共查询到20条相似文献,搜索用时 15 毫秒
1.
In this paper we present an acoustic motion detection system to be used in a small mobile robot. While the first purpose of the system has been to be a reliable computational implementation, cheap enough to be built in hardware, effort has also been taken to construct a biologically plausible solution. The motion detector consists of a neural network composed of motion-direction sensitive neurons with a preferred direction and a preferred region of the azimuth. The system was designed to produce a higher response when stimulated by motion in the preferred direction than in the null direction and that is in fact what the system does, which means that, as desired, the system can detect motion and distinguish its direction. 相似文献
2.
A neural network which models multistable perception is presented. The network consists of sensor and inner neurons. The dynamics is established by a stochastic neuronal dynamics, a formal Hebb-type coupling dynamics and a resource mechanism that corresponds to saturation effects in perception. From this a system of coupled differential equations is derived and analyzed. Single stimuli are bound to exactly one percept, even in ambiguous situations where multistability occurs. The network exhibits discontinuous as well as continuous phase transitions and models various empirical findings, including the percepts of succession, alternative motion and simultaneity; the percept of oscillation is explained by oscillating percepts at a continuous phase transition. Received: 13 September 1995 / Accepted: 3 June 1996 相似文献
3.
Chaotic dynamics generated in a chaotic neural network model are applied to 2-dimensional (2-D) motion control. The change
of position of a moving object in each control time step is determined by a motion function which is calculated from the firing
activity of the chaotic neural network. Prototype attractors which correspond to simple motions of the object toward four
directions in 2-D space are embedded in the neural network model by designing synaptic connection strengths. Chaotic dynamics
introduced by changing system parameters sample intermediate points in the high-dimensional state space between the embedded
attractors, resulting in motion in various directions. By means of adaptive switching of the system parameters between a chaotic
regime and an attractor regime, the object is able to reach a target in a 2-D maze. In computer experiments, the success rate
of this method over many trials not only shows better performance than that of stochastic random pattern generators but also
shows that chaotic dynamics can be useful for realizing robust, adaptive and complex control function with simple rules. 相似文献
4.
A statistical correlation technique (SCT) and two variants of a neural network are presented to solve the motion correspondence problem. Solutions of the motion correspondence problem aim to maintain the identities of individuated elements as they move. In a pre-processing stage, two snapshots of a moving scene are convoluted with two-dimensional Gabor functions, which yields orientations and spatial frequencies of the snapshots at every position. In this paper these properties are used to extract, respectively, the attributes orientation, size and position of line segments. The SCT uses cross-correlations to find the correct translation components, angle of rotation and scaling factor. These parameters are then used in combination with the positions of the line segments to calculate the centre of motion. When all of these parameters are known, the new positions of the line segments from the first snapshot can be calculated and compared to the features in the second snapshot. This yields the solution of the motion correspondence problem. Since the SCT is an indirect way of solving the problem, the principles of the technique are implemented in interactive activation and competition neural networks. With boundary problems and noise these networks perform better than the SCT. They also have the advantage that at every stage of the calculations the best candidates for corresponding pairs of line segments are known. 相似文献
5.
6.
We have developed a Behler–Parrinello Neural Network (BPNN) that can be employed to calculate energies and forces of zirconia bulk structures with oxygen vacancies with similar accuracy as that of the density functional theory (DFT) calculations that were used to train the BPNN. In this work, we have trained the BPNN potential with a reference set of 2178 DFT calculations and validated it against a dataset of untrained data. We have shown that the bulk structural parameters, equation of states, oxygen vacancy formation energies and diffusion barriers predicted by the BPNN potential are in good agreement with the reference DFT data. The transferability of the BPNN potential has also been benchmarked with the prediction of structures that were not included in the reference set. The evaluation time of the BPNN is orders of magnitude less than corresponding DFT calculations, although the training process of the BPNN potential requires non-negligible amount of computational resources to prepare the dataset. The computational efficiency of the NN enabled it to be used in molecular dynamics simulations of the temperature-dependent diffusion of an oxygen vacancy and the corresponding diffusion activation energy. 相似文献
7.
This paper considers the problem of training layered neural networks to generate sequences of states. Aiming at application for situations when an integral characteristic of the process is known rather than the specific sequence of states we put forward a method in which underlying general principle is used as a foundation for the learning procedure. To illustrate the ability of a network to learn a task and to generalize algorithm we consider an example where a network generates sequences of states referred to as trajectories of motion of a particle under an external field. Training is grounded on the employment of the least action principle. In the course of training at restricted sections of the path the network elaborates a recurrent rule for the trajectory generation. The rule proves to be equivalent to the correct equation of motion for the whole trajectory. 相似文献
8.
E.Sture Eriksson 《Journal of insect physiology》1984,30(5):363-368
The responses of single units in the optic lobe of the blowfly Phormia terraenovae have been investigated using micro-electrode techniques and computer generation of optical stimulation. In order to test the idea that single units perform a “neural vector analysis” the optical stimulation was designed in such a way that the mathematical vector analytic capacity of the neurones could be investigated by using a single luminous dot moving in the proper way. The integrative mechanism of the neurone could be studied by using two dots moving in such a way that the inhibitory and excitatory components of the stimulus were related in precise ways. The data verify the notion of “neural vector analysis” and open the way for an analysis of motion perception and perceptual constancies on the basis of neural mechanisms. 相似文献
9.
In this paper we consider some classical control theoretic properties of a nonlinear neural network proposed by Ouztöreli (1979) to represent the activities of constiuent neurones in terms of the input signals and coupling (associative) properties. By breaking the network into linear and nonlinear components we have been able to localize the nonlinearities in the individual neural response latencies through the system.This work was partially supported by the Natural Sciences and Engineering Research Council of Canada by Grant NSERC-A 4345 to M.N.O. and Grant NSERC-A 2568 to T.M.C. through the University of Alberta 相似文献
10.
Björklund M 《Journal of theoretical biology》2002,218(2):149-154
The tactics of mate choice was studied by means of a simple neural network model. A female was assessing 6 or 43 males and optimal choice was assumed to be the largest male of the set of males visited. This was run over a set of variances in male traits from very low as in fluctuating asymmetry to very high as in ornaments. This was done in two ways: by estimating the mean number of visits to each male before the optimal choice was done, or the probability of choosing the largest male given the constraints of five visits. When an error was introduced in perception the number of visits was very high if variance was low, but levelled off and reached an asymptote at fairly low levels of variance, i.e. variance among males is important only up to a certain level. When the number of visits was constrained the probability of choosing the right male increased with increasing variance. When asymmetry was evaluated the chance of finding the "best" male in five visits was very low (<10%) for the 6-male case, and it never happened in the 43-male case. 相似文献
11.
A. Carlson 《Biological cybernetics》1990,64(2):171-176
The Hebbian rule (Hebb 1949), coupled with an appropriate mechanism to limit the growth of synaptic weights, allows a neuron to learn to respond to the first principal component of the distribution of its input signals (Oja 1982). Rubner and Schulten (1990) have recently suggested the use of an anti-Hebbian rule in a network with hierarchical lateral connections. When applied to neurons with linear response functions, this model allows additional neurons to learn to respond to additional principal components (Rubner and Tavan 1989). Here we apply the model to neurons with non-linear response functions characterized by a threshold and a transition width. We propose local, unsupervised learning rules for the threshold and the transition width, and illustrate the operation of these rules with some simple examples. A network using these rules sorts the input patterns into classes, which it identifies by a binary code, with the coarser structure coded by the earlier neurons in the hierarchy. 相似文献
12.
Motion recognition has received increasing attention in recent years owing to heightened demand for computer vision in many domains, including the surveillance system, multimodal human computer interface, and traffic control system. Most conventional approaches classify the motion recognition task into partial feature extraction and time-domain recognition subtasks. However, the information of motion resides in the space-time domain instead of the time domain or space domain independently, implying that fusing the feature extraction and classification in the space and time domains into a single framework is preferred. Based on this notion, this work presents a novel Space-Time Delay Neural Network (STDNN) capable of handling the space-time dynamic information for motion recognition. The STDNN is unified structure, in which the low-level spatiotemporal feature extraction and high-level space-time-domain recognition are fused. The proposed network possesses the spatiotemporal shift-invariant recognition ability that is inherited from the time delay neural network (TDNN) and space displacement neural network (SDNN), where TDNN and SDNN are good at temporal and spatial shift-invariant recognition, respectively. In contrast to multilayer perceptron (MLP), TDNN, and SDNN, STDNN is constructed by vector-type nodes and matrix-type links such that the spatiotemporal information can be accurately represented in a neural network. Also evaluated herein is the performance of the proposed STDNN via two experiments. The moving Arabic numerals (MAN) experiment simulates the object's free movement in the space-time domain on image sequences. According to these results, STDNN possesses a good generalization ability with respect to the spatiotemporal shift-invariant recognition. In the lipreading experiment, STDNN recognizes the lip motions based on the inputs of real image sequences. This observation confirms that STDNN yields a better performance than the existing TDNN-based system, particularly in terms of the generalization ability. In addition to the lipreading application, the STDNN can be applied to other problems since no domain-dependent knowledge is used in the experiment. 相似文献
13.
Fukushima K 《Biological cybernetics》2001,84(4):251-259
Human beings are often able to read a letter or word partly occluded by contaminating ink stains. However, if the stains
are completely erased and the occluded areas of the letter are changed to white, we usually have difficulty in reading the
letter. In this article I propose a hypothesis explaining why a pattern is easier to recognize when it is occluded by visible
objects than by invisible opaque objects. A neural network model is constructed based on this hypothesis.
The visual system extracts various visual features from the input pattern and then attempts to recognize it. If the occluding
objects are not visible, the visual system will have difficulty in distinguishing which features are relevant to the original
pattern and which are newly generated by the occlusion. If the occluding objects are visible, however, the visual system can
easily discriminate between relevant and irrelevant features and recognize the occluded pattern correctly.
