University of Cambridge > Talks.cam > Computational Neuroscience > Approximate nonlinear filtering with a neural network

  Browse A-Z

Log in

Cambridge users (raven)details Other usersdetails No account?details

Information on

Subscribing to talksdetails Finding a talkdetails Adding a talkdetails Disseminating talksdetails Help and Documentationdetails

Approximate nonlinear filtering with a neural network

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact Guillaume Hennequin.

One of the most impressive property of the brain is its ability to continuously extract relevant features from the environment. For example, when surrounded by a noisy crowd, humans can extract the voice of a single person or track its position over time. However, it still remains unknown how this feature extraction takes place in the brain. We formulate this problem in a very general framework where the task is to continuously infer hidden variables given past observations for a an arbitrary nonlinear generative model. Even though, the formal solution to this general problem has been given by the Kushner equation in the form of a stochastic partial differential equation for the posterior distribution, its practical applicability remains difficult due to the closure problem (every moment depends on higher order moments). Here, we propose an approximate yet tractable solution in the form of a sampling based filter. Interestingly, this sampling based filter is biologically plausible and could be implemented by a recurrent network of analog neurons. Furthermore, we derive a learning rule for the parameters of the model. We show through numerical simulations that the performance of this neural filter is as good as a standard particle filter in the limit of large number of particles. Remarkably, when the number of dimensions is large and when the number of particles is limited, the neural filter outperforms the standard particle filter.

This talk is part of the Computational Neuroscience series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.

Other lists

Craik Club The Faraday Institute for Science and Religion Lady Margaret Beaufort Commemoration Event CHUCOL seminars Guy Emerson's list Brain Mapping Unit Networks Meeting and the Cambridge Connectome Consortium

Other talks

Project Management Phylogenetic hypothesis of the Oleeae tribe (Oleaceae)
 Diversification and molecular evolution patterns in plastid and nuclear ribosomal DNA Exploring the mechanisms of haematopoietic lineage progression at the single-cell level A lifelong project in clay: Virtues of Unity Cafe Synthetique: Synthetic Biology Industry Night The DNA oxygenase TET1 in mammalian embryonic development and epigenetic reprogramming
 

© 2006-2024 Talks.cam, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity