TF_ContinualLearningViaSynapticIntelligence
TF_ContinualLearningViaSynapticIntelligence copied to clipboard
Published
20 hours ago •
spiglerg
spiglerg
Tensorflow implementation of the `intelligent synapse' model from [Zenke et al., (2017)] and application to the Permuted MNIST benchmark.
Results
1
TF_ContinualLearningViaSynapticIntelligence issues
Sort by
recently updated
recently updated
newest added
May I ask why aren't you normalizing the cross_entropy loss across the batch before calculating the gradients in the following line: `cross_entropy = -tf.reduce_sum( y_tgt*tf.log(y+1e-04) + (1.-y_tgt)*tf.log(1.-y+1e-04) )` If I...
