Imperial College London > Talks@ee.imperial > Daniel F M Goodman's list > Predictive representation learning in biological neural networks Speaker: Friedemann Zenke
Log inImperial users Other users No account?Information onFinding a talk Adding a talk Syndicating talks Who we are Everything else |
Predictive representation learning in biological neural networks Speaker: Friedemann ZenkeAdd to your list(s) Download to your calendar using vCal
If you have a question about this talk, please contact Dan F M Goodman. Discriminating distinct objects and concepts from sensory stimuli is essential for survival. Our brains perform this processing in deep sensory networks shaped through plasticity. However, our understanding of the underlying plasticity mechanisms still needs to be improved. I will introduce Latent Predictive Learning (LPL), a local learning rule that conceptually extends Bienenstock-Cooper-Munro (BCM) theory. We show that deep neural networks equipped with LPL develop disentangled object representations without supervision. The same rule accurately captures neuronal selectivity changes observed in the primate inferotemporal cortex in response to altered visual experience. Finally, our model generalizes to spiking neural networks and naturally accounts for several experimentally observed properties of synaptic plasticity, including metaplasticity and spike-timing-dependent plasticity (STDP). LPL thus constitutes a plausible normative theory of representation learning in the brain while making concrete testable predictions. This talk is part of the Daniel F M Goodman's list series. This talk is included in these lists:Note that ex-directory lists are not shown. |
Other listsIEEE Magnetics Society Distinguished Lecturer Visits Wind Farms SAP C_C4H225_12Other talksKeynote Speech on Influence and persuasion Two Applications of Compression in Group Testing and Multi-Armed Bandits |