Melodic Expectation in Finnish Spiritual Folk Hymns: Convergence of Statistical, Behavioral, and Computational Approaches

1999 ◽  
Vol 17 (2) ◽  
pp. 151-195 ◽  
Author(s):  
Carol L. Krumhansl ◽  
Jukka Louhivuori ◽  
Petri Toiviainen ◽  
Topi Järvinen ◽  
Tuomas Eerola
Keyword(s):  
Network Models ◽  
Folk Songs ◽  
The Self ◽  
Behavioral Experiment ◽  
General Distribution ◽  
Style Analysis ◽  
Self Organizing Map ◽  
Neural Network Models ◽  
The Third ◽  
Melodic Expectation

This study of Finnish spiritual folk hymns combined three approaches to understanding melodic expectation. The first approach was a statistical style analysis of a representative corpus of 18 hymns, which determined the relative frequencies of tone onsets and two- and three-tone transitions. The second approach was a behavioral experiment in which listeners, either familiar (experts) or unfamiliar (nonexperts) with the hymns, made judgments about melodic continuations. The third approach simulated melodic expectation with neural network models of the self-organizing map (SOM) type (Kohonen, 1997). One model was trained on a corpus of Finnish folk songs and Lutheran hymns (Finnish SOM), while another was trained with the hymn contexts used in the experiment with the correct continuation tone (Hymn SOM). The three approaches converged on the following conclusions: (1) Listeners appear to be sensitive to the distributions of tones and tone transitions in music, (2) The nonexperts' responses more strongly reflected the general distribution of tones, whereas the experts' responses more strongly reflected the tone transitions and the correct continuations, (3) The SOMs produced results similar to listeners and also appeared sensitive to the distributions of tones and tone transitions, (4) The Hymn SOM correlated more strongly with the experts' judgments than the Finnish SOM, and (5) the principles of the implication-realization model (Narmour, 1990) were weighted similarly by the behavioral data and the Hymn SOM. /// Tässä suomalaisia hengellisiä kansansävelmiä käsittelevässä tutkimuksessa pyrittiin selvittämään melodisia odotuksia kolmen tutkimusmenetelmän avulla. Ensimmäinen menetelmä oli kyseistä tyyliä edustavien 18 sävelmän tilastollinen analyysi, jossa määritelteltiin sävelkorkeuksien sekä kahden ja kolmen sävelen siirtymien tilastolliset jakaumat. Toinen menetelmä oli behavioraalinen koe, jossa kuulijat arvioivat sävelmien jatkoja. Kuulijat jakaantuivat kahteen ryhmään: sävelmät tunteviin (asiantuntijoihin) ja sävelmiä tuntemattomiin (ei-asiantuntijoihin). Kolmannessa menetelmässä simuloitiin melodisia odotuksia itsejärjestäytyvään karttaan (Kohonen, 1997) perustuvalla keinotekoisella hermoverkkomallilla. Ensimmäiselle mallille opetettiin joukko suomalaisia kansanlauluja ja luterilaisia virsiä (suomalainen verkko), toiselle kokeessa käytettyjä hengellisiä kansansävelmiä (hengellinen verkko). Käytetyt menetelmät tuottivat yhteneviä tuloksia ja antoivat aihetta seuraaviin johtopäätöksiin: (1) kuulijat näyttävät olevan vastaanottavaisia musiikin säveljakaumille ja sävelsiirtymille, (2) ei-asiantuntijoiden vastaukset noudattivat enemmän sävelten yleistä jakaumaa, kun taas asiantuntijoiden vastaukset heijastivat enemmän sävelsiirtymiä ja sävelmien oikeita jatkoja, (3) hermoverkot tuottivat tuloksia, jotka olivat samankaltaisia kuulijoiden arvioiden kanssa ja jotka noudattivat sävelten ja sävelsiirtymien jakaumia, (4) hengellisen verkon tulokset korreloivat suomalaisen verkon tuloksia voimakkaammin asiantuntijoiden arvioiden kanssa, ja (5) behavioraaliset tulokset ja hengellinen verkko painottavat implikaatio-realisaatio-mallin (Narmour, 1990) periaatteita samalla tavalla.

