A Neural Model of Memory Impairment in Diffuse Cerebral Atrophy

1995 ◽  
Vol 166 (1) ◽  
pp. 19-28 ◽  
Author(s):  
Eytan Ruppin ◽  
James A. Reggia
Keyword(s):  
Neural Network ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Memory Impairment ◽  
Clinical Manifestations ◽  
Cerebral Atrophy ◽  
Network Models ◽  
Neural Model ◽  
Neural Models ◽  
Neural Network Models

BackgroundComputer-supported neural network models have been subjected to diffuse, progressive deletion of synapses/neurons, to show that modelling cerebral neuropathological changes can predict the pattern of memory degradation in diffuse degenerative processes such as Alzheimer's disease. However, it has been suggested that neural models cannot account for more detailed aspects of memory impairment, such as the relative sparing of remote versus recent memories.MethodThe latter claim is examined from a computational perspective, using a neural associative memory model.ResultsThe neural network model not only demonstrates progressive memory deterioration as diffuse network damage occurs, but also exhibits differential sparing of remote versus recent memories.ConclusionsOur results show that neural models can account for a large variety of experimental phenomena characterising memory degradation in Alzheimer's patients. Specific testable predictions are generated concerning the relation between the neuroanatomical findings and the clinical manifestations of Alzheimer's disease.

scholarly journals Towards Enhanced Performance of Neural-Network-Based Fault Detection Using an Sequential D-Optimum Experimental Design

2018 ◽  
Vol 8 (8) ◽  
pp. 1290 ◽  
Author(s):  
Beata Mrugalska
Keyword(s):  
Neural Network ◽  
Experimental Design ◽  
Fault Detection ◽  
Network Models ◽  
Neural Model ◽  
Neural Network Models ◽  
Optimum Experimental Design ◽  
The Neural Network ◽  
Adaptive Thresholds ◽  
Linear Neural Network

Increasing expectations of industrial system reliability require development of more effective and robust fault diagnosis methods. The paper presents a framework for quality improvement on the neural model applied for fault detection purposes. In particular, the proposed approach starts with an adaptation of the modified quasi-outer-bounding algorithm towards non-linear neural network models. Subsequently, its convergence is proven using quadratic boundedness paradigm. The obtained algorithm is then equipped with the sequential D-optimum experimental design mechanism allowing gradual reduction of the neural model uncertainty. Finally, an emerging robust fault detection framework on the basis of the neural network uncertainty description as the adaptive thresholds is proposed.

Criteria for comparing artificial intelligence systems

2021 ◽  
pp. 21-27
Author(s):  
В.А. Пятакович ◽  
В.Ф. Рычкова ◽  
Н.Г. Левченко
Keyword(s):  
Neural Network ◽  
Network Models ◽  
Neural Model ◽  
Neural Network Models ◽  
Actual Problem ◽  
Neuro Fuzzy ◽  
Classification Of Images ◽  
Fuzzy Network ◽  
First Time

Модели нейронных и нейро-нечетких сетевых критериев сравнения в задачах диагностики и классификации образов. Предложен комплекс критериев для оценки свойств искусственных нейронных и нейро-нечетких сетей. Он включает в себя критерии разнообразия, подгонки, эластичности, равнозначности, устойчивости к шуму, аварийной ситуации, а также заданную монотонность для построения нейронной модели. Применение предложенных критериев на практике позволяет автоматизировать процесс построения, анализа и сравнения нейронных моделей для решения задач диагностики и классификации паттернов. Предложено решение задачи повышения эффективности параметрического синтеза нейросетевых моделей сложных систем для обоснованного принятия решений о классификации подводных целей. Научная новизна работы заключается в том, что впервые предложен комплекс моделей критериев, характеризующих такие свойства нейронных и нейро-нечетких сетей как разнообразие, переобученность, эластичность, эквифинальность, устойчивость к шуму, эмерджентность, что позволяет автоматизировать решение задачи анализа свойств и сравнения нейросетевых и нейро-нечетких моделей при решении задач диагностики и классификации образов. В работе решена актуальная задача автоматизации анализа свойств и сравнения нейросетевых моделей. Models of neural and neuro-fuzzy network comparison criterions in the tasks of diagnostics and pattern classification. The complex of criterions for an estimation of properties artificial neural and neuro-fuzzy networks is proposed. It includes criterions of variety, overfitting, elasticity, equifinality, stability to a noise, emergency, and also set monotonicity for a neural model construction. The application of offered criterions in practice allows to automatize the process of a construction, analysis and comparison of neural models for problem solving of diagnostics and patternt classification. The solution of the problem of increasing the efficiency of parametric synthesis of neural network models of complex systems for informed decision-making on the classification of underwater targets is proposed. The scientific novelty of the work lies in the fact that for the first time a set of models of criteria characterizing such properties of neural and neuro-fuzzy networks as diversity, retraining, elasticity, equifinality, noise resistance, emergence is proposed, which allows automating the solution of the problem of analyzing the properties and comparing neural network and neuro-fuzzy models when solving problems of diagnostics and classification of images. The paper solves the actual problem of automating the analysis of properties and comparison of neural network models.

