Search

The research reported in this paper focuses on the response of identical discrete-time neural oscillators to a random telegraph signal input. It is shown that there are well-defined domains in which the random input can synchronize even a large population of oscillators within a few hundred steps. The presence of chaos is shown to be essential for the synchronization, which suggests a possible role for chaos in spatially extended physical systems. The effect of independent noise on the system is also studied.

The neural basis of creative thinking - indeed of all thinking - remains mysterious. One influential theory by Mednick holds that creative thinking reflects a difference in the associational structure of conceptual representations in the mind. We have previously proposed a neural network model based on itinerant dynamics to model thinking, and used it to show that a small-world, scale-free associational structure - similar to that found empirically in linguistic data - is especially efficient for exploring conceptual space and generating conceptual combinations. In this paper, we apply this model to associative networks obtained from the poetry of Dylan Thomas and John Gay, and the prose of F. Scott Fitzgerald and George Orwell. Network analysis shows that poetic texts indeed incorporate a wider distribution of associations than prose. However, neural simulations using semantic networks from the four sources present a more complex picture. We also consider the case where a poet's associative network is transformed to that of a prose-writer to test the impact of this manipulation.

In this paper we study the effect of external ideas on brainstorming by means of two computational models: a transient emergent attractors model (TEAM) and a probabilistic associative model (PAM). New behavioral experimental results show that hints or others' ideas can either hinder or enhance ideas generated during exposure period, while they consistently enhance the quantity of ideas produced after exposure. The TEAM model consists of a neural network of concept nodes connected by means of category membership and relatedness. Ideas emerge dynamically from the activity of the network by temporarily strengthening the connections between co-active nodes. Local inhibition inactivates current idea nodes and allows another idea to form. Active nodes prime connected inactive nodes depending on the recent activity of the node. The model shows that hindering of the number of ideas during hint presentation depends on the strength of hints and that the speed and duration of priming is essential for the long-term priming effect of hints observed in experiments. For comparison purposes, a PAM model originally proposed by Brown and Paulus (1998) is used to explain the same experimental data.

We present in this paper a personality-based architecture (PA) that combines elements from the subsumption architecture and reinforcement learning to find alternate solutions for problems facing artificial agents exploring unknown environments. The underlying PA algorithm is decomposed into layers according to the different (non-contiguous) stages that our agent passes in, which in turn are influenced by the sources of rewards present in the environment. The cumulative rewards collected by an agent, in addition to its internal composition serve as factors in shaping its personality. In missions where multiple agents are deployed, our solution-goal is to allow each of the agents develop its own distinct personality in order for the collective to reach a balanced society, which then can accumulate the largest possible amount of rewards for the agent and society as well. The architecture is tested in a simulated matrix world which embodies different types of positive rewards and negative rewards. Varying experiments are performed to compare the performance of our algorithm with other algorithms under the same environment conditions. The use of our architecture accelerates the overall adaptation of the agents to their environment and goals by allowing the emergence of an optimal society of agents with different personalities. We believe that our approach achieves much efficient results when compared to other more restrictive policy designs.

It is generally believed that cognition involves the self-organization of coherent dy- namic functional networks across several brain regions in response to incoming stimulus and internal modulation. These context-dependent networks arise continually from the spatiotemporally multi-scale structural substrate of the brain configured by evolution, development and previous experience, persisting for 100–200 ms and generating re- sponses such as imagery, recall and motor action. In the current paper, we show that a system of interacting modular attractor networks can use a selective mechanism for assembling functional networks from the modular substrate. We use the approach to develop a model of idea-generation in the brain. Ideas are modeled as combinations of concepts organized in a recurrent network that reflects previous associations between them. The dynamics of this network, resulting in the transient co-activation of concept groups, is seen as a search through the space of ideas, and attractor dynamics is used to “shape” this search. The process is required to encompass both rapid retrieval of old ideas in familiar contexts and efficient search for novel ones in unfamiliar situations (or during brainstorming). The inclusion of an adaptive modulatory mechanism allows the network to balance the competing requirements of exploiting previous learning and exploring new possibilities as needed in different contexts.

