Neural Reckoning is a research group at Imperial College London, led by Dan Goodman, with a main focus on computational neuroscience.

Anna Levina - Timescales: flexible in biological neural systems, useful for computations
44:35
Anna Levina - Timescales: flexible in biological neural systems, useful for computations
Veronika Koren - Efficient encoding/transmission/transformation sensory features in a multilayer SNN
25:25
Veronika Koren - Efficient encoding/transmission/transformation sensory features in a multilayer SNN
Ulaş İbrahim Ayyılmaz - Exc/inh neurons distinct roles for learning, temporal scaling, and WM
22:56
Ulaş İbrahim Ayyılmaz - Exc/inh neurons distinct roles for learning, temporal scaling, and WM
Rainer Engelken - Using Dynamical Systems Theory to Improve Surrogate Gradient Learning in SNNs
24:13
Rainer Engelken - Using Dynamical Systems Theory to Improve Surrogate Gradient Learning in SNNs
Filippo Moro - On the role of temporal hierarchy in Spiking Neural Networks
21:12
Filippo Moro - On the role of temporal hierarchy in Spiking Neural Networks
David Kappel - Spiking networks for efficient machine learning
47:11
David Kappel - Spiking networks for efficient machine learning
Flash talks from SNUFA 2024
23:13
Flash talks from SNUFA 2024
William Podlaski - Storing overlapping associative memories on latent manifolds in low-rank SNNs
22:34
William Podlaski - Storing overlapping associative memories on latent manifolds in low-rank SNNs
Christian Machens - Computing with spikes - a geometric approach to spiking neural networks
43:22
Christian Machens - Computing with spikes - a geometric approach to spiking neural networks
Matteo Saponati - Feedback control algorithm for online learning in SNN and neuromorphic devices
22:47
Matteo Saponati - Feedback control algorithm for online learning in SNN and neuromorphic devices
Karim Habashy - Adapting to time: why nature chose to evolve a diverse set of neurons
20:04
Karim Habashy - Adapting to time: why nature chose to evolve a diverse set of neurons
Chiara Bartolozzi - Neuromorphic technologies for robotic applications, from sensing to control
46:59
Chiara Bartolozzi - Neuromorphic technologies for robotic applications, from sensing to control
W9 V1 - What are spikes for?
9:35
W9 V1 - What are spikes for?
W9 V0 - Does neuroscience work?
6:55
W9 V0 - Does neuroscience work?
W8 V2 - Neuromorphic sensing and applications
2:38
W8 V2 - Neuromorphic sensing and applications
W8 V1 - Neuromorphic computing
10:09
W8 V1 - Neuromorphic computing
W8 V0 - Introduction to neuromorphic devices
3:57
W8 V0 - Introduction to neuromorphic devices
W7 V0 - Decision making
6:02
W7 V0 - Decision making
W6 V4 - Exercise
2:44
W6 V4 - Exercise
W6 V2 - Manipulating
8:42
W6 V2 - Manipulating
W6 V1 - Analysing
9:24
W6 V1 - Analysing
W6 V0 - Observing
8:21
W6 V0 - Observing
W5 V2 - Surrogate gradients
11:24
W5 V2 - Surrogate gradients
W5 V1 - Limited gradients
5:15
W5 V1 - Limited gradients
W5 V0 - Spiking is not differentiable
5:31
W5 V0 - Spiking is not differentiable
Rodolphe Sepulchre - Neuromorphic learning: a control perspective
45:16
Rodolphe Sepulchre - Neuromorphic learning: a control perspective
Antony W. N’dri - Combining various types of STDP to learn efficient neural codes
22:52
Antony W. N’dri - Combining various types of STDP to learn efficient neural codes
Jeff Krichmar - CARLSim: An Open-Source Community Resource for Large-Scale, Detailed SNN R&D
50:30
Jeff Krichmar - CARLSim: An Open-Source Community Resource for Large-Scale, Detailed SNN R&D
Alexander Efremov - Training fast spiking networks through STDP and control feedback
18:51
Alexander Efremov - Training fast spiking networks through STDP and control feedback
Justus Huebotter - Training Spiking Neural Networks for Continuous Control with Surrogate Gradients
23:11
Justus Huebotter - Training Spiking Neural Networks for Continuous Control with Surrogate Gradients