[go: up one dir, main page]

Bengio et al., 1992 - Google Patents

Learning the dynamic nature of speech with back-propagation for sequences

Bengio et al., 1992

Document ID
7433189786861186310
Author
Bengio Y
De Mori R
Gori M
Publication year
Publication venue
Pattern recognition letters

External Links

Snippet

A novel learning algorithm is proposed, called Back-Propagation for Sequences (BPS), for a particular class of dynamic neural networks in which some units have local feedback. These networks can be trained to respond to sequences of input patterns and seem particularly …
Continue reading at www.sciencedirect.com (other versions)

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computer systems based on biological models
    • G06N3/02—Computer systems based on biological models using neural network models
    • G06N3/08—Learning methods
    • G06N3/082—Learning methods modifying the architecture, e.g. adding or deleting nodes or connections, pruning
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computer systems based on biological models
    • G06N3/02—Computer systems based on biological models using neural network models
    • G06N3/04—Architectures, e.g. interconnection topology
    • G06N3/049—Temporal neural nets, e.g. delay elements, oscillating neurons, pulsed inputs
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computer systems based on biological models
    • G06N3/02—Computer systems based on biological models using neural network models
    • G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
    • G06N3/063—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computer systems based on biological models
    • G06N3/02—Computer systems based on biological models using neural network models
    • G06N3/04—Architectures, e.g. interconnection topology
    • G06N3/0454—Architectures, e.g. interconnection topology using a combination of multiple neural nets
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computer systems based on biological models
    • G06N3/02—Computer systems based on biological models using neural network models
    • G06N3/10—Simulation on general purpose computers
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06K—RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00—Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/62—Methods or arrangements for recognition using electronic means
    • G06K9/6217—Design or setup of recognition systems and techniques; Extraction of features in feature space; Clustering techniques; Blind source separation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06K—RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00—Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/62—Methods or arrangements for recognition using electronic means
    • G06K9/6267—Classification techniques
    • G06K9/6268—Classification techniques relating to the classification paradigm, e.g. parametric or non-parametric approaches
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06K—RECOGNITION OF DATA; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
    • G06K9/00—Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
    • G06K9/62—Methods or arrangements for recognition using electronic means
    • G06K9/6296—Graphical models, e.g. Bayesian networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N99/00—Subject matter not provided for in other groups of this subclass
    • G06N99/005—Learning machines, i.e. computer in which a programme is changed according to experience gained by the machine itself during a complete run

Similar Documents

Publication Publication Date Title
Hihi et al. Hierarchical recurrent neural networks for long-term dependencies
Bengio et al. Input-output HMMs for sequence processing
Choi et al. A tutorial on deep learning for music information retrieval
Pal et al. Multilayer perceptron, fuzzy sets, and classification
Waibel Modular construction of time-delay neural networks for speech recognition
Robinson et al. The utility driven dynamic error propagation network
Mori BPS: A learning algorithm for capturing the dynamic nature of speech
Bengio et al. Learning the dynamic nature of speech with back-propagation for sequences
Becker Unsupervised learning procedures for neural networks
US5150323A (en) Adaptive network for in-band signal separation
US5255348A (en) Neural network for learning, recognition and recall of pattern sequences
US5095443A (en) Plural neural network system having a successive approximation learning method
Stornetta et al. A dynamical approach to temporal pattern processing
EP0526504B1 (en) Artificial neural device
Bourlard et al. Speech dynamics and recurrent neural networks
KR20010002997A (en) A selective attention method using neural networks
Medhat et al. Automatic classification of music genre using masked conditional neural networks
Aleksander Neural systems engineering: towards a unified design discipline?
WO1991002323A1 (en) Adaptive network for classifying time-varying data
Boers et al. Evolving neural networks using the “Baldwin effect”
Rhodes et al. A scalable model of cerebellar adaptive timing and sequencing: The recurrent slide and latch (RSL) model
Bengio et al. Recurrent neural networks for adaptive temporal processing
Becker Learning temporally persistent hierarchical representations
Kumagai et al. Structured learning in recurrent neural network using genetic algorithm with internal copy operator
Gori et al. Temporal pattern recognition using EBPS