Hierarchical linear dynamical systems for unsupervised musical note recognition

DOI10.1016/j.jfranklin.2017.04.013zbMath1395.94026OpenAlexW2606734503MaRDI QIDQ1661447

Goktug T. Cinar, Jose C. Principe, Pedro M. N. Sequeira

Publication date: 16 August 2018

Published in: Journal of the Franklin Institute (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.jfranklin.2017.04.013

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural biology (92C20) Neural networks for/in biological studies, artificial life and related topics (92B20) Pattern recognition, speech recognition (68T10) Image processing (compression, reconstruction, etc.) in information and communication theory (94A08)

Uses Software

• LSTM

Cites Work

• Unnamed Item
• Motion detection, noise reduction, texture suppression, and contour enhancement by spatiotemporal Gabor filters with surround inhibition
• A discriminative model for polyphonic piano transcription
• Natural image statistics. A probabilistic approach to early computational vision.
• Clustering of time series data -- a survey
• Learning Nonregular Languages: A Comparison of Simple Recurrent Networks and LSTM
• A new form of the extended Kalman filter for parameter estimation in linear systems with correlated noise
• Multifeature-Based Surround Inhibition Improves Contour Detection in Natural Images
• Neural networks and physical systems with emergent collective computational abilities.