Sepp Hochreiter
Josef "Sepp" Hochreiter (born 14 February 1967) is a German computer scientist. Since 2018 he has led the Ins*ute for Machine Learning at the Johannes Kepler University of Linz after having led the Ins*ute of Bioinformatics from 2006 to 2018. In 2017 he became the head of the Linz Ins*ute of Technology (LIT) AI Lab. Hochreiter is also a founding director of the Ins*ute of Advanced Research in Artificial Intelligence (IARAI). Previously, he was at the Technical University of Berlin, at the University of Colorado at Boulder, and at the Technical University of Munich. He is a chair of the Critical *essment of M*ive Data *ysis (CAMDA) conference.
Hochreiter has made contributions in the fields of machine learning, deep learning and bioinformatics, most notably the development of the long short-term memory (LSTM) neural network architecture, but also in meta learning, reinforcement learning and biclustering with application to bioinformatics data.
Contents
- 1 Scientific career
- 1.1 Long short-term memory (LSTM)
- 1.2 Other machine learning contributions
- 2 Awards
- 3 References
- 4 External links
Scientific career
Long short-term memory (LSTM)
Hochreiter developed the long short-term memory (LSTM) neural network architecture in his diploma thesis in 1991 leading to the main publication in 1997. LSTM overcomes the problem that recurrent neural networks (RNNs) forget information over time (vanishing or exploding gradient). In 2007, Hochreiter and others successfully applied LSTM with an optimized architecture to very fast protein *logy detection without requiring a sequence alignment. LSTM networks have also been also used in Google Voice for transcription and search, and in the Google Allo chat app for generating response suggestion with low latency.
Other machine learning contributions
Beyond LSTM, Hochreiter has developed "Flat Minimum Search" to increase the generalization of neural networks and introduced rectified factor networks (RFNs) for sparse codingwhich have been applied in bioinformatics and genetics. Hochreiter introduced modern Hopfield networks with continuous states and applied them to the task of immune repertoire cl*ification.
Hochreiter worked with Jürgen Schmidhuber in the field of reinforcement learning on actor-critic systems thatlearn by "backpropagation through a model".
Hochreiter has been involved in the development of factor *ysis methods with application to bioinformatics, including FABIA for biclustering, HapFABIA for detecting short segments of iden*y by descent and FARMS for preprocessing and summarizing high-density oligonucleotide DNA microarrays to *yze RNA gene expression.
In 2006, Hochreiter and others proposed an extension of the support vector machine (SVM), the "Potential Support Vector Machine" (PSVM), which can be applied to non-square kernel matrices and can be used with kernels that are not positive definite. Hochreiter and his collaborators have applied PSVM to feature selection, including gene selection for microarray data.
Awards
Hochreiter was awarded the IEEE CIS Neural Networks Pioneer Prize in 2021 for his work on LSTM.
References
External links
- Home Page Sepp Hochreiter