Title: Time Organized Maps Learning cortical topography from spatiotemporal stimuli
1Time Organized Maps Learning cortical
topography from spatiotemporal stimuli
- Learning cortical topography from spatiotemporal
stimuli, J. Wiemer, F. Spengler, F. Joublin, P.
Stagge, S. Wacquant, Biological Cybernetics, 2000 - The Time-Organized Map Algorithm Extending the
Self-Organizing Map to Spatiotemporal Signals,
Jan C.Wiemer, Neural Computation, 2003
Presented by Mojtaba Solgi
TexPoint fonts used in EMF. Read the TexPoint
manual before you delete this box. AAAAA
2Outline
- The purpose and biological motivation
- The Model TOM Algorithm
- Wave propagation
- Learning
- Experiments and Results
- Gaussian stimuli
- Generic artificial stimuli
- Semi-natural stimuli
- Discussion
- z
3Neurobiological experiments, Spengler et al.,
1996, 1999
4Terminology
- Integration
- Fusion of different stimuli into one
representation - Segregation
- Process of Increasing representational distance
of different stimuli - z
52D Network Architecture Activation positional
shift
6One-dimensional model
7Wave propagation
8Integration and Segregation
9Algorithm
- Compute neurons activations and the position of
the top winner neuron - Compute the neural position of the propagated
wave from the last time step activation
10Algorithm Cont.
- Shift the position of the top winner neuron due
to interaction with propagated wave
11Algorithm Cont.
- Again shift the position of the winner neuron
this time due to noise - Update the winner neurons weights
- SOM
- Hebbian
12Experiments with Gaussian stimuli 2D neural
layer
- Simulation of ontogenesis (Development)
13Experiments with Gaussian stimuli 2D neural
layer
- Simulation of post-ontogenetic plasticity
14One-dimensional model
15Experiments with generic artificial stimuli 1D
neural layer
The input
16Experiments with semi-natural stimuli 1D neural
layer
17Experiments with semi-natural stimuli 1D neural
layer
18Discussion
- Importance of temporal stimulus for development
of cortical topography - Continuous mapping of related stimuli
- Inter-Stimulus-Interval-Dependant representations
- Hardly scalable
- No recognition performance on real-world problems
- Tested only on artificial input
19Summary
- Utilizing temporal information in developing
cortical topography - Wave-like spread of cortical activity
- Experiments and results show compatibility of the
model with neurobiological observations - Biologically inspired and plausible, but no
engineering performance
20Thank you!