Unsupervised Conditional Reflex Learning Based on Convolutional Spiking Neural Network and Reward Modulation
- NEST
- Pytorch
- SkypeTorch
- V-REP (simulation platform)
- ROS(interface between simulation environment and the script)
- generate noise-like data with opencv and put the data into ./images
- train the feature-extract unit with the generated noise-like data in an unsupervised manner:
python ./feature_extract_unit/train_with_noiselikedata.py
- train the decision-making unit:
python ./decision_making_unit/train.py
-
parameters of the network can be changed in ./decision_making_unit/parameters.py
-
note: ./decision_making_unit/environment_1.py corresponds to scenario 1~3 and ./decision_making_unit/environment_2.py corresponds to scenario 4.
-
Our work is based on the following works: