From 4ce38f7320406291c31e79ebfe2dc83cbbe53dfd Mon Sep 17 00:00:00 2001 From: Thomas Limbacher Date: Tue, 14 Jul 2020 14:38:34 +0200 Subject: [PATCH] Update README.md --- README.md | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index a7c3ca1..d2a2949 100644 --- a/README.md +++ b/README.md @@ -17,7 +17,19 @@ conda env create --file=environment.yml to install the required packages and their dependencies. ## Usage -TODO +Run the following command + +```bash +python babi_task_single.py +``` + +to start training on bAbI task 1 in the 10k training examples setting. Set the command line argument `--task_id` to train on other tasks. You can try different model configurations by changing various command line arguments. For example, + +```bash +python babi_task_single.py --task_id=4 --memory_size=20 --epochs=50 --logging=1 +``` + +will train the model with an associative memory of size 20 on task 4 for 50 epochs. The results will be stored in `/results`. ## References * Limbacher, T., Legenstein, R. (2020). H-Mem: Harnessing synaptic plasticity with Hebbian Memory Networks bioRxiv https://dx.doi.org/10.1101/2020.07.01.180372