scholarly journals A continuous-time neural model for sequential action

2014 ◽  
Vol 369 (1655) ◽  
pp. 20130623 ◽  
Author(s):  
George Kachergis ◽  
Dean Wyatte ◽  
Randall C. O'Reilly ◽  
Roy de Kleijn ◽  
Bernhard Hommel
Keyword(s):  
Continuous Time ◽  
Network Models ◽  
Neural Model ◽  
Learning Mechanisms ◽  
Neural Network Models ◽  
Continuous Processes ◽  
Sequential Action ◽  
Directed Learning ◽  
Bidirectional Associations ◽  
Task Representations

Action selection, planning and execution are continuous processes that evolve over time, responding to perceptual feedback as well as evolving top-down constraints. Existing models of routine sequential action (e.g. coffee- or pancake-making) generally fall into one of two classes: hierarchical models that include hand-built task representations, or heterarchical models that must learn to represent hierarchy via temporal context, but thus far lack goal-orientedness. We present a biologically motivated model of the latter class that, because it is situated in the Leabra neural architecture, affords an opportunity to include both unsupervised and goal-directed learning mechanisms. Moreover, we embed this neurocomputational model in the theoretical framework of the theory of event coding (TEC), which posits that actions and perceptions share a common representation with bidirectional associations between the two. Thus, in this view, not only does perception select actions (along with task context), but actions are also used to generate perceptions (i.e. intended effects). We propose a neural model that implements TEC to carry out sequential action control in hierarchically structured tasks such as coffee-making. Unlike traditional feedforward discrete-time neural network models, which use static percepts to generate static outputs, our biological model accepts continuous-time inputs and likewise generates non-stationary outputs, making short-timescale dynamic predictions.

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.

scholarly journals An emergentist perspective on the origin of number sense

2018 ◽  
Vol 373 (1740) ◽  
pp. 20170043 ◽  
Author(s):  
Marco Zorzi ◽  
Alberto Testolin
Keyword(s):  
Visual Cues ◽  
Number Sense ◽  
Network Models ◽  
Learning Mechanisms ◽  
Neural Network Models ◽  
Human Infants ◽  
Numerosity Discrimination ◽  
Domain Specific ◽  
Numerical Abilities ◽  
Dependent Learning

The finding that human infants and many other animal species are sensitive to numerical quantity has been widely interpreted as evidence for evolved, biologically determined numerical capacities across unrelated species, thereby supporting a ‘nativist’ stance on the origin of number sense. Here, we tackle this issue within the ‘emergentist’ perspective provided by artificial neural network models, and we build on computer simulations to discuss two different approaches to think about the innateness of number sense. The first, illustrated by artificial life simulations, shows that numerical abilities can be supported by domain-specific representations emerging from evolutionary pressure. The second assumes that numerical representations need not be genetically pre-determined but can emerge from the interplay between innate architectural constraints and domain-general learning mechanisms, instantiated in deep learning simulations. We show that deep neural networks endowed with basic visuospatial processing exhibit a remarkable performance in numerosity discrimination before any experience-dependent learning, whereas unsupervised sensory experience with visual sets leads to subsequent improvement of number acuity and reduces the influence of continuous visual cues. The emergent neuronal code for numbers in the model includes both numerosity-sensitive (summation coding) and numerosity-selective response profiles, closely mirroring those found in monkey intraparietal neurons. We conclude that a form of innatism based on architectural and learning biases is a fruitful approach to understanding the origin and development of number sense. This article is part of a discussion meeting issue ‘The origins of numerical abilities'.

scholarly journals Analyzing Malaria Disease Using Effective Deep Learning Approach

Diagnostics ◽  
2020 ◽  
Vol 10 (10) ◽  
pp. 744
Author(s):  
Krit Sriporn ◽  
Cheng-Fa Tsai ◽  
Chia-En Tsai ◽  
Paohsi Wang
Keyword(s):  
Diagnostic System ◽  
Network Models ◽  
Neural Model ◽  
Activation Function ◽  
Training Dataset ◽  
Neural Network Models ◽  
Recall Accuracy ◽  
Detection Approach ◽  
Computer Aided ◽  
Rotational Method

Medical tools used to bolster decision-making by medical specialists who offer malaria treatment include image processing equipment and a computer-aided diagnostic system. Malaria images can be employed to identify and detect malaria using these methods, in order to monitor the symptoms of malaria patients, although there may be atypical cases that need more time for an assessment. This research used 7000 images of Xception, Inception-V3, ResNet-50, NasNetMobile, VGG-16 and AlexNet models for verification and analysis. These are prevalent models that classify the image precision and use a rotational method to improve the performance of validation and the training dataset with convolutional neural network models. Xception, using the state of the art activation function (Mish) and optimizer (Nadam), improved the effectiveness, as found by the outcomes of the convolutional neural model evaluation of these models for classifying the malaria disease from thin blood smear images. In terms of the performance, recall, accuracy, precision, and F1 measure, a combined score of 99.28% was achieved. Consequently, 10% of all non-dataset training and testing images were evaluated utilizing this pattern. Notable aspects for the improvement of a computer-aided diagnostic to produce an optimum malaria detection approach have been found, supported by a 98.86% accuracy level.

