Project 5: End-to-End development of Machine Learning Heart Failure Prediction model

Full Implementation and Web Application Link WebApp deployed using Heroku Source code on GitHub Jupyter Notebook Steps Involved Data Collection Data Cleaning Exploratory data analysis Model Building Hyperparameter Tuning Best model selection Model deployed on production environment

June 5, 2021

Project 4: Proof statistically that unsupervised representation learning enhance classifier performance

Full Implementation and details Project on GitHub Problem Statement Design and train a network that combines supervised and unsupervised architecture in one model to achieve a classification task Dataset Strictly Imbalance CIFAR-10 dataset Architecture Convolutional Neural Network based AutoEncoder Encoder architecture as classifer with additional dense layer to classify images Handling Imbalance dataset Proper distribution of weights for each class Data augmentation emphasize on minority classes AutoEncoder Training Results Reconstruction of images with Mean-Squared-Error loss Classifier Training Scenarios Experiment Results Accuracy on CIFAR-10 test dataset on 10,000 images Training Methodology Xavier Init Pretrained Autoencoder Init Avg Improvement Data Augmentation SGD 0.

June 1, 2021

Project 3: IMDb Movies Case Study

We have the data for the 100 top-rated movies from the past decade along with various pieces of information about the movie, its actors, and the voters who have rated these movies online. we will try to find some interesting insights into these movies and their voters, using Python. Full details and Implementation Jupyter Notebook Some of the interesting insights Average ratings by Males and Females varying across the genres Inferences: Sci-Fi appears to be the highest rated genre in the age group of U18 for both males and females.