Project: Propose, build, and deploy your own data science (machine learning) code on an engineering/science data set
The classroom instruction in this course is aimed at preparing first-year engineering students to use modern data science tools (e.g., python scikit-learn, matplotlib, and pandas). This class will provide tools that are useful for all engineering disciplines (e.g., chemical engineering, mechanical engineering, materials science); not just computer science/computer engineering. The skill set learned in this class is expected to prove useful for future engineering courses and also for engineering careers in industry, government, and academia. Course content will expand the students’ horizons of the utility of data science in real-world contexts and help them reflect on their own understanding of the course material.
The goal is to learn modern data science skills to help address the big challenges facing society (e.g., energy, environment, medicine). This course will familiarize students with the principles of modern data science techniques in the context of engineering. Topics and applications covered include data collection, curation, and supervised and unsupervised machine learning. Algorithms covered will include the perceptron, principal component analysis, feed forward neural networks, and random forests, among others. Homework and lab exercises include hands-on practice of using data science to solve science and engineering problems. Students will be responsible for a data science project on a topic of interest (the instructor will also suggest project topics for consideration).
• Gain exposure to applied engineering fields where data science and machine learning (ML) are playing an important role
• Learn data science skills for use in your future career as an engineer
• Draw connections between theory, modeling, and applications in data science & ML
• Provide opportunities for open-ended project work
• Practice and receive feedback on writing and oral communication