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 The predictive brain: temporal coincidence and temporal order in synaptic learning mechanisms.

1994 ◽  
Vol 1 (1) ◽  
pp. 1-33
Author(s):  
P R Montague ◽  
T J Sejnowski
Keyword(s):  
Synaptic Plasticity ◽  
Temporal Order ◽  
Hebbian Learning ◽  
Learning Rule ◽  
Network Models ◽  
Learning Mechanisms ◽  
Neural Network Models ◽  
Spatial And Temporal Scales ◽  
Synaptic Inputs ◽  
Learning Rules

Some forms of synaptic plasticity depend on the temporal coincidence of presynaptic activity and postsynaptic response. This requirement is consistent with the Hebbian, or correlational, type of learning rule used in many neural network models. Recent evidence suggests that synaptic plasticity may depend in part on the production of a membrane permeant-diffusible signal so that spatial volume may also be involved in correlational learning rules. This latter form of synaptic change has been called volume learning. In both Hebbian and volume learning rules, interaction among synaptic inputs depends on the degree of coincidence of the inputs and is otherwise insensitive to their exact temporal order. Conditioning experiments and psychophysical studies have shown, however, that most animals are highly sensitive to the temporal order of the sensory inputs. Although these experiments assay the behavior of the entire animal or perceptual system, they raise the possibility that nervous systems may be sensitive to temporally ordered events at many spatial and temporal scales. We suggest here the existence of a new class of learning rule, called a predictive Hebbian learning rule, that is sensitive to the temporal ordering of synaptic inputs. We show how this predictive learning rule could act at single synaptic connections and through diffuse neuromodulatory systems.

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 Towards Autonomous Drone Racing without GPU Using an OAK-D Smart Camera

Sensors ◽  
2021 ◽  
Vol 21 (22) ◽  
pp. 7436
Author(s):  
Leticia Oyuki Rojas-Perez ◽  
Jose Martinez-Carranza
Keyword(s):  
Graphics Processing Units ◽  
Network Models ◽  
Depth Estimation ◽  
Neural Model ◽  
Smart Camera ◽  
Neural Network Models ◽  
Original Weight ◽  
Computationally Intensive ◽  
Graphics Processing ◽  
Initial Results

Recent advances have shown for the first time that it is possible to beat a human with an autonomous drone in a drone race. However, this solution relies heavily on external sensors, specifically on the use of a motion capture system. Thus, a truly autonomous solution demands performing computationally intensive tasks such as gate detection, drone localisation, and state estimation. To this end, other solutions rely on specialised hardware such as graphics processing units (GPUs) whose onboard hardware versions are not as powerful as those available for desktop and server computers. An alternative is to combine specialised hardware with smart sensors capable of processing specific tasks on the chip, alleviating the need for the onboard processor to perform these computations. Motivated by this, we present the initial results of adapting a novel smart camera, known as the OpenCV AI Kit or OAK-D, as part of a solution for the ADR running entirely on board. This smart camera performs neural inference on the chip that does not use a GPU. It can also perform depth estimation with a stereo rig and run neural network models using images from a 4K colour camera as the input. Additionally, seeking to limit the payload to 200 g, we present a new 3D-printed design of the camera’s back case, reducing the original weight 40%, thus enabling the drone to carry it in tandem with a host onboard computer, the Intel Stick compute, where we run a controller based on gate detection. The latter is performed with a neural model running on an OAK-D at an operation frequency of 40 Hz, enabling the drone to fly at a speed of 2 m/s. We deem these initial results promising toward the development of a truly autonomous solution that will run intensive computational tasks fully on board.

scholarly journals Fitting a recurrent dynamical neural network to neural spiking data: tackling the sigmoidal gain function issues

2019 ◽  
pp. 903-920
Author(s):  
REŞAT ÖZGÜR DORUK
Keyword(s):  
Neural Network ◽  
Firing Rate ◽  
Recurrent Neural Network ◽  
Continuous Time ◽  
Network Models ◽  
Estimation Algorithm ◽  
Solid Base ◽  
Gain Function ◽  
Neural Network Models ◽  
Neural Spiking

This is a continuation of a recent study (Doruk RO, Zhang K. Fitting of dynamic recurrent neural network models to sensory stimulus-response data. J Biol Phys 2018; 44: 449-469), where a continuous time dynamical recurrent neural network is fitted to neural spiking data. In this research, we address the issues arising from the inclusion of sigmoidal gain function parameters to the estimation algorithm. The neural spiking data will be obtained from the same model as that of Doruk and Zhang, but we propose a different model for identification. This will also be a continuous time recurrent neural network, but with generic sigmoidal gains. The simulation framework and estimation algorithms are kept similar to that of Doruk and Zhang so that we can have a solid base to compare the results. We evaluate the estimation performance in two different ways. First, we compare the firing rate responses of the original and the estimated model. We find that responses of both models to the same stimuli are similar. Secondly, we evaluate variations of the standard deviations of the estimates against a number of samples and stimulus parameters. They show a similar pattern to that of Doruk and Zhang. We thus conclude that our model serves as a reasonable alternative provided that firing rate is the response of interest (to any stimulus).

Sign in / Sign up

Export Citation Format

Share Document