Timbre Similarity: Convergence of Neural, Behavioral, and Computational Approaches

1998 ◽  
Vol 16 (2) ◽  
pp. 223-241 ◽  
Author(s):  
Petri Toiviainen ◽  
Mari Tervaniemi ◽  
Jukka Louhivuori ◽  
Marieke Saher ◽  
Minna Huotilainen ◽  
...  
Keyword(s):  
Brain Activity ◽  
Network Models ◽  
Large Set ◽  
Self Organizing Map ◽  
Neural Network Models ◽  
Behavioral Measures ◽  
Electrical Brain Activity ◽  
Behavioral Studies ◽  
Artificial Neurons ◽  
Self Organizing

The present study compared the degree of similarity of timbre representations as observed with brain recordings, behavioral studies, and computer simulations. To this end, the electrical brain activity of subjects was recorded while they were repetitively presented with five sounds differing in timbre. Subjects read simultaneously so that their attention was not focused on the sounds. The brain activity was quantified in terms of a change-specific mismatch negativity component. Thereafter, the subjects were asked to judge the similarity of all pairs along a five-step scale. A computer simulation was made by first training a Kohonen self-organizing map with a large set of instrumental sounds. The map was then tested with the experimental stimuli, and the distance between the most active artificial neurons was measured. The results of these methods were highly similar, suggesting that timbre representations reflected in behavioral measures correspond to neural activity, both as measured directly and as simulated in self-organizing neural network models.

Implementation of Neural Networks: Optical Architectures and Devices

1987 ◽  
Vol 109 ◽  
Author(s):  
Kevin J. Malloy ◽  
C. Lee Giles
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Network Models ◽  
The Self ◽  
Optical Systems ◽  
Neural Network Models ◽  
Electro Optic ◽  
Device Technology

ABSTRACTWe introduce neural networks as a new basis for computation. The role optics can play In implementing neural networks is discussed in terms of the requirements for optical systems and devices. A conclusion is drawn that the rapidly evolving knowledge of neural network models argues for a flexible and adaptable device technology. Such a technology is described using the self electro-optic effect device as an example.

31P MRS Data Analysis of Liver Cancer Based on Neural Networks

2010 ◽  
Vol 20-23 ◽  
pp. 630-635
Author(s):  
Qiang Liu ◽  
Ning Wang ◽  
Yi Hui Liu ◽  
Shao Qing Wang ◽  
Jin Yong Cheng ◽  
...  
Keyword(s):  
Neural Network ◽  
Liver Cancer ◽  
Back Propagation ◽  
Network Models ◽  
Resonance Spectroscopy ◽  
Self Organizing Map ◽  
Neural Network Models ◽  
31P Mrs ◽  
Hepatic Diseases

31P MRS(31Phosphorus Magnetic Resonance Spectroscopy) is a non invasive protocol for analyzing the energetic metabolism and biomedical changes in cellular level. Evaluation of 31P MRS is important in diagnosis and treatment of many hepatic diseases. In this paper, we apply back-propagation neural network (BP) and self-organizing map (SOM) neural network to analyze 31P MRS data to distinguish three diagnostic classes of cancer, normal and cirrhosis tissue. 66 samples of 31P MRS data are selected including cancer, normal and cirrhosis tissue. Four experiments are carried out. Good performance is achieved with limited samples. Experimental results prove that neural network models based on 31P MRS data offer an alternative and promising technique for diagnostic prediction of liver cancer in vivo.

Training Algorithms

2014 ◽  
pp. 68-84
Keyword(s):  
Back Propagation ◽  
Network Models ◽  
High Dimensional ◽  
Training Algorithms ◽  
Self Organizing Map ◽  
Neural Network Models ◽  
Supervised Training ◽  
Supervised And Unsupervised Learning ◽  
Unsupervised Training ◽  
Statistical Relationships

The process of assigning the weight to each connection is called training. A network can be subject to supervised or unsupervised training. In this chapter, supervised and unsupervised learning are explained and then various training algorithms such as multilayer perceptron (MLP) and Back Propagation (BP) as supervised training algorithms are introduced. The unsupervised training algorithm, namely Kohonen's self-organizing map (SOM), is introduced as one of most popular neural network models. SOMs convert high-dimensional, non-linear statistical relationships into simple geometric relationships in an n-dimensional array.

