Filters








440 Hits in 6.0 sec

Audio classification systems using deep neural networks and an event-driven auditory sensor

Enea Ceolini, Ilya Kiselev, Shih-Chii Liu
2019 2019 IEEE SENSORS  
We describe ongoing research in developing audio classification systems that use a spiking silicon cochlea as the front end.  ...  Abstract-We describe ongoing research in developing audio classification systems that use a spiking silicon cochlea as the front end.  ...  We investigate 3 architectures, namely a multilayer perceptron (MLP), a convolutional neural network (CNN), and a recurrent neural network (RNN) with a CNN front end.  ... 
doi:10.1109/sensors43011.2019.8956592 fatcat:awz4gsx43rar5kbchn6tgf4kg4

A neurally inspired musical instrument classification system based upon the sound onset

Michael J. Newton, Leslie S. Smith
2012 Journal of the Acoustical Society of America  
Classification uses a time-domain neural network, the echo state network.  ...  A gammatone filterbank and spiking onset detectors, built from dynamic synapses and leaky integrate-and-fire neurons, create parallel spike trains that emphasize the sound onset.  ...  ACKNOWLEDGMENTS The authors thank Herbert Jaeger and Kevin Swingler for useful discussions about the classifier configurations and the two anonymous reviewers for helpful comments about an earlier version  ... 
doi:10.1121/1.4707535 pmid:22712950 fatcat:vuerf23m4bcjvbscb4cb2gh3ci

Wavelets in Recognition of Bird Sounds

Arja Selin, Jari Turunen, Juha T. Tanttu
2006 EURASIP Journal on Advances in Signal Processing  
The results were encouraging: the SOM network recognized 78% and the MLP network 96% of the test sounds correctly.  ...  The recognition algorithm consists of feature extraction using wavelet decomposition and recognition using either supervised or unsupervised classifier.  ...  The authors would like to thank Pertti Kalinainen, Ilkka Heiskanen, and Jan-Erik Bruun for their recordings and Docent Mikko Ojanen for his helpful comments on biological issues.  ... 
doi:10.1155/2007/51806 fatcat:manhsisw6jdjxombfrsmfjunye

Real-Time Recognition Of Dynamic Hand Postures On A Neuromorphic System

Qian Liu, Steve Furber
2015 Zenodo  
Inspired by the behaviours of the primary visual cortex, Convolutional Neural Networks (CNNs) are modelled using both linear perceptrons and spiking Leaky Integrate-and-Fire (LIF) neurons.  ...  ) silicon retina in concert with the SpiNNaker real-time Spiking Neural Network (SNN) simulator.  ...  Using the approch of HMMs [32] and applying to spiking neural networks is an idea we wish to explore as part of this promising work.  ... 
doi:10.5281/zenodo.1107242 fatcat:6pqvr7bk5venpn7h2rngqdryhq

Feature Extraction and Connectionist Classification of SODAR Echograms

S. Choudhury, S. Mitra
2006 IEEE Geoscience and Remote Sensing Letters  
Index Terms-Acoustic remote sensing, classification, fast Fourier transform (FFT), neural networks, sonic detection and ranging (SODAR) identification.  ...  The lower atmospheric patterns (each depicting a different atmospheric condition) recorded by this system can prove to be extremely useful if classified and interpreted correctly.  ...  Artificial neural networks (ANNs) or connectionist models [4] attempt to replicate the computational power of biological neural networks and, thereby, endow machines with some of the cognitive abilities  ... 
doi:10.1109/lgrs.2005.854200 fatcat:6efu4jgbnngntpwzkrmkdbdedq

Enhanced Robot Speech Recognition Using Biomimetic Binaural Sound Source Localization

Jorge Davila-Chacon, Jindong Liu, Stefan Wermter
2018 IEEE Transactions on Neural Networks and Learning Systems  
First, a spiking neural network inspired by the midbrain auditory system based on our previous work is applied to calculate the sound signal angle.  ...  Then, a feedforward neural network is used to handle high levels of ego noise and reverberation in the signal. Finally, the sound signal is fed into an ASR system.  ...  Finally, we use a feedforward neural network in the last layer of our SSL system for the classification of S I C .  ... 
doi:10.1109/tnnls.2018.2830119 pmid:29993561 fatcat:wpyurosalfgs5aec5titoklkbq

Annotated bibliographies in combinatorial optimization

1998 Computers and Mathematics with Applications  
A mean field algorithm for Bayes learning in large feed-forward neural networks (Manfred Opper and Ole Winther). Removing noise in on-line search using adaptive  ...  Neural models for part-whole hierarchies (Maximilian Riesenhuber and Peter Dayan). II. Neuroscience. Temporal low-order statistics of natural sounds (H. Attias and C.E. Schreiner).  ... 
doi:10.1016/s0898-1221(98)90497-7 fatcat:t45peagjhjctfg7vne5zqrxtne

Interior point algorithms: Theory and analysis

1998 Computers and Mathematics with Applications  
A mean field algorithm for Bayes learning in large feed-forward neural networks (Manfred Opper and Ole Winther). Removing noise in on-line search using adaptive  ...  Neural models for part-whole hierarchies (Maximilian Riesenhuber and Peter Dayan). II. Neuroscience. Temporal low-order statistics of natural sounds (H. Attias and C.E. Schreiner).  ... 
doi:10.1016/s0898-1221(98)90495-3 fatcat:22z6xhizjvhtxi22rigsfnopcq

