About This Course
Welcome to the online course for CogWorks. This course is designed to familiarize students with powerful methods of data analysis, including state-of-the-art machine learning techniques. Ultimately, these concepts and tools will allow us to customize our own cognitive assistants!
The online section for this course can be broken down into the following components:
- Machine Learning
- Module 1: Perspectives on Machine Learning
- Module 2: Your First Classifier
- Module 3: Gradient-Based Learning
- Module 4: Back-Propagation
It is beneficial for students to have previous experience programming. While a relatively comprehensive introduction to Python is presented here, this course is not designed to serve as an introduction to programming.
Students are expected to have strong skills in mathematics. They will need to work with functions of multiple variables and have a keen ability to think visually about functions and mappings. Experience in trigonometry and pre-calculus is necessary. It is not necessary for students to have taken calculus or linear algebra, but some of these concepts will be used. Past CogWorks students did not have calculus and linear algebra experience, and completed this course with great success; it did require them to put in some extra individual effort to understand these concepts.
Interest, enthusiasm, and an attention for detail are all a must!
Ryan Soklaski is a technical staff member of Lincoln Laboratory’s Artificial Intelligence Technologies group. There, he researches machine learning techniques that are performant under data-restricted circumstances, and works as a core developer for a lab-internal machine learning library. Prior to joining the laboratory, Ryan earned his PhD in theoretical condensed matter physics at Washington University in St. Louis. His doctoral thesis involved conducting physics simulations on high-performance computing clusters to study the physical mechanisms that drive the glass formation process in metallic liquids. Ryan’s background in education includes working as a lead-instructor for an undergraduate physics course at Washington University, and as a graduate-level teaching assistant. His interests include methods of numerical analysis, developing software in Python, and quantum mechanics.
David Mascharka is a research engineer at covariant.ai, where he focuses on perception-related tasks. His work is aimed at enabling robots to see, understand, and interact with the real world in complex ways. Prior to his role at covariant, David was a computer vision researcher in Lincoln Laboratory's Intelligence and Decision Technologies group. His academic interests include trust and interpretability in machine systems, acting under uncertainty, and the philosophical intersections of technology and everyday life.
Petar Griggs is an undergraduate student at Harvard University, studying math and physics. He is currently a Student Technical Assistant in Lincoln Laboratory’s Artificial Intelligence Technology group, developing models to design and predict materials and their physical properties. In his course work, Petar’s interests lie primarily in stochastic processes and differential geometry, and their applications in physics and statistics. A member of CogWorks’ inaugural 2017 cohort, Petar has been involved with BWSI and CogWorks ever since.