Feedforward neural networks with continuous-valued activation functions have recently emerged as a powerful paradigm for modeling nonlinear systems. Several classes of such networks have been proved to possess universal approximation capabilities. Prominent among the advantages claimed for such networks are robustness and distributedness of processing and representation. However, there has been little direct research on either issue, particularly the former, and these characteristics of neural networks have been accepted mostly on faith, or on the basis of heuristic arguments. In this paper, we attempt to construct a framework within which these very important issues can be addressed in a coherent and tractable manner. The focus of the paper is on a particularly simple, but instructive, problem: to predict the effect of perturbations in internal neuron outputs on the performance of the network as a whole. This is directly useful in three ways: 1) it gives information about the network's tolerance of internal perturbations; 2) it can be used as a criterion for selecting among multiple network solutions to a given modeling problem; and 3) it provides a framework for relating the performance of a network to the performance of its components. Of these, the third is especially attractive because it can be used as the basis for a theory of distributed representation and processing in feedforward networks.

Creativity and insight are distinctive attributes of human cognition, but their neural basis remains poorly understood due to the difficulty of experimental study. As such, computational modeling can play an important role in understanding these phenomena. Some researchers have proposed that creative individuals have a “deeper” organization of knowledge, allowing them to connect remote associates and form novel ideas. It is reasonable to assume that the depth and richness of semantic organization in individual minds is related to the connectivity of neural networks involved in semantic representation. In this paper, we use a simple and plausible neurodynamical model of semantic networks to study how the connectivity structure of these networks relates to the richness of the semantic constructs, or ideas, they can generate. This work is motivated, in part, by research showing that experimentally obtained semantic networks have a specific connectivity pattern that is both small-world and scale-free. We show that neural semantic networks reflecting this structure have richer semantic dynamics than those with other connectivity structures. Though simple, this model may provide insight into the important issue of how the physical structure of the brain determines one of the most profound features of the human mind - its capacity for creative thought.

Understanding the ability of humans and animals to exhibit a large repretoire of complex movements in a continuosly changing and uncertain environment is of interest to both biologists and engineers. Even the simplest movements require complex control of internal and external variables of the body and the environment in a variety of contexts. Classical methods - such as those used in industrial robotics - are difficult to apply in these high degree-of-freedom situations. Studies on motor control in animals have led to the discovery that, rather than using standard feedback control based on continuous tracking of desired trajectories, animals' movements emerge from the controlled combination of pre-configured movement primitives or synergies. These synergies define coordinated patterns of activity across specific sets of muscles, and can be triggered as a whole with controlled amplitude and temporal offset. Combinations of synergies, therefore, allow emergent configuration of a wide range of complex movements. Control is both simpler and richer in this synergistic framework because it is based on selection and combination of synergies rather than myopic tracking of trajectories. Though the existence of motor synergies is now well-established, there is very little computational modeling of them at the neural level. In this paper, we describe a simple neural model for motor synergies, and show how a small set of synergies selected through a redundancy-reduction principle can generate a rich motor repertoire in a model two-jointed arm system.

Due to its effectiveness, the amount of projects and people involved in research of Intelligent Systems is growing. This positive trend has resulted in the increase in demand for academic educational courses/learning experiences especially at the graduate level. This paper focuses on the approaches of two educators at the University of Cincinnati in the area of fuzzy logic and intelligent & adaptive systems. The lessons learned and the winning strategies are underscored in an attempt to enhance the open exchange of ideas, teaching styles and methodologies.

This paper proposes a coverage scheme for the rapid mapping of an area’s characteristics by a group of mobile and autonomous sensory agents. It is assumed that the agents utilize the wireless medium for communication, and have limited computational, storage and processing capabilities. These wireless sensory agents collaborate among each other in order to optimize their coverage tasks and communications. In this paper, we present a scheme that helps maximize the system’s efficiency through an adaptive coverage algorithm, where agents share information and collectively build a spatio-temporal view of the activity patterns of the area. Our scheme is particularly useful in applications where the events of interest exhibit an oscillatory behavior. Relevant applications include distant scouting and exploratory missions where the size and number of the scouting agents are crucial to the success of the mission.

