CARLsim is an efficient, easy-to-use, GPU-accelerated software framework for simulating large-scale spiking neural network (SNN) models with a high degree of biological detail.
MIT License
41
stars
16
forks
source link
CARLsim6 saveSimluation() and loadSimulation() #33
Using the saveSimulation function in CARLsim6 to store the weights after the training of ECJ, there is a situation that the dimensionality of the weights stored in the generated sim.dat file does not match the actual network structure, and the size of the dimensionality stored in the training network is changing every time.
Using the saveSimulation function in CARLsim6 to store the weights after the training of ECJ, there is a situation that the dimensionality of the weights stored in the generated sim.dat file does not match the actual network structure, and the size of the dimensionality stored in the training network is changing every time.