Over the three weeks of the Brains, Minds, and Machines summer course, students engage in open-ended projects that provide an opportunity to explore course topics more deeply and apply new computational or empirical methods learned in the tutorials. This project experience is often cited by students as a highlight of the summer course.
While most students pursue individual projects, some work in small teams of 2 or 3 students, and all work closely with a faculty or TA advisor. Some projects explore computational models, either extensions to existing models or the design of new models, including the analysis of results from computer simulations. Other projects incorporate the analysis of data from behavioral, physiological, or fMRI experiments, considering new analysis methods or relating empirical results to model predictions. Some students design projects around their current research, although they are strongly encouraged to explore new problems and methods.
The project work culminates in an oral presentation to the Brains, Minds and Machines summer course community.
To facilitate the design of projects for the 2015 summer course, faculty instructors and teaching assistants generated initial broad project ideas in each of five topic areas:
Development of intelligence
Neural circuits for intelligence
Visual intelligence
Social intelligence
Theories of intelligence
The 2015 Project Ideas Document (PDF) has brief summaries of project topics, with pointers to useful literature and other resources.
Student Project Video - iCub Robot Plays the Piano
Description: Diego Mendoza-Halliday programs the humanoid iCub robot to transform the sound of musical notes into motor commands to the iCub’s agile fingers, enabling it to play the “Happy Birthday” song on a mock piano keyboard.
Student Project Video - Capturing Neural Plasticity in Deep Networks
Description: Neural networks in the brain continually adapt their form and function to changing circumstances. Nick Cheney explores how this neuroplasticity can be modeled in deep learning networks, yielding stable learning behavior in dynamically changing networks.
Student Project Video - Impact of Attention on Cortical Models of Visual Recognition
Description: Danny Jeck explores how modulations in neural behavior in the early stages of visual processing, due to shifts in the focus of visual attention, impact the performance of later cortical areas engaged in object recognition.
Student Project Video - Learning to Recognize Digits and Faces from Few Examples
Description: Alon Baram and Laurie Bayet build upon a model of visual recognition that learns to identify digits and faces from novel viewpoints, using limited training examples of the sort that an infant may experience as it learns to recognize new faces.
Student Project Video - Modeling Dynamic Memory with Hopfield Networks
Description: David Rolnick and Ishita Dasgupta explore how Hopfield networks, commonly used to model static memories, can be extended to represent dynamically shifting memory states that capture stochastic sequences of events.
