scholarly journals Tinnitus-like “hallucinations” elicited by sensory deprivation in an entropy maximization recurrent neural network

2021 ◽  
Author(s):  
Aviv Dotan ◽  
Oren Shriki
Keyword(s):  
Neural Network ◽  
Hearing Loss ◽  
Auditory Processing ◽  
Computational Models ◽  
Learning Algorithm ◽  
Sensory Deprivation ◽  
Network Activity ◽  
External Stimulation ◽  
Output Layer ◽  
Auditory Responses

AbstractSensory deprivation has long been known to cause hallucinations or “phantom” sensations, the most common of which is tinnitus induced by hearing loss, affecting 10–20% of the population. An observable hearing loss, causing auditory sensory deprivation over a band of frequencies, is present in over 90% of people with tinnitus. Existing plasticity-based computational models for tinnitus are usually driven by homeostasis mechanisms, modeled to fit phenomenological findings. Here, we use an objective-driven learning algorithm to model an early auditory processing neuronal network, e.g., in the dorsal cochlear nucleus. The learning algorithm maximizes the network’s output entropy by learning the feed-forward and recurrent interactions in the model. We show that the connectivity patterns and responses learned by the model display several hallmarks of early auditory neuronal networks. We further demonstrate that attenuation of peripheral inputs drives the recurrent network towards its critical point and transition into a tinnitus-like state. In this state, the network activity resembles responses to genuine inputs even in the absence of external stimulation, namely, it “hallucinates” auditory responses. These findings demonstrate how objective-driven plasticity mechanisms that normally act to optimize the network’s input representation can also elicit pathologies such as tinnitus as a result of sensory deprivation.Author summaryTinnitus or “ringing in the ears” is a common pathology. It may result from mechanical damage in the inner ear, as well as from certain drugs such as salicylate (aspirin). A common approach toward a computational model for tinnitus is to use a neural network model with inherent plasticity applied to early auditory processing, where the input layer models the auditory nerve and the output layer models a nucleus in the brain stem. However, most of the existing computational models are phenomenological in nature, driven by a homeostatic principle. Here, we use an objective-driven learning algorithm based on information theory to learn the feed-forward interactions between the layers, as well as the recurrent interactions within the output layer. Through numerical simulations of the learning process, we show that attenuation of peripheral inputs drives the network into a tinnitus-like state, where the network activity resembles responses to genuine inputs even in the absence of external stimulation; namely, it “hallucinates” auditory responses. These findings demonstrate how plasticity mechanisms that normally act to optimize network performance can also lead to undesired outcomes, such as tinnitus, as a result of reduced peripheral hearing.

scholarly journals Tinnitus-like “hallucinations” elicited by sensory deprivation in an entropy maximization recurrent neural network

2021 ◽  
Vol 17 (12) ◽  
pp. e1008664
Author(s):  
Aviv Dotan ◽  
Oren Shriki
Keyword(s):  
Hearing Loss ◽  
Auditory Processing ◽  
Computational Models ◽  
Learning Algorithm ◽  
Sensory Deprivation ◽  
Recurrent Network ◽  
Dorsal Cochlear Nucleus ◽  
Network Activity ◽  
External Stimulation ◽  
Entropy Maximization

Sensory deprivation has long been known to cause hallucinations or “phantom” sensations, the most common of which is tinnitus induced by hearing loss, affecting 10–20% of the population. An observable hearing loss, causing auditory sensory deprivation over a band of frequencies, is present in over 90% of people with tinnitus. Existing plasticity-based computational models for tinnitus are usually driven by homeostatic mechanisms, modeled to fit phenomenological findings. Here, we use an objective-driven learning algorithm to model an early auditory processing neuronal network, e.g., in the dorsal cochlear nucleus. The learning algorithm maximizes the network’s output entropy by learning the feed-forward and recurrent interactions in the model. We show that the connectivity patterns and responses learned by the model display several hallmarks of early auditory neuronal networks. We further demonstrate that attenuation of peripheral inputs drives the recurrent network towards its critical point and transition into a tinnitus-like state. In this state, the network activity resembles responses to genuine inputs even in the absence of external stimulation, namely, it “hallucinates” auditory responses. These findings demonstrate how objective-driven plasticity mechanisms that normally act to optimize the network’s input representation can also elicit pathologies such as tinnitus as a result of sensory deprivation.

scholarly journals Prediction of Flight Status of Logistics UAVs Based on an Information Entropy Radial Basis Function Neural Network

Sensors ◽  
2021 ◽  
Vol 21 (11) ◽  
pp. 3651
Author(s):  
Qin Yang ◽  
Zhaofa Ye ◽  
Xuzheng Li ◽  
Daozhu Wei ◽  
Shunhua Chen ◽  
...  
Keyword(s):  
Neural Network ◽  
Radial Basis Function ◽  
Network Structure ◽  
Information Entropy ◽  
Basis Function ◽  
Learning Algorithm ◽  
Rbf Neural Network ◽  
Output Layer ◽  
Radial Basis ◽  
Hidden Layer