The generation of sequential responses is a fundamental aspect of cognitive function, encompassing processes such as motor control, linguistic expression, memory recall and thought itself. There is considerable evidence that complex cognitive responses (such as voluntary actions) are constructed as chunked sequences of more elementary response primitives or synergies, which can themselves be seen often as sequences of simpler primitives. Almost all neural models of sequence representation are based on the principle of recurrence, where each successive item is generated by preceding items. However, it is also interesting to consider the possibility of purely spatial neural representations that result in sequential readout of pre-existing response elements. Such representations offer several potential benefits, including parsimony, efficiency, flexibility and generalization. In particular, they can allow response sequences to be stored in memory as chunks encoded by fixed point attractors. In this paper, we present a simple spiking neuron model for the flexible encoding and replay of response sequences through the impulsive triggering of coding patterns represented as fixed point attractors. While not intended as a detailed description of a specific brain region, the model seeks to capture fundamental control mechanisms that may apply in many parts of the nervous system.

The self-organization of social networks and the emergence of ideas have both been studied extensively in recent years, but seldom in a single framework. In this paper, we describe a distributed multi-agent model for the self-organization of social networks from encounters between agents with specific ideas, which are seen as combinations of words. Each agent maintains a semantic network of the words it knows, which implicitly defines the ideas in its repertoire. Agents exchange their ideas over their social networks, and incorporate the received ideas in their semantic networks. Social bonds are made and broken based on the agents' social and semantic preferences (i.e., shared ideas), leading to the emergence of social communities. Thus, the model embodies a circular interaction between the formation of social networks and new ideas. We mine the resulting communities for novel ideas that are generated by their members, and look at the effect of interaction choices on their formation.

This paper studies the distributed resource exploitation problem (DREP) where many resources are distributed across an unknown environment, and several agents move around in it with the goal to exploit/visit the resources. A resource may be anything that can be harvested/sensed/acted upon by an agent when the agent visits that resource’s physical location. A sensory agent (SA) is a mobile and autonomous sensory entity that has the capability of sensing a resource’s attribute and therefore determining the exploitatory gain factor or profitability when this resource is visited. This type of problem can be seen as a combination of two well-known problems: the Dynamic Traveling Salesman Problem (DTSP) [8] and the Vehicle Routing Problem (VRP) [1]. But the DREP differs significantly from these two. In the DTSP we have a single agent that needs to visit many fixed cities that have costs associated to their pairwise links, so it is an optimization of paths on a static graph with time-varying costs. In VRP on the other hand, we have a number of vehicles with uniform capacity, a common depot, and several stationary customers scattered around an environment, so the goal is to find the set of routes with overall minimum route cost to service all the customers. In our problem, we have multiple SAs deployed in an unknown environment with multiple dynamic resources each with a dynamically varying value. The goal of the SAs is to adapt their paths collaboratively to the dynamics of the resources in order to maximize the general profitability of the system.

Randomly deployed wireless sensor networks are becoming increasingly viable for many applications. Such networks can comprise anywhere from a few hundred to thousands of sensor nodes, and these sizes are likely to grow with advancing technology, making scalability a primary concern. Each node in these sensor networks is a small unit with limited resources and localized sensing and communication. Thus, all global tasks must be accomplished through self-organized distributed algorithms, which also leads to improved scalability, robustness and flexibility. In this paper, we examine the use of distributed algorithms to infer the spatial structure of an extended environment monitored by a self-organizing sensor network. Based on its sensing, the network segments the environment into regions with distinct characteristics, thereby inferring a cognitive map of the environment. This, in turn, can be used to answer global queries about the environment efficiently and accurately. The main challenge to the network arises from the necessarily irregular spatial sampling and the need for totally distributed computation. We consider distributed machine learning techniques for segmentation and study the variation of segmentation quality with reconstruction at different node densities and in environments of varying complexity.

