Course Description

Supervised and Unsupervised and Reinforcement. The Machine Learning curriculum begins with the fundamentals of neural networks and deep supervised learning using Python3's Numpy library. Starting with perceptrons and single-layered neural networks, students work their way up to build out the forward and back propagation of deep feed-forward, convolutional, and recurrent neural networks from scratch. Then, with their proficiency in the foundations of deep learning, students are introduced to the Tensorflow and Keras frameworks in which they are able to build increasingly complex deep architectures for computer vision and natural language processing applications. Students build upon their knowledge of deep learning by diving into the realm of unsupervised learning. In this subtopic, students discover how to draw inferences from datasets where the outcome is unknown. After being introduced to the concepts of dimensionality reduction and clustering, students are able to apply their knowledge to applications such as market analysis, recommender systems, biological research, and more. To complete the trifecta of machine learning, students dig into the theories behind deep reinforcement learning and how to use them for real life applications such as autonomous driving, and game agents. Since data is the backbone of all machine learning, our curriculum wouldn't be complete without the study of data collection and management. Students learn about SQL and NOSQL databases, how to scrape and label datasets while avoiding human bias, and how to manage large scale datasets with Pandas, Hadoop, and Google Cloud Platform. Our curriculum is continuously evolving to focus on current trends, ensuring that students learn what is relevant and are able to evolve with the growing industry. To facilitate students' ability to keep up with such a fast-paced industry, students are also asked to read multiple journal articles every week and implement these architectures, ensuring that they are able to continue their studies throughout their careers.