School on Analytical Connectionism

Analytical Connectionism is a 2-week summer course on analytical tools, including methods from statistical physics and probability theory, for probing neural network models of higher-level cognition. The course brings together neuroscience, psychology and machine-learning communities, and introduces attendees to analytical methods for neural network analysis and connectionist theories of higher-level cognition and psychology.

Connectionism, a theoretical approach in cognitive science, uses neural network models to simulate a wide range of phenomena, including perception, memory, decision-making, language, and cognitive control. However, most connectionist models remain, to a certain extent, black boxes, and we lack a mathematical understanding of their behaviours. Recent progress in machine learning theory has provided novel analytical tools that have advanced our mathematical understanding of deep neural networks, and have the potential to help make these “black boxes” more transparent.

This course will introduce:

• mathematical methods for neural network analysis, providing a solid overview of the analytical tools available to understand neural network models;
• key connectionist models with links to experimental observations, which provide targets for analytical results.

During the course, you will:

• attend lectures given by leading researchers on theoretical methods and applications, key connectionist models, and experimental observations;
• participate in tutorials, Q&A sessions, and panel discussions;
• take part in networking activities such as poster sessions;
• work in groups on a novel research project, mentored by the course organisers and lecturers.

The 2024 edition of the Analytical Connectionism summer school will focus on using analytical models to study connectionism and its application to cognition. Topics will include developmental psychology, particularly how cognitive functions evolve, and memory, both from neurobiological and cognitive neuroscience perspectives. The course will also explore large language models (LLMs) and their relation to language processing, alongside discussions in computational neuroscience on sensory processing and decision-making. Together, these areas will provide a thorough understanding of cognition through analytical and computational approaches.

Target audience

This course is appropriate for graduate students, postdoctoral fellows and early-career faculty in a number of fields, including psychology, neuroscience, physics, computer science, and mathematics. Attendees are expected to have a strong background in one of these disciplines and to have made some effort to introduce themselves to a complementary discipline.

The course is limited to just under 40 attendees, who will be chosen to balance the representation of different fields. In circumstances where all other things are equal, priority will be given to applicants from populations underrepresented in the scientific workforce as defined by NIH, including but not limited to racially underrepresented individuals, women, individuals with disabilities, and individuals from disadvantaged backgrounds.

Course fees

There are no course fees, but attendees are expected to cover their own travel, visa expenses, and any meals not offered by the summer school. (Morning and afternoon coffee breaks and lunch will be provided Monday to Friday.) Accommodation in NYC for students not living in NYC and the surrounding areas will be provided by the school.

Travel grants inclusive of the above named personal expenses will be offered to individuals whose participation furthers the goal to promote diversity in systems and computational neuroscience, in particular among populations underrepresented in the scientific workforce as defined by NIH.