Publications
Journal, Book-Chapter, Thesis:
- F. A. Gers and W. Boomgarden.
Beschleunigte Medikamenten-Entwicklung durch virtuelles Screening.
Pharma and Food, 2003.
to appear.
- J. A. Pérez-Ortiz, F. A. Gers, D. Eck,
and J. Schmidhuber.
Kalman filters improve LSTM network performance in problems unsolvable by
traditional recurrent nets.
Neural Networks, 16(2):241-250, 2002.
- J. Schmidhuber, F. A. Gers, and
D. Eck.
Learning nonregular languages: A comparison of simple recurrent networks and
LSTM.
Neural Computation, 14(9):2039-2041, 2002.
- F. A. Gers and J. Schmidhuber.
LSTM recurrent networks learn simple context free and context sensitive
languages.
IEEE Transactions on Neural Networks, 12(6):1333-1340, 2001.
- F. A. Gers.
Long Short-Term Memory in Recurrent Neural Networks.
PhD thesis, Department of Computer Science, Swiss Federal Institute of
Technology, Lausanne, EPFL, Switzerland, 2001.
- F. A. Gers, J. Schmidhuber, and
F. Cummins.
Learning to forget: Continual prediction with LSTM.
Neural Computation, 12(10):2451-2471, 2000.
- F. A. Gers, J. Schmidhuber, and
N. Schraudolph.
Learning precise timing with LSTM recurrent networks.
Journal of Machine Learning Research (JMLR), 3:115-143, 2002.
- F. A. Gers, H. De Garis, and M. Korkin.
Evolution of neural sructures based on cellular automata.
In C. Jain Lakhmi, editor, Soft Computing Techniques in Knowlage-based
Intelligent Engineering Systems, pages 259-278. Physica-Verlag,
Heidelberg New York, 1997.
- F. A. Gers, H. De Garis, and M. Korkin.
A simplified cellular automata based neuron model.
In J.K Hao, E. Lutton, E. Ronald, M. Schoennauer, and D. Snyers, editors,
Artificial Evolution, pages 315-334. Springer Verlag,
1997.
- F. A. Gers and J. W. Czarske.
Untersuchungen zur verteilten Temperatur-Sensorik mit stimulierter
Brillouin-Streuung.
In Laser'95 Conference Proceedings C P22,
Note: Material aus Diplomarbeit, 1995.
Conference, Workshop:
- F. A. Gers, J. A. Pérez-Ortiz, D. Eck,
and J. Schmidhuber.
DEKF-LSTM.
In Verleysen, editor, 10th European Symposium on Artificial Neural
Networks. ESANN'2002. Proceedings. Brussels, Belgium, pages 369-376,
2002.
- F. A. Gers, J. A. Pérez-Ortizand,
D. Eck, and J. Schmidhuber.
Learning context sensitive languages with LSTM trained with kalman filters.
In J. Dorronsoro, editor, Proc. ICANN 2002, Int. Conf. on Artificial
Neural Networks, pages 655-660, Berlin, 2002. Springer.
- J. A. Pérez-Ortizand,
J. Schmidhuber, F. A. Gers, and D. Eck.
Improving long-term online prediction with decoupled extended kalman filters.
In J. Dorronsoro, editor, Proc. ICANN 2002, Int. Conf. on Artificial
Neural Networks, pages 1055-1060, Berlin, 2002. Springer.
- F. A. Gers, D. Eck, and J. Schmidhuber.
Applying LSTM to time series predictable through time-window approaches.
In Proc. ICANN 2001, Int. Conf. on Artificial Neural Networks,
Vienna, Austria, 2001. IEE, London.
- F. A. Gers, D. Eck, and J. Schmidhuber.
Applying LSTM to time series predictable through time-window approaches.
In M. Marinaro and R. Tagliaferri, editors, Neural Nets, WIRN
Vietri-2001, Proceedings 11th Workshop on Neural Nets, Vietri sul
Mare, Italy, 2001. Springer Verlag, Berlin.
- F. A. Gers and J. Schmidhuber.
LSTM learns context free languages.
In Snowbird 2000 Conference, 2000.
- F. A. Gers and J. Schmidhuber.
Long Short-Term Memory learns context free and context sensitive languages.
In Kurkova et./ al./, editor, Proceedings of the ICANNGA 2001
Conference, volume 1, pages 134-137, Wien,NY, 2001. Springer.
- F. A. Gers and J. Schmidhuber.
Neural processing of complex continual input streams.