A Wireless Sensor Network (WSN) is a set of sensor nodes that can communicate wirelessly with each other across an extended environment. Sensor networks are being used for various military, environmental, human-centric and robotic applications [Arampatzis 2005]. Most of the research on WSNs is focused on networks with identical nodes that have the same transmission range. This creates a homogeneous network whose connectivity can be modeled as an undirected graph. Homogenous networks are simple to analyze, but are well-known to be suboptimal with regard to efficiency, longevity and robustness [Yarvis 2005]. The random deployment of homogeneous nodes results in an uneven connectivity with critical nodes, making the network non-robust to node failure. A simple solution to overcome this problem would be to increase the transmission range of all nodes, but, this creates undue congestion in other parts of the network. In a heterogeneous network, in contrast, nodes can individually select their transmission range and tune their connectivity locally without creating congestion. This effectively reduces the number of hops between nodes without increasing bandwidth needs and energy. Though the resulting networks are more efficient and robust than homogeneous ones, they are difficult to analyze (see Duarte-Melo et al. [Duarte-Melo 2002] for some analysis).

Most research on wireless sensor networks has focused on homogeneous networks where all nodes have identical transmission ranges. However, heterogeneous networks, where nodes have different transmission ranges, are potentially much more efficient. In this chapter, we study how heterogeneous networks can be configured by distributed self-organization algorithms where each node selects its own transmission range based on local information. We define a specific performance function, and show empirically that self-organization based on local information produces networks that are close to optimal, and that including more information provides only marginal benefit. We also investigate whether the quality of networks configured by self-organization results from their generic connectivity distribution (as is argued for scale-free networks) or from their specific pattern of heterogeneous connectivity, finding the latter to be the case. The study confirms that heterogeneous networks outperform homogeneous ones, though with randomly deployed nodes, networks that seek homogeneous out-degree have an advantage over networks that simply use the same transmission range for all nodes. Finally, our simulation results show that highly optimized network configurations are as robust as non-optimized ones with respect to random node failure, but are much more susceptible to targeted attacks that preferentially remove nodes with the highest connectivity, confirming the trade-off between optimality and robustness postulated for optimized complex systems.

Understanding the neural mechanisms of the idea generation process has implications for research in brainstorming, creativity and innovation. In this paper we present a conceptual neural model for generating ideas. The model extends the associative memory model of Brown et al. (1998) by explicitly representing categories as networks of concepts and ideas as conceptual combinations. Simulation results are compared with experimental results on effects of priming on low, versus high accessibility categories.

Brainstorming is the process of generating ideas in a specific task or problem context.We have previously presented a connectionist framework to study the dynamics of idea generation in individuals. In this paper, we develop this model further, and apply it to studying qualitatively the effects of priming on the process of ideation. Motivated by experimental data from a previous study, we explore the differential effects of relevant and irrelevant primes on productivity of idea generation in specific problem/task contexts. Simulations using our model suggest that even irrelevant primes can provide a modest productivity boost in contexts that are familiar or are similar to familiar contexts, but no benefit when the context is unfamiliar. We propose possible explanations for these results and make predictions for future experiments.

In humans and primates, the sequential structure of complex actions is apparently learned at an abstract "cognitive" level in several regions of the frontal cortex, independent of the control of the immediate effectors by the motor system. At this level, actions are represented in terms of kinematic parameters --- especially direction of end effector movement --- and encoded using population codes. Muscle force signals are generated from this representation by downstream systems in the motor cortex and the spinal cord. In this paper, we consider the problem of learning population-coded kinematic sequences in an abstract neural network model of the medial frontal cortex. For concreteness, the sequences are represented as line drawings in a two-dimensional workspace. Learning such sequences presents several challenges because of the internal complexity of the individual sequences and extensive overlap between sequences. We show that, by using a simple module-selection mechanism, our model is capable of learning multiple sequences with complex structure and very high cross-sequence similarity.

