Search PubMed⌕ Search

Biomedical subjects

Jürgen Schmidhuber

Publications and source records attributed to Jürgen Schmidhuber.

6 recordsLinked to original sources
PubMed2004

Self-organizing nets for optimization.

Given some optimization problem and a series of typically expensive trials of solution candidates sampled from a search space, how can we efficiently select the next candidate? We address this fundamental problem by embedding simple optimization strategies in learning algorithms inspired by Kohonen's self-organizing maps and neural gas networks. Our adaptive nets or grids are used to identify and exploit search space regions that maximize the probability of generating points closer to the optima. Net nodes are attracted by candidates that lead to improved evaluations, thus, quickly biasing the active data selection process toward promising regions, without loss of ability to escape from local optima. On standard benchmark functions, our techniques perform more reliably than the widely used covariance matrix adaptation evolution strategy. The proposed algorithm is also applied to the problem of drag reduction in a flow past an actively controlled circular cylinder, leading to unprecedented drag reduction.

Neural Networks, Computer↗
PubMed2003

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

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 decoupled extended Kalman filter training algorithm allows for even better performance, reducing significantly the number of training steps when compared to the original gradient descent training algorithm. In this paper we present a set of experiments which are unsolvable by classical recurrent networks but which are solved elegantly and robustly and quickly by LSTM combined with Kalman filters.

Algorithms↗
PubMedDate not supplied

Framewise phoneme classification with bidirectional LSTM and other neural network architectures.

In this paper, we present bidirectional Long Short Term Memory (LSTM) networks, and a modified, full gradient version of the LSTM learning algorithm. We evaluate Bidirectional LSTM (BLSTM) and several other network architectures on the benchmark task of framewise phoneme classification, using the TIMIT database. Our main findings are that bidirectional networks outperform unidirectional ones, and Long Short Term Memory (LSTM) is much faster and also more accurate than both standard Recurrent Neural Nets (RNNs) and time-windowed Multilayer Perceptrons (MLPs). Our results support the view that contextual information is crucial to speech processing, and suggest that BLSTM is an effective architecture with which to exploit it.

Algorithms↗