In Proc. IJCNN'2000, Int. Joint Conf. on Neural Networks, Como,
Italy, 2000.
- F. A. Gers and J. Schmidhuber.
Recurrent nets that time and count.
In Proc. IJCNN'2000, Int. Joint Conf. on Neural Networks, Como,
Italy, 2000.
- M. Hough, H. De Garis, M. Korkin, F. A.
Gers, and N. E. Nawa.
Spiker : Analog waveform to digital spiketrain conversion in atr's artificial
brain "cam-brain" project.
In Int. Conf. on Robotics and Artificial Life, Beppu, Japan,
1999.
- Fred Cummins, Felix Gers, and Jürgen
Schmidhuber.
Language identification from prosody without explicit features.
In Proceedings of EUROSPEECH'99, volume 1, pages 371-374, 1999.
- F. A. Gers, J. Schmidhuber, and F. Cummins.
Learning to forget: Continual prediction with LSTM.
In Proc. ICANN'99, Int. Conf. on Artificial Neural Networks,
volume 2, pages 850-855, Edinburgh, Scotland, 1999. IEE, London.
- F. Cummins, F. A. Gers, and
J. Schmidhuber.
Automatic discrimination among languages based on prosody alone.
Technical Report IDSIA-03-99, IDSIA, Lugano, CH, 1999.
- F. A. Gers, J. Schmidhuber, and F. Cummins.
Continual prediction using LSTM with forget gates.
In M. Marinaro and R. Tagliaferri, editors, Neural Nets, WIRN Vietri-99,
Proceedings 11th Workshop on Neural Nets, pages 133-138, Vietri sul
Mare, Italy, 1999. Springer Verlag, Berlin.
- H. De Garis, F. A. Gers, M. Korkin,
A. Agah, and N. E. Nawa.
Building an artificial brain using an FPGA based 'CAM-brain machine'.
Artificial Life and Robotics Journal, 2:56-61, 1998.
- N. E. Nawa, H. De Garis, F. A. Gers, and
M. Korkin.
'ATR's CAM-brain machine (CBM) simulation results and representation
issues.
In Genetic Programming Conference, 1998.
- F. A. Gers, H. De Garis, and M. Korkin.
Codi-1bit : A cellular automata based neural net model simple enough to be
implemented in evolvable hardware.
In Int.Symposium on Artificial Life and Robotics (AROB), Beppu, Oita,
Japan, 1998.
- M. Korkin, H. De Garis, F. A. Gers,
and H. Hemmi.
'CBM (CAM-brain machine) : A hardware tool which evolves a neural net
module in a fraction of a second and runs a million neuron artificial brain
in real time.
In Genetic Programming Conference, Stanford, USA, 1997.
- F. A. Gers and H. De Garis.
Codi-1bit : A simplified cellular automata based neuron model.
In Artificial Evolution Conference (AE), Nimes, France, 1997.
- F. A. Gers and H. De Garis.
CAM-brain : A new model for ATR's cellular automata based artificial brain
project.
In Int. Conf. on Evolvable Systems Conference Proceedings (ICES) S7-5,
Tsukuba, Japan, 1996.
- F. A. Gers and H. De Garis.
Porting a cellular automata based artificial brain to MIT's cellular automata
machine "CAM-8".
In Int. Conf. on Simulated Evolution and Learnin (SEAL) S7-3, Taejon,
Korea, 1996.
Technical Report, Patent:
- F. A. Gers, D. Eck, and J. Schmidhuber.
Applying LSTM to time series predictable through time-window approaches.
Technical Report IDSIA-22-00, IDSIA, Manno, CH, 2000.
- F. A. Gers and J. Schmidhuber.
Long Short-Term Memory learns context free languages and context sensitive
languages.
Technical Report IDSIA-03-00, IDSIA, Manno, CH, 2000.
- F. A. Gers and J. Schmidhuber.
Neural processing of complex continual input streams.
Technical Report IDSIA-02-00, IDSIA, Manno, CH, 2000.
- F. A. Gers and J. Schmidhuber.
Recurrent nets that time and count.
Technical Report IDSIA-01-00, IDSIA, Manno, CH, 2000.
- F. A. Gers, J. Schmidhuber, and F. Cummins.
Learning to forget: Continual prediction with LSTM.
Technical Report IDSIA-01-99, IDSIA, Lugano, CH, 1999.
- F. A. Gers and H. De Garis.
Neurocellular automaton and optimizer.
US patent No.:USP 6061674.