scholarly journals Development of a Matlab(R) Toolbox for the Design of Grey-Box Neural Models

2006 ◽  
Vol 1 (2) ◽  
pp. 7 ◽  
Author(s):  
Gonzalo Acuña ◽  
Erika Pinto
Keyword(s):  
Neural Network ◽  
Gaussian Noise ◽  
Network Models ◽  
Neural Models ◽  
Neural Network Models ◽  
Matlab Toolbox ◽  
Validation Data ◽  
Stirred Reactor ◽  
One Step ◽  
Design Construction

A Matlab Toolbox is developed for the design, construction and validation of grey-box neural network models. This toolbox, available in www.diinf.usach.cl=gacuna has been tested in simulations with a continuously stirred reactor process. The grey-box model performs well for validation data with 5% additive gaussian noise for one-step-ahead (OSA) and model-predictive-output (MPO) estimations.

Gated Hierarchical LSTMs for Target-Based Sentiment Analysis

2018 ◽  
Vol 28 (11n12) ◽  
pp. 1719-1737
Author(s):  
Hao Wang ◽  
Xiaofang Zhang ◽  
Bin Liang ◽  
Qian Zhou ◽  
Baowen Xu
Keyword(s):  
Neural Network ◽  
Sentiment Analysis ◽  
Short Term Memory ◽  
Network Models ◽  
Neural Model ◽  
Attention Mechanism ◽  
Support Vector ◽  
Neural Network Models ◽  
Long Distance ◽  
Sentence Level

In the field of target-based sentiment analysis, the deep neural model combining attention mechanism is a remarkable success. In current research, it is commonly seen that attention mechanism is combined with Long Short-Term Memory (LSTM) networks. However, such neural network-based architectures generally rely on complex computation and only focus on single target. In this paper, we propose a gated hierarchical LSTM (GH-LSTMs) model which combines regional LSTM and sentence-level LSTM via a gated operation for the task of target-based sentiment analysis. This approach can distinguish different polarities of sentiment of different targets in the same sentence through a regional LSTM. Furthermore, it is able to concentrate on the long-distance dependency of target in the whole sentence via a sentence-level LSTM. The final results of our experiments on multi-domain datasets of two languages from SemEval 2016 indicate that our approach yields better performance than Support Vector Machine (SVM) and several typical neural network models. A case study of some typical examples also makes a supplement to this conclusion.

scholarly journals FEEDFORWARD NEURAL NETWORKS AND THE FORECASTING OF MULTI-SECTIONAL DEMAND FOR TELECOM SERVICES: A COMPARATIVE STUDY OF EFFECTIVENESS FOR HOURLY DATA

2020 ◽  
Vol 19 (3) ◽  
pp. 13-25
Author(s):  
Paweł Kaczmarczyk
Keyword(s):  
Neural Network ◽  
Network Models ◽  
Feedforward Neural Networks ◽  
Neural Model ◽  
Feedforward Neural Network ◽  
Neural Network Models ◽  
Explanatory Variables ◽  
The Neural Network ◽  
Hourly Data ◽  
Short Term Forecasting

