Feel free to contribute & open an issue to help the nervous system
- Neuron Models
- Neural Population
- Unsupervised STDP Learning
- Reward Modulated STDP Learning
- DoG & Gabor in Convolution
- Full object detection model based on spiking neural network
- Gabor Filter
- Difference of Gaussian
- Feature map
- Detect dominant lines and features, and show improvement and precision through time
- Implementation Unsupervised STDP Learning
- Plot delta weights caused by STDP learning for two neuron with random excitation
- Generate 10x2 Spiking Networks & learn Two 10th-tuple by each output neuron
- Add an inhibitory neuron to upper network
Model trained and tested on caltech101 dataset
Caltech-101 consists of pictures of objects belonging to 101 classes, plus one background clutter class. Each image is labelled with a single object. Each class contains roughly 40 to 800 images, totalling around 9k images. Images are of variable sizes, with typical edge lengths of 200-300 pixels.
We presents an deep spiking neural model which consist of 3 layer. for first two layer only STDP learning is used, and for last layer dopamine releases followed by STDP and anti-STDP.
For more documentation see code, documentation will be updated
class videos and Lecture Notes
Computational Neuroscience Research Lab. (Department of Computer Science, University of Tehran) For more info, please visit cnrl.ut.ac.ir