Recurrent Neural Networks

concepts · 4 notes linked

Related: Tensorflow · Pytorch · Deep Learning Frameworks · Deepmind · Calligrapher AI · Handwriting Synthesis · Generative Models · Backpropagation Through Time

Notes

• A ten-minute introduction to sequence-to-sequence learning in Keras — Keras LSTM encoder-decoder implementation for sequence-to-sequence translation
• Deepfakes for scrawl: With handwriting synthesis, no pen is necessary — RNN web app synthesizes realistic varied handwriting without fonts
• How to implement an RNN (2/2) - Tensor data and non-linearities — From-scratch NumPy RNN with tensor input, tanh activations, and RMSProp optimizer
• Implementation differences in LSTM layers- Tensorflow vs Pytorch | Towards Data Science — API and parameter differences in LSTM layer implementations across TF and PyTorch