Artificial Intelligence and Machine Learning Projects

1. Applied Statistics

This project used Hypothesis Testing and Visualization to leverage customer's health information like smoking habits, bmi, age, and gender for checking statistical evidence to make valuable decisions of insurance business like charges for health insurance.

Skills and Tools :

Hypothesis Testing, Data Visualisation, Statistical Inferences

Project Link : https://nbviewer.jupyter.org/github/sahil-pattnayak/Great-Learning-AIML-Projects/blob/master/Applied%20Statistics/Applied%20Statistics%20Project.ipynb

2. Supervised Learning

This Project involved using classification algorithms to predict the income level of the customers based on attributes like 'sex', 'marital-status', 'age', 'occupation' etc. The classification algorithms that were used are:

• Naive Bayes
• Logistic Regression
• K-Nearest Neighbor (kNN)
• Support Vector Classifier
  And finally, a comparison of accuracy across these models was done to finalize the model for prediction.

Skills and Tools :

EDA and Classification Algorithms

Project Link : https://nbviewer.jupyter.org/github/sahil-pattnayak/Great-Learning-AIML-Projects/blob/master/Supervised%20Learning/Supervised%20Learning%20%28Classification%29%20Project.ipynb

3. Ensemble Techniques

This project invovled using different classification alogorithms to predict whether a customer will subscribe to term deposit or not based on leveraged customer information of bank marketing campaigns. Ensemble techniques like boosting and bagging were used to further improve the classification results. The classification algorithms that were used are:

• Gaussian Naive Bayes
• Logistic Regression
• Decision Tree
• K-Nearest Neighbour (kNN)
• Support Vector Classifier
• Random Forest Classifier
• Bagging Classifier
• AdaBoost Classifier
• Gradient Boosting Classifier
• XGBoost Classifier
• Bagging Classifier
  And finally, a comparison of accuracy across these models was done to finalize the model for prediction.

Skills and Tools :

Classification, Decision Trees, Ensemble Techniques

Project Link : https://nbviewer.jupyter.org/github/sahil-pattnayak/Great-Learning-AIML-Projects/blob/master/Ensemble%20Techniques/Ensemble%20Techniques%20Project.ipynb

4. Unsupervised Learning

This project invovled using classification of vehicles into different types based on silhouttes which may be viewed from many angles. Used PCA in order to reduce dimensionality and SVC for classification and GridSearch was used to find the optimal hyper-parameters for the model. Further, the metrics of models were compared based on 4 different attributes:

• Support Vector Classifier with PCA
• Support Vector Classifier with PCA using GridSearch
• Support Vector Classifier without PCA
• Support Vector Classifier without PCA using GridSearch

Skills and Tools :

Support Vector Classifier, Principal Component Analysis

Project Link : https://nbviewer.jupyter.org/github/sahil-pattnayak/Great-Learning-AIML-Projects/blob/master/Unsupervised%20Learning/Unsupervised%20Learning%20Project%20PCA.ipynb

5. Featurization, Model Selection & Tuning

This project involved feature exploration and selection to predict the strength of high-performance concrete. Used Regression models to find out the most important features and predict the strength. Cross-validation techniques and Grid search were used to tune the parameters for best model performance. The regression algorithms that were used are:

• Linear Regressor
• Ridge Regressor
• Lasso Regressor
• Polynomial (2) Regressor
• Polynomial (3) Regressor
• Decision Tree Regressor
• Random Forest Regressor
• AdaBoost Regressor
• Gradient Boosting Regressor
• XGBoost Regressor

Skills and Tools :

Regression, Decision trees, feature engineering

Project Link : https://nbviewer.jupyter.org/github/sahil-pattnayak/Great-Learning-AIML-Projects/blob/master/Featurization%2C%20Model%20Selection%20%26%20Tuning/Project.ipynb

6. Introduction to Neural Network and Deep Learning

The objective of the project is to learn how to implement a simple image classification pipeline based on the k-Nearest Neighbour and a deep neural network.
SVHN is a real-world image dataset for developing object recognition algorithms with a requirement on data formatting but comes from a significantly harder, unsolved, real-world problem (recognizing digits and numbers in natural scene images). SVHN is obtained from house numbers in Google Street View images.

Skills and Tools :

Neural Networks, Deep Learning, Keras, Image Recognition

Project Link : https://nbviewer.jupyter.org/github/sahil-pattnayak/Great-Learning-AIML-Projects/blob/master/Introduction%20to%20Neural%20Network%20and%20Deep%20Learning/Neural%20Network%20Project.ipynb

7. Computer Vision - Face Detection

In this hands-on project, the goal is to build a face recognition system, which includes building a face detector to locate the position of a face in an image and a face identification model to recognize whose face it is by matching it to the existing database of faces. Recognize, identify and classify faces within images using CNN and image recognition algorithms.

Skills and Tools :

Computer Vision, CNN, Transfer Learning, Object detection

Project Link : https://nbviewer.jupyter.org/github/sahil-pattnayak/Great-Learning-AIML-Projects/blob/master/Computer%20Vision/Face-Detection%20Project.ipynb

8. Computer Vision - Face Recognition

The objective of this project is to build a face recognition system, which includes building a face detector to locate the position of a face in an image and a face identification model to recognize whose face it is by matching it to the existing database of faces.
Face recognition deals with Computer Vision a discipline of Artificial Intelligence and uses techniques of image processing and deep learning.

Skills and Tools :

Computer Vision, Keras, CNN, Siamese Networks, Triplet loss

Project Link : https://nbviewer.jupyter.org/github/sahil-pattnayak/Great-Learning-AIML-Projects/blob/master/Computer%20Vision/Face_Recognition_Project_AWS.ipynb

9. Natural Language Processing - Sarcasm Detection

The goal of this hands-on project is to analyse the headlines of the articles from news sources and detect whether they are sarcastic or not.

Skills and Tools :

LSTM, Classification, GloVe

Project Link : https://nbviewer.jupyter.org/github/sahil-pattnayak/Great-Learning-AIML-Projects/blob/master/Natural%20Language%20Processing/NLP_Project_Sarcasm_Detection.ipynb