A model for learning to segment temporal sequences, utilizing a mixture of RNN experts together with adaptive variance

DOI10.1016/j.neunet.2008.09.005zbMath1254.68215arXiv0706.1317WikidataQ48872888 ScholiaQ48872888MaRDI QIDQ1932118

Jun Tani, Jun Namikawa

Publication date: 17 January 2013

Published in: Neural Networks (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/0706.1317

zbMATH Keywords

maximum likelihood estimation; recurrent neural network; mixture of experts; self-organization; segmentation of temporal sequences

Mathematics Subject Classification ID

68T05: Learning and adaptive systems in artificial intelligence

65C40: Numerical analysis or methods applied to Markov chains

Related Items

Learning to imitate stochastic time series in a compositional way by chaos

Uses Software

• LSTM

Cites Work

• Unnamed Item
• Dynamical networks in function dynamics
• Functional dynamics. I: Articulation process
• Learning to imitate stochastic time series in a compositional way by chaos
• Learning Nonregular Languages: A Comparison of Simple Recurrent Networks and LSTM
• Recurrent Neural Networks with Small Weights Implement Definite Memory Machines
• Dynamics and computation in functional shifts
• Chaotic itinerancy
• Functional dynamics. II: Syntactic structure