Aiming at addressing the problems of short battery life, low payload and unmeasured load ratio of logistics Unmanned Aerial Vehicles (UAVs), the Radial Basis Function (RBF) neural network was trained with the flight data of logistics UAV from the Internet of Things to predict the flight status of logistics UAVs. Under the condition that there are few available input samples and the convergence of RBF neural network is not accurate, a dynamic adjustment method of RBF neural network structure based on information entropy is proposed. This method calculates the information entropy of hidden layer neurons and output layer neurons, and quantifies the output information of hidden layer neurons and the interaction information between hidden layer neurons and output layer neurons. The structural design and optimization of RBF neural network were solved by increasing the hidden layer neurons or disconnecting unnecessary connections, according to the connection strength between neurons. The steepest descent learning algorithm was used to correct the parameters of the network structure to ensure the convergence accuracy of the RBF neural network. By predicting the regression values of the flight status of logistics UAVs, it is demonstrated that the information entropy-based RBF neural network proposed in this paper has good approximation ability for the prediction of nonlinear systems.

scholarly journals Speech-evoked Brainstem Auditory Responses and Auditory Processing Skills: A Correlation in Adults with Hearing Loss

2017 ◽  
Vol 22 (01) ◽  
pp. 038-044 ◽  
Author(s):  
Taissane Sanguebuche ◽  
Bruna Peixe ◽  
Rúbia Bruno ◽  
Eliara Biaggio ◽  
Michele Garcia
Keyword(s):  
Hearing Loss ◽  
Auditory Processing ◽  
Auditory Pathway ◽  
Gap Detection ◽  
Behavioral Tests ◽  
Behavioral Skills ◽  
Auditory Responses ◽  
Level Difference ◽  
Masking Level Difference ◽  
Brainstem Response

Introduction The auditory system consists of sensory structures and central connections. The evaluation of the auditory pathway at a central level can be performed through behavioral and electrophysiological tests, because they are complementary to each other and provide important information about comprehension. Objective To correlate the findings of speech brainstem-evoked response audiometry with the behavioral tests Random Gap Detection Test and Masking Level Difference in adults with hearing loss. Methods All patients were submitted to a basic audiological evaluation, to the aforementioned behavioral tests, and to an electrophysiological assessment, by means of click-evoked and speech-evoked brainstem response audiometry. Results There were no statistically significant values among the electrophysiological test and the behavioral tests. However, there was a significant correlation between the V and A waves, as well as the D and F waves, of the speech-evoked brainstem response audiometry peaks. Such correlations are positive, indicating that the increase of a variable implies an increase in another and vice versa. Conclusion It was possible to correlate the findings of the speech-evoked brainstem response audiometry with those of the behavioral tests Random Gap Detection and Masking Level Difference. However, there was no statistically significant correlation between them. This shows that the electrophysiological evaluation does not depend uniquely on the behavioral skills of temporal resolution and selective attention.

A New Backpropagation Learning Algorithm for Layered Neural Networks with Nondifferentiable Units

2007 ◽  
Vol 19 (5) ◽  
pp. 1422-1435 ◽  
Author(s):  
Takahumi Oohori ◽  
Hidenori Naganuma ◽  
Kazuhisa Watanabe
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
High Performance ◽  
Large Scale ◽  
Learning Algorithm ◽  
Backpropagation Algorithm ◽  
Digital Version ◽  
Output Layer ◽  
Simulation Results ◽  
Large Scale Networks

We propose a digital version of the backpropagation algorithm (DBP) for three-layered neural networks with nondifferentiable binary units. This approach feeds teacher signals to both the middle and output layers, whereas with a simple perceptron, they are given only to the output layer. The additional teacher signals enable the DBP to update the coupling weights not only between the middle and output layers but also between the input and middle layers. A neural network based on DBP learning is fast and easy to implement in hardware. Simulation results for several linearly nonseparable problems such as XOR demonstrate that the DBP performs favorably when compared to the conventional approaches. Furthermore, in large-scale networks, simulation results indicate that the DBP provides high performance.

Share Market Data Prediction Strategies using Deep Learning Algorithm

2019 ◽  
Vol 13 ◽  
Author(s):  
A John. ◽  
D. Praveen Dominic ◽  
M. Adimoolam ◽  
N. M. Balamurugan
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Stock Market ◽  
Predictive Analytics ◽  
Learning Algorithm ◽  
Market Price ◽  
Stochastic Gradient ◽  
Stochastic Gradient Descent ◽  
Mining Machine ◽  
Gradient Descent Algorithm