The proposed model is an extended version of the neocognitron model. The activity of the feature-extracting cells whose receptive
fields cover the occluding objects is suppressed in an early stage of the hierarchical network. Since the irrelevant features
generated by the occlusion are thus eliminated, the model can recognize occluded patterns correctly, provided the occlusion
is not so large as to prevent recognition even by human beings.
Received: 21 February 2000 / Accepted in revised form: 11 September 2000 相似文献
14.
Recently, numerous attempts have been made to understand the dynamic behavior of complex brain systems using neural network models. The fluctuations in blood-oxygen-level-dependent (BOLD) brain signals at less than 0.1 Hz have been observed by functional magnetic resonance imaging (fMRI) for subjects in a resting state. This phenomenon is referred to as a "default-mode brain network." In this study, we model the default-mode brain network by functionally connecting neural communities composed of spiking neurons in a complex network. Through computational simulations of the model, including transmission delays and complex connectivity, the network dynamics of the neural system and its behavior are discussed. The results show that the power spectrum of the modeled fluctuations in the neuron firing patterns is consistent with the default-mode brain network's BOLD signals when transmission delays, a characteristic property of the brain, have finite values in a given range. 相似文献
15.
During recent years, neural network research has been extendedto a large number of different fields, increasingly attractingthe interest of workers from various disciplines. The computersimulations carried out with this research require an appropriatesoftware environment. The computational similarities of manykinds of simulations allow the design of software componentsthat are largely independent of the specific application. Theseconsiderations are reflected, for example, by the general layoutof the MENS network simulator, as described in the accompanyingfirst paper. This paper presents the design considerations forthe simulator's different software components in more detail.In particular, design and implementation are discussed withrespect to computational and memory efficiency. The discussionincludes, for example, the representation of a network by thesimulator's data structure, the file-driven configuration andinitialization of a network, the simulator's stimulus and monitorsystem, and the simulator's control structures. In addition,the separation and interaction of application-specific and application-independentsoftware components are addressed. Particular performance aspectscomprise the implementation of synaptic delays, the dynamicdeletion of synaptic links in network learning, and the preprocessingof stimulus films. In addition, some general aspects of simulatorperformance and testing are considered. The material presentedin this paper concerns both the development of new simulationsoftware and the efficient use of existing programs. Therefore,both the general user as well as the software designer may hopefullybenefit from this presentation. 相似文献
16.
An object extraction problem based on the Gibbs Random Field model is discussed. The Maximum a'posteriori probability (MAP) estimate of a scene based on a noise-corrupted realization is found to be computationally exponential in nature. A neural network, which is a modified version of that of Hopfield, is suggested for solving the problem. A single neuron is assigned to every pixel. Each neuron is supposed to be connected only to all of its nearest neighbours. The energy function of the network is designed in such a way that its minimum value corresponds to the MAP estimate of the scene. The dynamics of the network are described. A possible hardware realization of a neuron is also suggested. The technique is implemented on a set of noisy images and found to be highly robust and immune to noise. 相似文献
17.
Jack W. Silverstein 《Biological cybernetics》1976,22(2):73-84
A mathematical model of neural processing is proposed which incorporates a theory for the storage of information. The model consists of a network of neurons that linearly processes incoming neural activity. The network stores the input by modifying the synaptic properties of all of its neurons. The model lends support to a distributive theory of memory using synaptic modification. The dynamics of the processing and storage are represented by a discrete system. Asymptotic analysis is applied to the system to show the learning capabilities of the network under constant input. Results are also given to predict the network's ability to learn periodic input, and input subjected to small random fluctuations. 相似文献
18.
Ursino M Cuppini C Magosso E Serino A di Pellegrino G 《Journal of computational neuroscience》2009,26(1):55-73
Neurons in the superior colliculus (SC) are known to integrate stimuli of different modalities (e.g., visual and auditory)
following specific properties. In this work, we present a mathematical model of the integrative response of SC neurons, in
order to suggest a possible physiological mechanism underlying multisensory integration in SC. The model includes three distinct
neural areas: two unimodal areas (auditory and visual) are devoted to a topological representation of external stimuli, and
communicate via synaptic connections with a third downstream area (in the SC) responsible for multisensory integration. The
present simulations show that the model, with a single set of parameters, can mimic various responses to different combinations
of external stimuli including the inverse effectiveness, both in terms of multisensory enhancement and contrast, the existence
of within- and cross-modality suppression between spatially disparate stimuli, a reduction of network settling time in response
to cross-modal stimuli compared with individual stimuli. The model suggests that non-linearities in neural responses and synaptic
(excitatory and inhibitory) connections can explain several aspects of multisensory integration. 相似文献
19.
This paper describes an experimental investigation concerning the use of neural networks to achieve the non-linear control of a continuous stirred tank fermenter. The influent dilution rate and the substrate concentration have been selected as control variables. The backpropagation learning algorithm has been used for both off-line and on-line identification of the inverse model which provides the control action. Experimental results show the performance and the implementation simplicity of this control approach. 相似文献
20.
Egelhaaf M 《Current biology : CB》2008,18(8):R339-R341
A wide range of novel approaches are being used to dissect the visual system of the fly, both the neural networks of motion detection and the performance of these networks under complex natural stimulus conditions. 相似文献