The presented research focuses on the construction of a model to effectively forecast demand for connection services – it is thus relevant to the Prediction System (PS) of telecom operators. The article contains results of comparative studies regarding the effectiveness of neural network models and regressive-neural (integrated) models, in terms of their short-term forecasting abilities for multi-sectional demand of telecom services. The feedforward neural network was used as the neural network model. A regressive-neural model was constructed by fusing the dichotomous linear regression of multi-sectional demand and the feedforward neural network that was used to model the residuals of the regression model (i.e. the residual variability). The response variable was the hourly counted seconds of outgoing calls within the framework of the selected operator network. The calls were analysed within: type of 24 hours (e.g. weekday/weekend), connection categories, and subscriber groups. For both compared models 35 explanatory variables were specified and used in the estimation process. The results show that the regressive-neural model is characterised by higher approximation and predictive capabilities than the non-integrated neural model.

scholarly journals Neural Models of Text Normalization for Speech Applications

2019 ◽  
Vol 45 (2) ◽  
pp. 293-337 ◽  
Author(s):  
Hao Zhang ◽  
Richard Sproat ◽  
Axel H. Ng ◽  
Felix Stahlberg ◽  
Xiaochang Peng ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Language Processing ◽  
Speech Synthesis ◽  
Network Models ◽  
Neural Models ◽  
Neural Network Models ◽  
Sentential Context ◽  
Finite State ◽  
Text Normalization

Machine learning, including neural network techniques, have been applied to virtually every domain in natural language processing. One problem that has been somewhat resistant to effective machine learning solutions is text normalization for speech applications such as text-to-speech synthesis (TTS). In this application, one must decide, for example, that 123 is verbalized as one hundred twenty three in 123 pages but as one twenty three in 123 King Ave. For this task, state-of-the-art industrial systems depend heavily on hand-written language-specific grammars. We propose neural network models that treat text normalization for TTS as a sequence-to-sequence problem, in which the input is a text token in context, and the output is the verbalization of that token. We find that the most effective model, in accuracy and efficiency, is one where the sentential context is computed once and the results of that computation are combined with the computation of each token in sequence to compute the verbalization. This model allows for a great deal of flexibility in terms of representing the context, and also allows us to integrate tagging and segmentation into the process. These models perform very well overall, but occasionally they will predict wildly inappropriate verbalizations, such as reading 3 cm as three kilometers. Although rare, such verbalizations are a major issue for TTS applications. We thus use finite-state covering grammars to guide the neural models, either during training and decoding, or just during decoding, away from such “unrecoverable” errors. Such grammars can largely be learned from data.

scholarly journals Devizaárfolyam előrejelzés neurális háló modell segítségével = Foreign Exchange Rate Forecast Using Neural Network

2021 ◽  
Vol 16 (1) ◽  
pp. 117-137
Author(s):  
Zsolt Lakatos
Keyword(s):  
Neural Network ◽  
Network Models ◽  
Foreign Exchange Rate ◽  
Neural Models ◽  
Short Term ◽  
Neural Network Models ◽  
Technical Indicators ◽  
The Neural Network ◽  
Master's Thesis ◽  
Technical Indicator

Modelljeimben a technikai indikátorok használatát kapcsolom össze a neurális hálós modellek előrejelző képességeivel. A technikai indikátorok használata mellett szól, hogy rövid távon a pénzügyi idősorok autokorreláltak, a neurális modellek pedig nemlineáris kapcsolatok modellezésére alkalmasak. A kapott eredmények révén azt a következtetést vontam le, hogy ugyan a neurális háló modellek optimalizációs képessége nagyon jó és alkalmazásukkal a megfelelő technikai indikátorok is meghatározhatók, de csak lassan képesek rátanulni az adatokra, így még a legkisebb tranzakciós költség alkalmazása mellett is csak a kezdeti befektetésünk elvesztését tudjuk halogatni. My present paper is the shortened version of my master's thesis in finance presented in November 2015, in which I presented the results of the research implemented in the Training Center for Bankers. In my models I combine the use of technical indicators with predictive capabilities of neural network models. The use of a technical indicator suggests that in the short term the financial timeseries are autocorrelated, and neural models are suitable for modeling nonlinear relationships. Based on the results I concluded that although the optimization capabilities of the neural network models are very good and their application can be determined by the appropriate technical indicators, but learning from timeseries data takes too much time, so even with the smallest transaction cost we can only delay the loss of our initial investment.

Sign in / Sign up

Export Citation Format

Share Document