diff --git a/README.md b/README.md index a03d61b44bc7337fe29cfbb37d9b828ce62c2c94..a77e7adb7db1701d4a443811f714adef0ec99d0e 100644 --- a/README.md +++ b/README.md @@ -139,18 +139,6 @@ model.fit(train_dataset=trainset, test_dataset=testset, val_dataset=None) ``` -## Naming conventions - -Some naming conventions used in the code differ from the ones used in the paper: -- CSNN: feature extraction layer -- CSNN-1: CSNN-16 (16 feature maps) -- CSNN-2: CSNN-64 (64 feature maps) -- CSNN-3: CSNN-128 (128 feature maps) -- Readout: classification layer -- SSTDP-OG: SSTDPv1 -- SSTDP: SSTDPv2 -- PCN-SSTDP: SSTDPv2+PCN - ## Known bugs - Depending on your machine, results on CIFAR-10 can slightly differ (not a significative difference though). It comes from the download/conversion process in `datasets/get_cifar10.py`.