Containes code and implementation of various machine learning concepts and Algorithms
Key Toipcs:
Supervised Machine Learning - Linear Regression models, Classification, Gradient Descent, Logistic Regression, Methods for improving model’s training and performance - Vectorization, Feature Scaling, Feature Engineering ,Polynomial Regression, Regularization to address overfitting.
Advanced Learning Algorithms - Neural networks, Decision Trees ( Random forests, XGBoost), training a neural network using TensorFlow, Multi class Classification, Error Analysis, Data Augmentation, Data Synthesis, Transfer Learning, Performance tuning of learning algorithms.
Unsupervised Learning Algorithms - Clustering, Anomaly Detection
Recommender Systems - Implementing Collaborative filtering recommender systems, Deep learning content based filtering using a neural networks.
Reinforcement Learning - Building a deep Q-learning neural network.