A Spiking Neural Network Framework for Robust Sound Classification

Jibin Wu, Yansong Chua, Malu Zhang, Haizhou Li, Kay Chen Tan
2018 Frontiers in Neuroscience  
This framework uses the unsupervised self-organizing map (SOM) for representing frequency contents embedded within the acoustic signals, followed by an event-based spiking neural network (SNN) for spatiotemporal  ...  With the advancement of deep learning models and the abundance of training data, the performance of automatic sound classification (ASC) systems has improved significantly in recent years.  ...  Spiking neural network (SNN) is one such class of neural networks motivated by event-based computation.  ... 
doi:10.3389/fnins.2018.00836 pmid:30510500 pmcid:PMC6252336 fatcat:ewolau63gnhsjgo4wvnuno77ha

Understanding a Deep Learning Technique through a Neuromorphic System a Case Study with SpiNNaker Neuromorphic Platform

Indar Sugiarto, Felix Pasila, R.H. Setyobudi, E. Alasaarela, F. Pasila, G. Chan, S.-G. Lee
2018 MATEC Web of Conferences  
Some DL architectures such as deep neural networks, deep belief networks and recurrent neural networks have been developed and applied to many fields with incredible results, even comparable to human intelligence  ...  In this paper, a neuromorphic platform called SpiNNaker is described and evaluated in order to understand its potential use as a platform for a deep learning approach.  ...  The authors would like to thank the Institute of Research and Community Development, Petra Christian University, Indonesia, for supporting our work through the project grant 02/LPPM/V/2017.  ... 
doi:10.1051/matecconf/201816401015 fatcat:yenldx2mrrdzhhpcipuntbhl5y

EEG Classification with BSA Spike Encoding Algorithm and Evolving Probabilistic Spiking Neural Network [chapter]

Nuttapod Nuntalid, Kshitij Dhoble, Nikola Kasabov
2011 Lecture Notes in Computer Science  
A novel evolving probabilistic spiking neural network reservoir (epSNNr) architecture is used for the purpose of learning and classifying the EEG signals after the BSA transformation.  ...  This study investigates the feasibility of Bens Spike Algorithm (BSA) to encode continuous EEG spatio-temporal data into input spike streams for a classification in a spiking neural network classifier.  ...  Acknowledgment The EEG data used in the experiments were collected in the RIKEN Brain Science Institute, Tokyo by a team lead by Case van Leuven and Andrjei Chihotsky.  ... 
doi:10.1007/978-3-642-24955-6_54 fatcat:zq3klrds2jcn3ampra37jlfeza

Improving Humanoid Robot Speech Recognition with Sound Source Localisation [chapter]

Jorge Dávila-Chacón, Johannes Twiefel, Jindong Liu, Stefan Wermter
2014 Lecture Notes in Computer Science  
The robot tracks a speaker with a binaural sound source localisation system (SSL) that uses spiking neural networks to model relevant areas in the mammalian auditory pathway for SSL.  ...  The accuracy of speech recognition is doubled when the robot orients towards the speaker in an optimal angle and listens only through one ear instead of averaging the input from both ears.  ...  This work was supported by the DFG German Research Foundation (grant #1247) -International Research Training Group CINACS (Cross-modal Interaction in Natural and Artificial Cognitive Systems).  ... 
doi:10.1007/978-3-319-11179-7_78 fatcat:tziohskdlzctzihmgbk7iysfk4

Emerging Memristive Devices for Brain-Inspired Computing and Artificial Perception

Jingyu Wang, Ying Zhu, Li Zhu, Chunsheng Chen, Qing Wan
2022 Frontiers in Nanotechnology  
neural networks.  ...  We believe that the advances and challenges will lead to significant advancements in artificial neural networks and intelligent humanoid robots.  ...  Wang et al. proposed a brain-like computing method using memristors (Wang W. et al., 2018) , they use the 1T1R structure combined with a spiking neural network for learning and recognition, the time difference  ... 
doi:10.3389/fnano.2022.940825 fatcat:3bgs2pczh5e3louvrpb3vl6vhi

Evolving spiking neural networks for spatio-and spectro-temporal pattern recognition

Nikola Kasabov
2012 2012 6th IEEE INTERNATIONAL CONFERENCE INTELLIGENT SYSTEMS  
This paper provides a survey on the evolution of the evolving connectionist systems (ECOS) paradigm, from simple ECOS introduced in 1998 to evolving spiking neural networks (eSNN) and neurogenetic systems  ...  Abstract This paper provides a survey on the evolution of the evolving connectionist systems (ECOS) paradigm, from simple ECOS introduced in 1998 to evolving spiking neural networks (eSNN) and neurogenetic  ...  Evolving Spiking Neural Networks for Spatioand Spectro-Temporal Pattern Recognition Evolving Spiking Neural Networks Based on the ECOS principles, an evolving spiking neural network architecture (eSNN  ... 
doi:10.1109/is.2012.6335110 dblp:conf/is/Kasabov12 fatcat:5qa7yzkkjbdc7gy3grz32a4beu

A Connectionist Approach to SODAR Pattern Classification

S. Choudhury, S. Mitra
2004 IEEE Geoscience and Remote Sensing Letters  
The observations obtained by these systems can prove to be extremely useful if classified and interpreted correctly.  ...  SODAR (or acoustic radar) systems are a useful tool to efficiently probe the lower planetary boundary layer (LPBL).  ...  MLPs have also been recently applied in this domain of atmospheric sciences. Neural-network-based techniques have been used in the prediction of tornado and damaging wind conditions [17] , [18] .  ... 
doi:10.1109/lgrs.2003.822309 fatcat:u2r527w3rjhwvfjofosjsnbd64
« Previous Showing results 1 — 15 out of 440 results