The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Representation of knowledge within a neural model is an active field of research involved with the development of alternative structures, training algorithms, learning modes and applications. Radial Basis Function Neural Networks (RBFNNs) constitute an important part of the neural networks research as the operating principle is to discover and exploit similarities between an input vector and a feature...
This paper presents a one-layer recurrent neural network for solving convex programming problems subject to linear equality and nonnegativity constraints. The number of neurons in the neural network is equal to that of decision variables in the optimization problem. Compared with the existing neural networks for optimization, the proposed neural network has lower model complexity. Moreover, the proposed...
To localize a seen object, the superior colliculus of the barn owl integrates the visual and auditory localization cues which are accessed from the sensory system of the brain. These cues are formed as visual and auditory maps, thus the alignment between visual and auditory maps is very important for accurate localization in prey behavior. Blindness or prism wearing may disturb this alignment. The...
Data representation methods related to ICA and sparse coding have successfully been used to model neural representation. However, they are highly abstract methods, and the neural encoding does not correspond to a detailed neuron model. This limits their power to provide deeper insight into the sensory systems on a cellular level. We propose here data representation where the encoding happens with...
Using Chebyshev inequality and nonnegative semi-martingale convergence theorem, the paper investigates asymptotic behavior of stochastic Cohen-Grossberg neural networks with delay by constructing suitable Lyapunov functional. Algebraic criteria are given for stochastic ultimate bounded and almost exponential stability. The result in the paper extend the main conclusion. In the end, examples are given...
This paper proposes a hierarchical architecture, HieNet, that utilizes the K-Iterations Fast Learning artificial Neural Network (KFLANN). Effective in its clustering capabilities, the KFLANN is capable of providing more stable and consistent clusters that are independent data presentation sequences (DPS). Leveraging on the ability to provide more consistent clusters, the KFLANN is initially used to...
Computational intelligence methods are well-suited for use in computer controlled opponents for video games. In many other applications of these methods, the aim is to simulate near-optimal intelligent behaviour. But in video games, the aim is to provide interesting opponents for human players, not optimal ones. In this study, we trained neural network-based computer controlled opponents to play like...
This paper introduces a novel design of an artificial neural network tailored for wafer-scale integration. The presented VLSI implementation includes continuous-time analog neurons with up to 16 k inputs. A novel interconnection and routing scheme allows the mapping of a multitude of network models derived from biology on the VLSI neural network while maintaining a high resource usage. A single 20...
Recently a sufficient condition for the recurrent neural network with the piecewise-linear output characteristic to generate a prescribed periodic sequence of binary vectors such that every two consecutive vectors differ in exactly one component has been derived. If a recurrent neural network satisfies this condition, it is guaranteed that any state trajectory of the network passes through the periodic...
Supervised ANNs such as Learning Vector Quantization (LVQs) and Multi-Layer Perceptrons (MLPs) usually do not support data visualization beside classification. Unsupervised visualization focused ANNs such as Self-organizing Maps (SOM) and its variants such as Visualization induced SOM (ViSOM) on the other hand, usually do not optimize data classification as compared with supervised ANNs such as LVQ...
The process of segmenting images is one of the most critical ones in automatic image analysis whose goal can be regarded as to find what objects are presented in images. Artificial neural networks have been well developed. First two generations of neural networks have a lot of successful applications. Spiking neuron networks (SNNs) are often referred to as the 3rd generation of neural networks which...
The NetFlix Prize is a research contest that will award $1 Million to the first group to improve NetFlixpsilas movie recommendation system by 10%. Contestants are given a dataset containing the movie rating histories of customers for movies. From this data, a processing scheme must be developed that can predict how a customer will rate a given movie on a scale of 1 to 5. An architecture is presented...
In this paper, we present a biologically inspired method for detecting pedestrians in images. The method is based on a convolutional neural network architecture, which combines feature extraction and classification. The proposed network architecture is much simpler and easier to train than earlier versions. It differs from its predecessors in that the first processing layer consists of a set of pre-defined...
The work presented in this paper concerns the detection of drowsy driving based on time series measurements of driving behavior. Artificial neural networks, trained using particle swarm optimization, have been used to combine several indicators of drowsy driving based on a data set originating from a large study carried out in the driving simulator at the Swedish National Road and Transportation Institute...
This paper attempts to model human brainpsilas cognitive process at the primary visual cortex to comprehend road sign. The cortical maps in visual cortex have been widely focused in recent research. We propose a visual model that locates road sign in an image and identifies the localized road sign. Gabor wavelets are used to encode visual information and extract features. Self-organizing maps are...
In this paper, we propose a knowledge processing system using Kohonen feature map associative memory with refractoriness based on area representation. The proposed system is based on the Kohonen feature map associative memory with refractoriness based on area representation. In the conventional Kohonen feature map associative memory, only one-to-one associations can be realized. In contrast, one-to-many...
In this research, we propose a similarity-based image retrieval from plural key images by self-organizing map with refractoriness. In the self-organizing map with refractoriness, the plural neurons in the map layer corresponding to the input can fire sequentially because of the refractoriness. The proposed image retrieval system from plural key images using the self-organizing map with refractoriness...
In this paper, we propose a Kohonen feature map associative memory with area representation for sequential analog patterns. This model is based on the Kohonen feature map associative memory with area representation for sequential patterns. Although the conventional Kohonen feature map associative memory with area representation for sequential patterns can deal with only binary (bipolar) patterns,...
In this research, we propose a similarity-based melody retrieval by self-organizing map with refractoriness. In the self-organizing map with refractoriness, the plural neurons in the map layer corresponding to the input can fire sequentially because of the refractoriness. The proposed melody retrieval system using the self-organizing map with refractoriness makes use of this property in order to retrieve...
Hypercolumn model (HCM) is a neural network model previously proposed to solve image recognition problem. In this paper, we propose an improved version of HCM network and demonstrate its ability to solve face recognition problem. HCM network is a hierarchical model based on self-organizing map (SOM) that closely follows the organization of visual cortex and builds an increasingly complex and invariant...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.