Unsupervised Learning in LSTM Recurrent Neural Networks

By Magdalena Klapper-Rybicka, N. Schraudolph, J. Urgen Schmidhuber. 2001

30 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Materials Chemistry, Statistical and Nonlinear Physics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Aditya Rawal
2. Scott Niekum
3. Aloysius Ka-Lau Mok
4. Kay E. Holekamp
5. Aunn Raza
6. Ala Al-Fuqaha
7. Hunain Arif
8. Amir Hussain

In Materials Chemistry

1. Aloysius Ka-Lau Mok
2. Risto Miikkulainen
3. Aditya Rawal
4. Kay E. Holekamp
5. Scott Niekum

In Statistical and Nonlinear Physics

1. Aloysius Ka-Lau Mok
2. Amir Hussain
3. Risto Miikkulainen
4. Junaid Qadir
5. Aditya Rawal
6. Kay E. Holekamp
7. Scott Niekum

Citations in the corpus

• Deep learning in neural networks: An overview (2014, neutral): “…(Hawkins & George, 2006; Kurzweil, 2012) also got interested in HTMs; compare also hierarchical HMMs (e.g., Fine, Singer, & Tishby, 1998), as well as later UL-based recurrent systems (Klampfl &Maass, 2013; Klapper-Rybicka et al., 2001; Steil, 2007; Young, Davis, Mishtal, & Arel, 2014).”
• Unsupervised Machine Learning for Networking: Techniques, Applications and Research Challenges (2017, methodology): “Considering unsupervised learning of RNN in the scope of this paper, [57] employ Long Short-termMemory (LSTM)RNN to be trained in an unsupervised manner using unsupervised learning algorithms, namely Binary Information Gain Optimization and”
• Discovering Gated Recurrent Neural Network Architectures (2018, methodology): “On a related note, Klapper-Rybicka et al. (2001) performed unsupervised clustering of musical data using LSTM networks.”
• Evolving Deep LSTM-based Memory Networks using an Information Maximization Objective (2016, methodology): “related note, [13] performed unsupervised clustering of musical data using LSTM networks.”