#### Filter Results:

- Full text PDF available (25)

#### Publication Year

2003

2016

#### Publication Type

#### Co-author

#### Publication Venue

#### Data Set Used

#### Key Phrases

Learn More

Several variants of the Long Short-Term Memory (LSTM) architecture for recurrent neural networks have been proposed since its inception in 1995. In recent years, these networks have become the state-of-the-art models for a variety of machine learning problems. This has led to a renewed interest in understanding the role and utility of various computational… (More)

Sequence prediction and classification are ubiquitous and challenging problems in machine learning that can require identifying complex dependencies between temporally distant inputs. Recurrent Neural Networks (RNNs) have the ability, in theory, to cope with these temporal dependencies by virtue of the short-term memory implemented by their recurrent… (More)

- Julian Togelius, Sergey Karakovskiy, Jan Koutník, Jürgen Schmidhuber
- 2009 IEEE Symposium on Computational Intelligence…
- 2009

We introduce a new reinforcement learning benchmark based on the classic platform game Super Mario Bros. The benchmark has a high-dimensional input space, and achieving a good score requires sophisticated and varied strategies. However, it has tunable difficulty, and at the lowest difficulty setting decent score can be achieved using rudimentary strategies… (More)

- Jan Koutník, Faustino J. Gomez, Jürgen Schmidhuber
- GECCO
- 2010

We propose a new indirect encoding scheme for neural networks in which the weight matrices are represented in the frequency domain by sets Fourier coefficients. This scheme exploits spatial regularities in the matrix to reduce the dimensionality of the representation by ignoring high-frequency coefficients, as is done in lossy image compression. We compare… (More)

- Pavel Kordík, Jan Koutník, Jan Drchal, Oleg Kovárík, Miroslav Cepek, Miroslav Snorek
- Neural Networks
- 2010

Optimization of neural network topology, weights and neuron transfer functions for given data set and problem is not an easy task. In this article, we focus primarily on building optimal feed-forward neural network classifier for i.i.d. data sets. We apply meta-learning principles to the neural network structure and function optimization. We show that… (More)

Many sequential processing tasks require complex nonlinear transition functions from one step to the next. However, recurrent neural networks with " deep" transition functions remain difficult to train, even when using Long Short-Term Memory (LSTM) networks. We introduce a novel theoretical analysis of recurrent networks based on Geršgorin's circle theorem… (More)

- Michael Wand, Jan Koutník, Jürgen Schmidhuber
- 2016 IEEE International Conference on Acoustics…
- 2016

Lipreading, i.e. speech recognition from visual-only recordings of a speaker's face, can be achieved with a processing pipeline based solely on neural networks, yielding significantly better accuracy than conventional methods. Feedforward and recurrent neural network layers (namely Long Short-Term Memory; LSTM) are stacked to form a single structure which… (More)

- Jan Koutník, Giuseppe Cuccu, Jürgen Schmidhuber, Faustino J. Gomez
- GECCO
- 2013

The idea of using evolutionary computation to train artificial neural networks, or neuroevolution (NE), for reinforcement learning (RL) tasks has now been around for over 20 years. However, as RL tasks become more challenging, the networks required become larger, as do their genomes. But, scaling NE to large nets (i.e. tens of thousands of weights) is… (More)

- Jan Koutník, Jürgen Schmidhuber, Faustino J. Gomez
- GECCO
- 2014

Dealing with high-dimensional input spaces, like visual input, is a challenging task for reinforcement learning (RL). Neuroevolution (NE), used for continuous RL problems, has to either reduce the problem dimensionality by (1) compressing the representation of the neural network controllers or (2) employing a pre-processor (compressor) that transforms the… (More)

- Jan Drchal, Jan Koutník, Miroslav Snorek
- IEEE Congress on Evolutionary Computation
- 2009

— In this paper we describe simulation of autonomous robots controlled by recurrent neural networks, which are evolved through indirect encoding using HyperNEAT algorithm. The robots utilize 180 degree wide sensor array. Thanks to the scalability of the neural network generated by HyperNEAT, the sensor array can have various resolution. This would allow to… (More)