scholarly journals Detecting Signatures in Hyperspectral Image Data of Wounds: A Compound Model of Self- Organizing Map and Least Square Fitting

2018 ◽  
Vol 4 (1) ◽  
pp. 419-422
Author(s):  
Redwan Abdo A. Mohammed ◽  
Daniel Schäle ◽  
Christoph Hornberger ◽  
Steffen Emmert
Keyword(s):  
Neural Network ◽  
Hyperspectral Image ◽  
Image Data ◽  
Network Models ◽  
Least Square Method ◽  
Least Square ◽  
Self Organizing Map ◽  
Neural Network Models ◽  
Wound Tissue ◽  
Self Organizing

AbstractThe purpose of this study is to develop a method to discriminate spectral signatures in wound tissue. We have collected a training set of the intensity of the remitted light for different types of wound tissue from different patients using a TIVITA™ tissue camera. We used a neural network technique (self-organizing map) to group areas with the same spectral properties together. The results of this work indicates that neural network models are capable of finding clusters of closely related hyperspectral signatures in wound tissue, and thus can be used as a powerful tool to reach the anticipated classification. Moreover, we used a least square method to fit literature spectra (i.e. oxygenated haemoglobin (O2Hb), deoxygenated haemoglobin (HHb), water and fat) to the learned spectral classes. This procedure enables us to label each spectral class with the corresponding absorbance properties for the different absorbance of interest (i.e. O2Hb, HHb, water and fat). The calculated parameters of a testing set were consistent with the expected behaviour and show a good agreement with the results of a second algorithm which is used in the TIVITA™ tissue camera.

Optimized Robotic WAAM

2022 ◽  
pp. 114-137
Author(s):  
Aya Abd Alla Ramadan ◽  
Sherif Elatriby ◽  
Abd El Ghany ◽  
Azza Fathalla Barakat
Keyword(s):  
Base Alloy ◽  
Network Models ◽  
Optimization Techniques ◽  
Tension Stress ◽  
Neural Network Models ◽  
Cold Metal Transfer ◽  
The Third ◽  
Third Stage ◽  
Cold Metal ◽  
Phd Thesis

This chapter summarizes a PhD thesis introducing a methodology for optimizing robotic MIG (metal inert gas) to perform WAAM (wire and arc additive manufacturing) without using machines equipped with CMT (cold metal transfer) technology. It tries to find the optimal MIG parameters to make WAAM using a welding robot feasible production technique capable of making functional products with proper mechanical properties. Some experiments were performed first to collect data. Then NN (neural network) models were created to simulate the MIG process. Then different optimization techniques were used to find the optimal parameters to be used for deposition. These results were practically tested, and the best one was selected to be used in the third stage. In the third stage, a block of metal was deposited. Then samples were cut from deposited blocks in two directions and tested for tension stress. These samples were successful. They showed behavior close to base alloy.

Generation of synthetic dielectric dispersion logs in organic-rich shale formations using neural-network models

Geophysics ◽  
2019 ◽  
Vol 84 (3) ◽  
pp. D117-D129 ◽  
Author(s):  
Jiabo He ◽  
Siddharth Misra
Keyword(s):  
Neural Network ◽  
Reservoir Characterization ◽  
Network Models ◽  
Dielectric Dispersion ◽  
Ann Model ◽  
Neural Network Models ◽  
Shale Formations ◽  
The Third ◽  
Predictive Method ◽  
Predictive Methods

