/fast-weights-pytorch

PyTorch Implementation of the paper [Using Fast Weights to Attend to the Recent Past]

Primary LanguagePythonApache License 2.0Apache-2.0

fast-weights-pytorch

PyTorch Implementation of the paper [Using Fast Weights to Attend to the Recent Past] Code for generating sequential data is forked from jiamings/fast-weights

Dependencies

Python >= 3.6 Pytorch TensorboardX Numpy Pickle

Usage

Generate a dataset

$ python generator.py

Train the model of fast-weights

$ python fast_weights.py

Training Result

References

Using Fast Weights to Attend to the Recent Past. Jimmy Ba, Geoffrey Hinton, Volodymyr Mnih, Joel Z. Leibo, Catalin Ionescu.

Layer Normalization. Jimmy Ba, Ryan Kiros, Geoffery Hinton.