Felix A. Gers

Sort by:

Learning to Forget: Continual Prediction with LSTM

Felix A. Gers, Jürgen Schmidhuber, Fred A. Cummins
Neural Computation
2000

Long short-term memory (LSTM; Hochreiter & Schmidhuber, 1997) can solve numerous tasks not solvable by previous learning algorithms for recurrent neural networks (RNNs). We identify a weakness of… (More)

LSTM recurrent networks learn simple context-free and context-sensitive languages

Felix A. Gers, Jürgen Schmidhuber
IEEE Trans. Neural Networks
2001

Previous work on learning regular languages from exemplary training sequences showed that long short-term memory (LSTM) outperforms traditional recurrent neural networks (RNNs). We demonstrate LSTMs… (More)

Learning Precise Timing with LSTM Recurrent Networks

Felix A. Gers, Nicol N. Schraudolph, Jürgen Schmidhuber
Journal of Machine Learning Research
2002

The temporal distance between events conveys information essential for numerous sequential tasks such as motor control and rhythm detection. While Hidden Markov Models tend to ignore this… (More)

Recurrent Nets that Time and Count

CoDi-1Bit: A Simplified Cellular Automata Based Neuron Model

Felix A. Gers, Hugo de Garis, Michael Korkin
Artificial Evolution
1997

This paper presents some simpliications to our recently introduced \CoDi-model", which we use to evolve Cellular Automata based neural network modules for ATR's artiicial brain project \CAM-Brain"… (More)

Kalman filters improve LSTM network performance in problems unsolvable by traditional recurrent nets

Juan Antonio Pérez-Ortiz, Felix A. Gers, Douglas Eck, Jürgen Schmidhuber
Neural Networks
2003

The long short-term memory (LSTM) network trained by gradient descent solves difficult problems which traditional recurrent neural networks in general cannot. We have recently observed that the… (More)

Building an artificial brain using an FPGA based CAM-Brain Machine

Hugo de Garis, Michael Korkin, Felix A. Gers, Norberto Eiji Nawa, Michael Hough
Applied Mathematics and Computation
2000

This paper reports on recent progress made in ATR's attempt to build a 10,000 evolved neural net module artificial brain to control the behaviors of a life sized robot kitten.

Applying LSTM to Time Series Predictable through Time-Window Approaches

Felix A. Gers, Douglas Eck, Jürgen Schmidhuber
ICANN
2000

Long Short-Term Memory (LSTM) is able to solve many time series tasks unsolvable by feed-forward networks using xed size time windows. Here we nd that LSTM's superiority does not carry over to… (More)

Analysing Errors of Open Information Extraction Systems

Rudolf Schneider, Tom Oberhauser, Tobias Klatt, Felix A. Gers, Alexander Löser
ArXiv
2017

We report results on benchmarking Open Information Extraction (OIE) systems using RelVis, a toolkit for benchmarking Open Information Extraction systems. Our comprehensive benchmark contains three… (More)

Learning Nonregular Languages: A Comparison of Simple Recurrent Networks and LSTM

Jürgen Schmidhuber, Felix A. Gers, Douglas Eck
Neural Computation
2002

In response to Rodriguez's recent article (2001), we compare the performance of simple recurrent nets and long short-term memory recurrent nets on context-free and context-sensitive languages.

Filter Results:

Publication Year

Publication Type

Co-author

Journals and Conferences