Background:: Predictive analytics has a multiplicity of statistical schemes from predictive modelling, data mining, machine learning. It scrutinizes present and chronological data to make predictions about expectations or if not unexplained measures. Most predictive models are used for business analytics to overcome loses and profit gaining. Predictive analytics is used to exploit the pattern in old and historical data. Objective: People used to follow some strategies for predicting stock value to invest in the more profit-gaining stocks and those strategies to search the stock market prices which are incorporated in some intelligent methods and tools. Such strategies will increase the investor’s profits and also minimize their risks. So prediction plays a vital role in stock market gaining and is also a very intricate and challenging process. Method: The proposed optimized strategies are the Deep Neural Network with Stochastic Gradient for stock prediction. The Neural Network is trained using Back-propagation neural networks algorithm and stochastic gradient descent algorithm as optimal strategies. Results: The experiment is conducted for stock market price prediction using python language with the visual package. In this experiment RELIANCE.NS, TATAMOTORS.NS, and TATAGLOBAL.NS dataset are taken as input dataset and it is downloaded from National Stock Exchange site. The artificial neural network component including Deep Learning model is most effective for more than 100,000 data points to train this model. This proposed model is developed on daily prices of stock market price to understand how to build model with better performance than existing national exchange method.

scholarly journals Early differences in auditory processing relate to Autism Spectrum Disorder traits in infants with Neurofibromatosis Type I

2021 ◽  
Vol 13 (1) ◽  
Author(s):  
Jannath Begum-Ali ◽  
◽  
Anna Kolesnik-Taylor ◽  
Isabel Quiroz ◽  
Luke Mason ◽  
...  
Keyword(s):  
Autism Spectrum Disorder ◽  
Auditory Processing ◽  
Neurofibromatosis Type ◽  
Autism Spectrum ◽  
Spectrum Disorder ◽  
Type I ◽  
Sensory Reactivity ◽  
Auditory Responses ◽  
Repetition Suppression ◽  
Age Related

Abstract Background Sensory modulation difficulties are common in children with conditions such as Autism Spectrum Disorder (ASD) and could contribute to other social and non-social symptoms. Positing a causal role for sensory processing differences requires observing atypical sensory reactivity prior to the emergence of other symptoms, which can be achieved through prospective studies. Methods In this longitudinal study, we examined auditory repetition suppression and change detection at 5 and 10 months in infants with and without Neurofibromatosis Type 1 (NF1), a condition associated with higher likelihood of developing ASD. Results In typically developing infants, suppression to vowel repetition and enhanced responses to vowel/pitch change decreased with age over posterior regions, becoming more frontally specific; age-related change was diminished in the NF1 group. Whilst both groups detected changes in vowel and pitch, the NF1 group were largely slower to show a differentiated neural response. Auditory responses did not relate to later language, but were related to later ASD traits. Conclusions These findings represent the first demonstration of atypical brain responses to sounds in infants with NF1 and suggest they may relate to the likelihood of later ASD.

scholarly journals Deep Learning Algorithm Trained with COVID-19 Pneumonia Also Identifies Immune Checkpoint Inhibitor Therapy-Related Pneumonitis

Cancers ◽  
2021 ◽  
Vol 13 (4) ◽  
pp. 652 ◽  
Author(s):  
Carlo Augusto Mallio ◽  
Andrea Napolitano ◽  
Gennaro Castiello ◽  
Francesco Maria Giordano ◽  
Pasquale D'Alessio ◽  
...  
Keyword(s):  
Neural Network ◽  
Computed Tomography ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Immune Checkpoint ◽  
Immune Checkpoint Inhibitor ◽  
Learning Algorithm ◽  
Checkpoint Inhibitor ◽  
Deep Convolutional Neural Network ◽  
Deep Learning Algorithm

Background: Coronavirus disease 2019 (COVID-19) pneumonia and immune checkpoint inhibitor (ICI) therapy-related pneumonitis share common features. The aim of this study was to determine on chest computed tomography (CT) images whether a deep convolutional neural network algorithm is able to solve the challenge of differential diagnosis between COVID-19 pneumonia and ICI therapy-related pneumonitis. Methods: We enrolled three groups: a pneumonia-free group (n = 30), a COVID-19 group (n = 34), and a group of patients with ICI therapy-related pneumonitis (n = 21). Computed tomography images were analyzed with an artificial intelligence (AI) algorithm based on a deep convolutional neural network structure. Statistical analysis included the Mann–Whitney U test (significance threshold at p < 0.05) and the receiver operating characteristic curve (ROC curve). Results: The algorithm showed low specificity in distinguishing COVID-19 from ICI therapy-related pneumonitis (sensitivity 97.1%, specificity 14.3%, area under the curve (AUC) = 0.62). ICI therapy-related pneumonitis was identified by the AI when compared to pneumonia-free controls (sensitivity = 85.7%, specificity 100%, AUC = 0.97). Conclusions: The deep learning algorithm is not able to distinguish between COVID-19 pneumonia and ICI therapy-related pneumonitis. Awareness must be increased among clinicians about imaging similarities between COVID-19 and ICI therapy-related pneumonitis. ICI therapy-related pneumonitis can be applied as a challenge population for cross-validation to test the robustness of AI models used to analyze interstitial pneumonias of variable etiology.

Sign in / Sign up

Export Citation Format

Share Document