Projects
My background and knowledge of skills helped me build some intriguing projects. Here are some of the projects.
01
Movie Genre Prediction - NLP
Want to know what type of movie it is based on only the story or review for that movie?
02
Blown by Style - Fashion MNIST
What if you wished to purchase some similar apparel you saw on a random person but were not sure where to find it? I can help you.
03
People-Interests Classification System
KNN for classification of people based on their interests and further to recommend the likeness for those who missed on some aspects with collaborative filtering.
04
Good or Bad Movie - NLP
Naive' Bayes Classification on the labeled reviews for a movie.
05
Titanic - Machine Learning from Disaster
Predicting the survival output of the passengers that were traveling on the titanic ship based on various attributes that contribute to the survival chances.
06
Fake/Real News Detection
Designed Fake-Real new system where the dataset is titles, text, and status. Vectorize method is used to count the word frequency after the text is tokenized and processed through stopwords. When a new text is given the program will classify whether the news is fake or real.
07
CIFAR10 - Image Classification
Image classification using CNN model for the given CIFAR-10 dataset. Modifications in the CNN layers to see the effects of the changes on the accuracy of the model.
08
Overfitting with Higher order Linear Regression
To understand the concept of overfitting for various degrees using Gradient descent and applications of regularization to overcome overfitting in the model.
09
Accident Detection and Prevention
Accident detection program using CNN model. The dataset is images defining cars with accidents or not. It detects the results and sends the message and location of the accident to defined authorities when an accident is detected.
10
Classification on News Group
A Naïve Bayes Classifier model which predicts the class of the given document against the trained data which are documents containing the same groups.
