Felix Gers

From Wikipedia, the free encyclopedia
Jump to navigation Jump to search

Felix Gers is a professor of computer science at Beuth University of Applied Sciences Berlin.[1] With Jürgen Schmidhuber and Fred Cummins, he introduced the forget gate to the long short-term memory recurrent neural network architecture.[2][3] This modification of the original[4] architecture has been shown to be crucial to the success of the LSTM at such tasks as speech and handwriting recognition.[3]


  1. ^ "Felix Gers - Professor at Beuth University of Applied Sciences Berlin". Retrieved May 13, 2017.
  2. ^ Felix A. Gers; Jürgen Schmidhuber; Fred Cummins (2000). "Learning to Forget: Continual Prediction with LSTM". Neural Computation. 12 (10): 2451–2471. doi:10.1162/089976600300015015.
  3. ^ a b Greff, Klaus; Srivastava, Rupesh K.; Koutnik, Jan; Steunebrink, Bas R.; Schmidhuber, Jurgen (2016). "LSTM: A Search Space Odyssey". IEEE Transactions on Neural Networks and Learning Systems: 1–11. arXiv:1503.04069. doi:10.1109/TNNLS.2016.2582924. ISSN 2162-237X.
  4. ^ Hochreiter, Sepp; Schmidhuber, Jürgen (1997). "Long Short-Term Memory". Neural Computation. 9 (8): 1735–1780. doi:10.1162/neco.1997.9.8.1735. ISSN 0899-7667.