Showing papers in "Neural Networks in 2006"

TL;DR: It is demonstrated that the suggested model can enable a model of object recognition in cortex to expand from recognizing individual objects in isolation to sequentially recognizing all objects in a more complex scene.

TL;DR: A linear matrix inequality (LMI) approach is developed to establish sufficient conditions for the RNNs to be globally exponentially stable, and the existence and uniqueness of the equilibrium point under mild conditions is proved.

TL;DR: This model incorporates the subthalamic nucleus (STN) and shows that by modulating when a response is executed, the STN reduces premature responding and therefore has substantial effects on which response is ultimately selected, particularly when there are multiple competing responses.

TL;DR: The clinical fields where neural network methods figure most prominently, the main algorithms featured, methodologies for model selection and the need for rigorous evaluation of results are reviewed.

TL;DR: A new model of decision-making in risky situations is proposed and differences between decisions under ambiguity and decisions under risk are described from a theoretical and clinical perspective.

TL;DR: This review considers the theoretical problems facing agents that must learn and choose on the basis of reward or reinforcement that is uncertain or delayed, in implicit or procedural (stimulus-response) representational systems and in explicit or declarative (action-outcome-value) representingational systems.

TL;DR: A novel method for estimating prediction uncertainty using machine learning techniques is presented and preliminary results show that the method is superior to other methods estimating the prediction interval.

TL;DR: The design of two-layer neural network enables this system to represent the topological structure of unsupervised on-line data, report the reasonable number of clusters, and give typical prototype patterns of every cluster without prior conditions such as a suitable number of nodes or a good initial codebook.

TL;DR: Evidence from rodents and monkeys that demonstrate the degree to which they take into account work and energetic requirements when deciding what responses to make is presented, suggesting that top-down signals from ACC to nucleus accumbens and/or midbrain DA cells may be vital for overcoming effort-related response costs.

TL;DR: This paper study the consequences of importing this competition into a reinforcement learning context, and demonstrate the resulting effects in an omission schedule and a maze navigation task, and discuss how it may be disciplined.

TL;DR: A meta-analysis underlines the gap between conceptual and computational models and points out the research effort required from both sides to reduce this gap.

TL;DR: It is demonstrated that a relatively large class of models, both with and without temporal integration and both stationary and time-variant could account for the behavioral data and the biological plausibility of the model parameters is discussed.

TL;DR: A conception of attentional networks arising from imaging studies as connections between activated brain areas carrying out localized mental operations is outlined and a wide range of methods are shown to suggest and analyze models of network function in the study of attention.

TL;DR: This work describes a robot architecture into which a computational model of the basal ganglia to generate integrated selection sequences in an autonomous agent is embedded, and demonstrates effective action selection by the embedded model under a wide range of sensory and motivational conditions.

TL;DR: An improvement to the AC architecture, called the "Single Network Adaptive Critic (SNAC)," is presented, which is applicable to a wide class of nonlinear systems where the optimal control (stationary) equation can be explicitly expressed in terms of the state and costate variables.

TL;DR: In this article, a linear matrix inequality (LMI) approach is developed to derive sufficient conditions ensuring the delayed neural network to have a unique equilibrium point, which is globally exponentially stable.

TL;DR: The issues of downscaling the outputs of GCMs using a temporal neural network (TNN) approach are presented and it is suggested that the TNN is an efficient method for down scaling both daily precipitation as well as daily temperature series.

TL;DR: A "heterarchical reinforcement learning" model is proposed, where reward prediction made by more limbic and cognitive loops is propagated to motor loops by spiral projections between the striatum and substantia nigra, assisted by cortical projections to the pedunculopontine tegmental nucleus, which sends excitatory input to the substantia Nigra.

TL;DR: In this paper, global exponential stability and exponential convergence are studied for a class of impulsive high-order bidirectional associative memory neural networks with time-varying delays by employing linear matrix inequalities and differential inequalities with delays and impulses.

TL;DR: A new type of numerical model, a complex hybrid environmental model based on a synergetic combination of deterministic and machine learning model components, has been introduced in this paper for applications to climate modeling and weather prediction.

TL;DR: Activity of a distributed paralimbic system, centered on the left hippocampus, correlated selectively with predictability as measured with mutual information, clear evidence that the brain is sensitive to the probabilistic context in which events are encountered.

TL;DR: This study presents experiments on the learning of object handling behaviors by a small humanoid robot using a dynamic neural network model, the recurrent neural network with parametric bias (RNNPB), and showed that entrainment of the internal memory structures of the RNNPB through the interactions of the objects and the human supporters are the essential mechanisms for those observed situated behaviors of the robot.

TL;DR: A neural network is proposed that adapts thresholds in order to maximize reward rate and makes predictions regarding optimal performance and provides a benchmark against which actual performance can be compared, as well as testable predictions about the way in which reward rate may be encoded by neural mechanisms.

TL;DR: It is shown that the Cohen-Grossberg neural network is globally exponentially stable, if the absolute value of the input vector exceeds a criterion.

TL;DR: A theoretical account for the time-courses of these two processes, whose instabilities are the basis of decision making, shows how the cross-over from spatial averaging for fast saccades to selection for slow saccade arises from the balance between excitatory and inhibitory processes.

TL;DR: The proposed model evolves both the weights and the structure of these networks by means of an evolutionary programming algorithm and shows better overall performance in the benchmark functions as well as the real-world problem of microbial growth modeling.

TL;DR: The nonlinear (NL) models showed higher correlation skills and lower root mean square errors over most areas of the domain, especially over the far western Pacific and the eastern equatorial Pacific at lead times longer than 3 months, with correlation skills enhanced by 0.10-0.14.

TL;DR: A dynamic model of attention based on the Continuum Neural Field Theory is presented that explains attention as being an emergent property of a neural population and can be considered as a generic attentional process of any spatio-temporal continuous input.

TL;DR: A probabilistic model of gaze imitation and shared attention that is inspired by Meltzoff and Moore's AIM model for imitation in infants is presented and it is shown that combining saliency maps with gaze estimates leads to greater accuracy than using gaze alone.

TL;DR: A biologically plausible model of decision making endowed with synaptic plasticity that follows a reward-dependent stochastic Hebbian learning rule is proposed, which constitutes a biophysical implementation of reinforcement learning and generates quasi-random behaviour robustly in spite of intrinsic biases.