BTT004 - Machine Learning Foundations

Course Description

Machine learning (ML) is increasingly a part of people's daily lives. Think about some of the technologies you use every day, such as the suggestions that appear on YouTube and Netflix and emails being diverted to the spam folder. All are practical applications of ML, a branch of artificial intelligence (AI) that allows computer programs to automatically improve through experience. Looking ahead, some of the world's most complex problems — such as future pandemics — could depend on ML as a solution. 

With a curriculum taught by Cornell Tech's Visiting Lecturer Brian D'Alessandro and developed in concert with industry leaders, this "Machine Learning Foundations" summer course will offer you the skills that will enable you to build ML solutions in real-world conditions through an ethical and inclusive lens. In this skills-based program, you will work with industry-relevant tools to analyze real-world data sets to identify patterns and relationships in data. By the end of this 9-week course, you will have hands-on experience solving real-world problems through building machine learning workflows and optimizing ML models from scratch.

Weekly synchronous lab sessions will give you the opportunity to explore these skills in a collaborative environment and gain hands-on experience in ML and data science. Ultimately, the foundational skills you will acquire in this "Machine Learning Foundations" curriculum will prepare you to take on real-world industry challenges in Studio this fall. 

During this part of the Break Through Machine Learning Program, you can expect to spend about eight to ten hours per week on asynchronous online content and about three hours per week on synchronous lab sessions with other students.

This course includes:

• Sixteen weekly assignments
• Nine live labs
• Nine lab assignments

Benefits to the Learner

• Understand the machine learning lifecycle and explore common machine learning packages
• Perform exploratory analysis to understand your data and prepare your data for machine learning applications
• Train and optimize two popular supervised learning algorithms: k-nearest neighbors (KNN) and decision trees (DT)
• Understand the mechanics of linear models and implement a common linear model from scratch
• Define the model evaluation metrics for specific applications by selecting the appropriate model candidates and hyperparameters for testing
• Understand the principle of ensemble models and how to train and tune a model using models as features
• Perform NLP sentiment analysis and implement deep learning models
• Identify performance issues and find solutions to fix and improve them

Applies Towards the Following Certificates

• Machine Learning Foundations V4 : Core Course