a Reinforcement Learning agent to navigate the classic 4x4 grid-world environment. The agent will learn an optimal policy through Q-Learning which will allow it to take actions to reach a goal while avoiding obstacles.