fast-weights 10 fast-weight-programmers 8 pytorch 7 transformers 5 self-referential-learning 3 self-referential-weight-matrix 3 language-modeling 2 torchbeast 2 recurrent-neural-networks 2 reinforcement-learning 2 deep-learning 2 linear-transformers 2 tensorflow 1 tensorflow-models 1 accuracy 1 dct 1 formal-languages 1 generative-adversarial-network 1 image-generation 1 neural-learning-rules 1 rnn-based-few-shot-learning 1 language-model 1 neural-odes 1 neural-differential-equations 1 controlled-differential-equations 1 continuous-time-sequence-processing 1 meta-learning 1 few-shot-learning 1 cuda 1 continual-learning 1