Data Science and Machine Learning

This course provides a complete grounding in the Data Science and Machine Learning domains, starting with a close analysis of the data lifecycle, key roles, and essential tools such as Python, Jupyter, and Git. Learners will lay the groundwork for the key mathematical concepts from a statistics and linear algebra foundation before getting started with the main features of the data workflow: retrieving data from a wide range of sources and learning crucial methodologies for cleaning, preprocessing, and feature building. The program then guides students through Exploratory Data Analysis and Visualization, enabling them to discern patterns and findings through univariate, bivariate, and multivariate examination, and create compelling visual representations using histograms, boxplots, and correlation matrices.

The program moves at a fast pace into the world of hands-on machine learning, beginning with supervised algorithms assigned for classification and regression, then branching off into specializations like Image Classification and Face Recognition using Convolutional Neural Networks (CNNs) and transfer learning techniques. Time Series Forecasting using a range of models, such as ARIMA, Facebook Prophet, and Long Short-Term Memory networks (LSTMs), is also tackled, with a real-world challenge being tackled using stock price prediction. The course ends with a final, comprehensive capstone project which demands that students combine their learning, picking and choosing the best models, through evaluation, on down to putting out a fully functional web application using Streamlit or Flask, thus ensuring a complete, portfolio-ready skill set is obtained.