BTT002 - Machine Learning Foundations

Course Description

Working with data can be messy, complex, and difficult to navigate, yet it is these foundational skills that will propel you into a career in artificial intelligence. In this 10-week skills-based training, you will work with tools like Jupyter Notebooks, NumPy, and Pandas. Using these industry-relevant tools, you will have the opportunity to analyze real-world data sets to identify patterns and relationships in data. You will gain experience creating expressive and computationally robust data science projects.

Once you master some data science basics, you will use several common machine learning tools, such as scikit-learn, to build ML models, and discover how to analyze the pros and cons of these different ML models. Ultimately, this curriculum will prepare you to approach real-world business problems, work with live data sets, and choose ML models best suited to uncovering new relationships and patterns in the data. This will provide you with the skills to unlock value in unstructured data sets and aid you in making recommendations about what models to use as well as what questions to ask to make sure they’re implemented in the most effective way, including how to train a more powerful model using advanced evaluation and hyperparameter tuning methods.

During this portion of the program, you can expect to spend about 15 hours a week on the online coursework and about 3 hours per week in the live Lab session.

Faculty Author

Benefits to the Learner

• Build an intuitive approach to understanding AI while practicing the basics of Python and development tools
• Practice the foundations of data science while exploring the common tools used in the field
• Analyze and visualize data to perform basic statistical analysis on data sets and visualize data using common Python packages like Matplotlib and seaborn
• Import, clean, filter, and analyze data sets to prepare for machine learning
• Define and compare machine learning models in order to make decisions on how to approach a machine learning problem
• Improve the accuracy of machine learning models using advanced evaluation and hyperparameter tuning methods
• Define and compare supervised and unsupervised machine learning methods
• Investigate how deep learning and neural networks can be used in machine learning

Applies Towards the Following Certificates

• Machine Learning Foundations : Core Course