Autism is a mental disorder characterized by deficits in socialization, communication, and imagination. Along with the deficits, autistic children may show savant skills ("islets of ability") of unknown orig...
详细信息
Autism is a mental disorder characterized by deficits in socialization, communication, and imagination. Along with the deficits, autistic children may show savant skills ("islets of ability") of unknown origin that puzzles their families and the psychologists. Comorbidity with epilepsy and mental retardation has brought the researchers' attention to neurobiological and cognitive theories of the syndrome. The present article proposes a neurobiological model for the autism based on the fundamental biological process of neuronal competition. A neural network capable of defining neural maps-synaptic projections preserving neighborhoods between two neural tissues-simulates the process of neurodevelopment. Experiments were performed reducing the level of neural growth factor released by the neurons, leading to ill-developed maps and suggesting the cause of the aberrant neurogenesis present in autism. The computer simulations hint that brain regions responsible for the formation of higher level representations are impaired in autistic patients. The lack of this integrated representation of the world would result in the peculiar cognitive deficits of socialization, communication, and imagination and could also explain some "islets of abilities", like excellent memory for raw data and stimuli discrimination. The neuronal model is based on plausible biological findings and on recently developed cognitive theories of autism. Close relations are established between the computational properties of the neural network model and the cognitive theory of autism denominated "weak central coherence", bringing some insight to the understanding of the disorder.
The original proposal of active contour models, also called snakes, for image segmentation, suffers from a strong sensitivity to its initial position and can not deal with topological changes. The sensitivity to initi...
详细信息
The original proposal of active contour models, also called snakes, for image segmentation, suffers from a strong sensitivity to its initial position and can not deal with topological changes. The sensitivity to initialization can be addressed by dynamic programming (DP) techniques which have the advantage of guaranteeing the global minimum and of being more stable numerically than the variational approaches. Their disadvantages are the storage requirements and computational complexity. In this paper we address these limitations of DP by reducing the region of interest (search space) through the use of the Dual-T-Snake approach. The solution of this method consists of two curves enclosing each object boundary which allows the definition of a more efficient search space for a DP technique. The resulting method (Dual-T-Snake plus DP) inherits the capability of changing the topology and avoiding local minima from the Dual-T-Snake and the global optimal properties of the dynamic programming. It can be also extended for 3D.
Proposes a method for data clustering in a n-dimensional space using the elastic net algorithm which is a variant of the Kohonen topographic map learning algorithm. The elastic net algorithm is a mechanical metaphor i...
详细信息
Proposes a method for data clustering in a n-dimensional space using the elastic net algorithm which is a variant of the Kohonen topographic map learning algorithm. The elastic net algorithm is a mechanical metaphor in which an elastic ring is attracted by points in a bi-dimensional space while their internal elastic forces try to shun the elastic expansion. The different weights associated with these two kinds of forces lead the elastic to a gradual expansion in the direction of the bi-dimensional points. In this method, the elastic net algorithm is employed with the help of a heuristic framework that improves its performance for application in the n-dimensional space of cluster analysis. Tests were made with two types of data sets: (1) simulated data sets with up to 1000 points randomly generated in groups linearly separable with up to dimension 10 and (2) the Fisher Iris Plant database, a well-known database referred to in the pattern recognition literature. The advantages of the method presented are its simplicity, its fast and stable convergence, beyond efficiency in cluster analysis.
In this paper we use execution-driven simulation of a scalable multiprocessor to evaluate the performance of the Andorra-I parallel logic programming system under invalidate and update-based protocols. We use two vers...
详细信息
Grasslands are the largest of the Earth's four major vegetation types and are among the most agriculturally productive lands. Grassland management practices alter biophysical factors, such as plant species composi...
详细信息
In this work we investigate how Distributed Shared Memory (DSM) architectures affect performance of or-parallel logic programming systems and how this performance approaches that of conventional C systems. Our work co...
详细信息
In this paper we propose a simple extension to the optical network of a scalable multiprocessor that optimizes page swap-outs significantly. More specifically, we propose to extend the network with an optical ring tha...
详细信息
A variety of alternate training strategies for implementing the dual heuristic programming (DHP) method of approximate dynamic programming in the neurocontrol context are explored. The DHP method of controller trainin...
详细信息
A variety of alternate training strategies for implementing the dual heuristic programming (DHP) method of approximate dynamic programming in the neurocontrol context are explored. The DHP method of controller training has been successfully demonstrated by a number of authors on a variety of control problems in recent years, but no unified view of the implementation details of the method has yet emerged. A number of options are described for sequencing the training of the controller and critic networks in DHP implementations. Results are given about their relative efficiency and the quality of the resulting controllers for two benchmark control problems.
The recent improvements in workstation and interconnection network performance have popularized the clusters of off-the-shelf workstations. However, the usefulness of these clusters is yet to be fully exploited, mostl...
详细信息
The recent improvements in workstation and interconnection network performance have popularized the clusters of off-the-shelf workstations. However, the usefulness of these clusters is yet to be fully exploited, mostly due to the inadequate management of cluster resources implemented by current distributed operating systems. In order to eliminate this problem and approach the computational power of large clusters of workstations, in this paper we propose Nomad, an efficient operating system for clusters of uni and/or multiprocessors. Nomad includes several important characteristics for modern cluster-oriented operating systems: scalability, efficient resource management across the cluster, efficient scheduling of parallel and distributed applications, distributed I/O, fault detection and recovery, protection, and backward compatibility. Some of the mechanisms used by Nomad, such as process checkpointing and migration, can be found in previously proposed systems. However, our system stands out for its strategy for disseminating information across the cluster and its efficient management of all cluster resources. In addition, Nomad is highly scalable as it uses neither centralized control nor extra messages to implement its functionality, taking advantage of the I/O traffic associated with its distributed file system. Our preliminary evaluation of the load balancing aspect of Nomad shows that the pattern of file accesses in our distributed Ale system allows for efficient and scalable load balancing. Our main conclusion is that the complete implementation of Nomad will most likely be efficient and will be a nice platform for future research on operating systems for clusters of workstations.
We have proposed for the task of hourly electric load forecasting a hybrid neural system combining unsupervised and supervised learning. The system consists of a recurrent neural gas (RNG) network and many Elman neura...
详细信息
We have proposed for the task of hourly electric load forecasting a hybrid neural system combining unsupervised and supervised learning. The system consists of a recurrent neural gas (RNG) network and many Elman neural networks (ENs). RNG is a modification we introduced in the neural gas (NG) network in order to enable it to do clustering using a sequence of input data. For verifying the RNG's performance, many architectures are compared in the learning of global and local models. In a global model only one supervised network is trained and in a local model the training examples are grouped by a clustering algorithm and each one of these groups is sent to different supervised networks. These architectures use different clustering algorithms (NG and RNG) or different supervised networks for prediction (ENs that are trained by backpropagation or backpropagation through time, and feedforward networks).
暂无评论