First-Spike-Based Visual Categorization Using Reward-Modulated STDP (Mozafari et al. 2018)

 Download zip file 
Help downloading and running models
Accession:240369
"...Here, for the first time, we show that (Reinforcement Learning) RL can be used efficiently to train a spiking neural network (SNN) to perform object recognition in natural images without using an external classifier. We used a feedforward convolutional SNN and a temporal coding scheme where the most strongly activated neurons fire first, while less activated ones fire later, or not at all. In the highest layers, each neuron was assigned to an object category, and it was assumed that the stimulus category was the category of the first neuron to fire. ..."
Reference:
1 . Mozafari M, Kheradpisheh SR, Masquelier T, Nowzari-Dalini A, Ganjtabesh M (2018) First-Spike-Based Visual Categorization Using Reward-Modulated STDP IEEE Transactions on Neural Networks and Learning Systems :1-13
Model Information (Click on a link to find other models with that property)
Model Type: Realistic Network;
Brain Region(s)/Organism:
Cell Type(s): Abstract integrate-and-fire neuron;
Channel(s):
Gap Junctions:
Receptor(s):
Gene(s):
Transmitter(s):
Simulation Environment: C#;
Model Concept(s): Reward-modulated STDP; STDP; Winner-take-all; Reinforcement Learning; Temporal Coding; Vision;
Implementer(s): Mozafari, Milad [milad.mozafari at ut.ac.ir];
/
MozafariEtAl2018
RLSNN
Core
Tester
RLSNN.sln
                            

Microsoft Visual Studio Solution File, Format Version 12.00
# Visual Studio 14
VisualStudioVersion = 14.0.25123.0
MinimumVisualStudioVersion = 10.0.40219.1
Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "Core", "Core\Core.csproj", "{3754A514-0D1F-40A2-B53E-C54D5D41B81D}"
EndProject
Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "Tester", "Tester\Tester.csproj", "{2A40F0CA-0CDD-46D8-B04D-F3A7D5326297}"
EndProject
Global
	GlobalSection(SolutionConfigurationPlatforms) = preSolution
		Debug|Any CPU = Debug|Any CPU
		Debug|x64 = Debug|x64
		Release|Any CPU = Release|Any CPU
		Release|x64 = Release|x64
	EndGlobalSection
	GlobalSection(ProjectConfigurationPlatforms) = postSolution
		{3754A514-0D1F-40A2-B53E-C54D5D41B81D}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
		{3754A514-0D1F-40A2-B53E-C54D5D41B81D}.Debug|Any CPU.Build.0 = Debug|Any CPU
		{3754A514-0D1F-40A2-B53E-C54D5D41B81D}.Debug|x64.ActiveCfg = Debug|Any CPU
		{3754A514-0D1F-40A2-B53E-C54D5D41B81D}.Debug|x64.Build.0 = Debug|Any CPU
		{3754A514-0D1F-40A2-B53E-C54D5D41B81D}.Release|Any CPU.ActiveCfg = Release|Any CPU
		{3754A514-0D1F-40A2-B53E-C54D5D41B81D}.Release|Any CPU.Build.0 = Release|Any CPU
		{3754A514-0D1F-40A2-B53E-C54D5D41B81D}.Release|x64.ActiveCfg = Release|Any CPU
		{3754A514-0D1F-40A2-B53E-C54D5D41B81D}.Release|x64.Build.0 = Release|Any CPU
		{2A40F0CA-0CDD-46D8-B04D-F3A7D5326297}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
		{2A40F0CA-0CDD-46D8-B04D-F3A7D5326297}.Debug|Any CPU.Build.0 = Debug|Any CPU
		{2A40F0CA-0CDD-46D8-B04D-F3A7D5326297}.Debug|x64.ActiveCfg = Debug|x64
		{2A40F0CA-0CDD-46D8-B04D-F3A7D5326297}.Debug|x64.Build.0 = Debug|x64
		{2A40F0CA-0CDD-46D8-B04D-F3A7D5326297}.Release|Any CPU.ActiveCfg = Release|Any CPU
		{2A40F0CA-0CDD-46D8-B04D-F3A7D5326297}.Release|Any CPU.Build.0 = Release|Any CPU
		{2A40F0CA-0CDD-46D8-B04D-F3A7D5326297}.Release|x64.ActiveCfg = Release|Any CPU
		{2A40F0CA-0CDD-46D8-B04D-F3A7D5326297}.Release|x64.Build.0 = Release|Any CPU
	EndGlobalSection
	GlobalSection(SolutionProperties) = preSolution
		HideSolutionNode = FALSE
	EndGlobalSection
EndGlobal

Loading data, please wait...