Dielectric dispersion (DD) logs acquired in subsurface geologic formations generally are composed of conductivity ([Formula: see text]) and relative permittivity ([Formula: see text]) measurements at four discrete frequencies in the range of 10 MHz to 1 GHz. Acquisition of DD logs in subsurface formations is operationally challenging, and it requires a hard-to-deploy infrastructure. We developed three supervised neural-network-based predictive methods to process conventional, easy-to-acquire subsurface logs for generating the eight DD logs acquired at four frequencies. These predictive methods will improve reservoir characterization in the absence of a DD logging tool. The predictive methods are tested in three wells intersecting organic-rich shale formations of the Permian Basin and the Bakken Shale. The first method predicts the eight dispersion logs simultaneously using a single artificial neural network (ANN) model, whereas the second method simultaneously predicts the four conductivity dispersion logs using one ANN model, followed by simultaneous prediction of four permittivity dispersion logs using a second ANN model. The third method sequentially predicts the eight dispersion logs, one at a time using eight sequential ANN models, based on a predetermined ranking of the prediction accuracy for each of the eight DD logs when simultaneously generated. Considering that the conventional and DD logs are recorded more than 10,000 ft deep in the subsurface using logging tools that are run at different times in rugose boreholes for sensing the near-wellbore geologic formation, the data used in this predictive work is prone to noise and biases that tend to adversely affect the prediction performances of the proposed methods. In terms of normalized root-mean square error (Nrms error), the prediction performances of the second predictive method are 8.5% worse and 6.2% better for the conductivity and permittivity dispersion logs, respectively, as compared with those of the first predictive method. The third method has best prediction performance for permittivity dispersion logs, which is 0.089 in terms of the Nrms error.

Intrinsic Plasticity for Natural Competition in Koniocortex-Like Neural Networks

2016 ◽  
Vol 26 (05) ◽  
pp. 1650040 ◽  
Author(s):  
Francisco Javier Ropero Peláez ◽  
Mariana Antonia Aguiar-Furucho ◽  
Diego Andina
Keyword(s):  
Neural Network ◽  
Vector Quantization ◽  
Network Models ◽  
Activation Function ◽  
Inhibitory Interneurons ◽  
Neural Network Models ◽  
The Third ◽  
Initial Network ◽  
Sensory Cortices ◽  
Intrinsic Plasticity

In this paper, we use the neural property known as intrinsic plasticity to develop neural network models that resemble the koniocortex, the fourth layer of sensory cortices. These models evolved from a very basic two-layered neural network to a complex associative koniocortex network. In the initial network, intrinsic and synaptic plasticity govern the shifting of the activation function, and the modification of synaptic weights, respectively. In this first version, competition is forced, so that the most activated neuron is arbitrarily set to one and the others to zero, while in the second, competition occurs naturally due to inhibition between second layer neurons. In the third version of the network, whose architecture is similar to the koniocortex, competition also occurs naturally owing to the interplay between inhibitory interneurons and synaptic and intrinsic plasticity. A more complex associative neural network was developed based on this basic koniocortex-like neural network, capable of dealing with incomplete patterns and ideally suited to operating similarly to a learning vector quantization network. We also discuss the biological plausibility of the networks and their role in a more complex thalamocortical model.

scholarly journals Exploration of Chemical Space with Partial Labeled Noisy Student Self-Training for Improving Deep Learning Performance: Application to Drug Metabolism

2020 ◽  
Author(s):  
Yang Liu ◽  
Hansaim Lim ◽  
Lei Xie
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Drug Discovery ◽  
Network Model ◽  
Neural Network Model ◽  
Chemical Space ◽  
Network Models ◽  
The Self ◽  
Learning Performance ◽  
Neural Network Models

AbstractMotivationDrug discovery is time-consuming and costly. Machine learning, especially deep learning, shows a great potential in accelerating the drug discovery process and reducing its cost. A big challenge in developing robust and generalizable deep learning models for drug design is the lack of a large amount of data with high quality and balanced labels. To address this challenge, we developed a self-training method PLANS that exploits millions of unlabeled chemical compounds as well as partially labeled pharmacological data to improve the performance of neural network models.ResultWe evaluated the self-training with PLANS for Cytochrome P450 binding activity prediction task, and proved that our method could significantly improve the performance of the neural network model with a large margin. Compared with the baseline deep neural network model, the PLANS-trained neural network model improved accuracy, precision, recall, and F1 score by 13.4%, 12.5%, 8.3%, and 10.3%, respectively. The self-training with PLANS is model agnostic, and can be applied to any deep learning architectures. Thus, PLANS provides a general solution to utilize unlabeled and partially labeled data to improve the predictive modeling for drug discovery.AvailabilityThe code that implements PLANS is available at https://github.com/XieResearchGroup/PLANS

Sign in / Sign up

Export Citation Format

Share Document