Artificial and natural computations for sensory perception: what is the link?
6-13 June 2020 - Bertinoro, Italy
Recent advances in machine learning have yielded deep neural network models with impressive performance in artificial perception, based in part on principles established by experimental studies of sensory neuroscience. This is an exciting time for research in this field, as such models provide quantitative theories for the key computations that give rise to perception in biological sensory systems. However, unlike brains, current deep neural network models are often brittle and do not generalize well to new situations. At the same time, many structural and functional aspects of real sensory systems appear to be incompatible with the very simple design of neural networks used in artificial intelligence (AI).
Picture © DeepArt.io
In this school, we will discuss analogies and discrepancies between sensory system computations and artificial intelligence models and how the two fields can interact more to advance each other. A set of international lectures will provide an overview of modern algorithms in artificial intelligence and recent breakthroughs in the neural mechanisms of sensory perception. The students will also learn how to practically implement AI tools, such as deep neural networks, and we will also discuss the ethical context of neuro-inspired computational technologies.
Registration and stipends
- Fee: FENS Members: TBC EUR
FENS Non-members: TBC EUR
- Registration fee covers tuition, accommodation and meals.
- FENS offers 4 stipends (covering the registration fee) available for candidates from disadvantaged countries. Any applicant in need of a grant should however first try to request it from the lab, institution or government if possible. You can apply for a stipend inside the application form.
- Please note that if you already benefited from a FENS grant in 2020, you are not eligible to receive a stipend.
- Applications will open in December 2019.
Bertinoro, Training Center of the University of Bologna, Italy
For enquiries, please contact: email@example.com