A large-scale sensor network (LSSN) is formed when a very large number of sensor nodes with short-range communication capabilities are deployed randomly over an extended region. The random distribution of nodes in an LSSN leads to regions of varying density, which means that if all nodes have an identical transmission radius, the effective connectivity would vary over the system. This leads to inefficiency in energy usage (in regions of unnecessarily high connectivity) and the danger of partitioning (in regions of low node density). In this paper, we propose a technique for adapting a node’s transmission radius based on a node’s local information. Through localized coordination and self-organization, nodes try to attain fairly uniform connectivity in the system to aid in efficient data messaging in the system. We study the benefits of network adaptation by incorporating it into an adaptive geographical routing algorithm called corridor routing. We present simulation results showing significant improvement in performance over routing algorithms that do not use network adaptation. We also propose and study several scenarios for network adaptation in the presence of node failures, and explore the effect of parameter variation.

With advances in miniaturization, wireless communication, and the theory of self-organizing systems, it has become possible to consider scenarios where a very large number of networkable sensors are deployed randomly over an extended environment and organize themselves into a network. Such networks — which we term large-scale sensor networks (LSSN’s) — can be useful in many situations, including military surveillance, environmental monitoring, disaster relief, etc. The idea is that, by deploying an LSSN, an extended environment can be rendered observable for an external user (e.g., a monitoring station) or for users within the system (e.g., persons walking around with palm-sized devices). Unlike custom-designed networks, these randomly deployed networks need no pre-design and configure themselves through a process of self-organization. The sensor nodes themselves are typically anonymous, and information is addressed by location or attribute rather than by node ID. This approach provides several advantages, including: 1) Scalability; 2) Robustness; 3) Flexibility; 4) Expandability; and 5) Versatility. Indeed, this abstraction is implicit in such ideas as smart paint, smart dust, and smart matter.

Cognitive control -the ability to produce appropriate behavior in complex situations -is a fundamental aspect of intelligence. It is increasingly evident that this control arises from the interaction of dynamics in several brain regions, and depends significantly on processes of modulation and dynamical biasing. While most research has focused on explanations of behavioral responses seen in experiments and pathologies, it is reasonable to expect that internal functions such as planning and thinking would also use similar control mechanisms. In this paper, we present a connectionist model for an idea generation process that can rapidly retrieve old ideas in familiar contexts and search for novel ideas in unfamiliar ones. Based on a simple reinforcement signal, the system learns context-dependent biases that represent effective internal "response systems" for generating ideas from conceptual elements. A broad goal of the research is to show that preconfigured structural modularity, limited real-time selectivity, and adaptive modulation can interact to produce the flexible functionality necessary for cognition and intelligent behavior.

Ad hoc wireless sensor networks are emerging as an important technology for applications such as environmental monitoring, battlefield surveillance and infrastructure security. While most research so far has focused on the network aspects of these systems (e.g., routing, scheduling, etc.), the capacity for scalable, in-field information processing is potentially their most important attribute. Networks that can infer the phenomenological structure of their environment can use this knowledge to improve both their sensing performance and their resource usage. These intelligent networks would require much less a priori design, and be truly autonomous. This paper presents a distributed algorithm for inferring the global topological connectivity of an environment through a simple self-organization algorithm based on Hebbian learning. The application considers sensors distributed over an environment with a network of tracks on which vehicles of various types move according to rules unknown to the sensor network. Each sensor infers the local topology of the track network by comparing its observations with those from neighboring sensors. The complete topology of the network emerges from the distributed fusion of these local views.

Context is an essential part of all cognitive function. However, neural network models have only considered this issue in limited ways, focusing primarily on the conditioning of a system’s response by its recent history. This type of context, which we term Type I, is clearly relevant in many situations, but in other cases, the system’s response for an extended period must be conditioned by stimuli encountered at a specific earlier time. For example, the decision to turn left or right at an intersection point in a navigation task depends on the goal set at the beginning of the task. We term this type of context, which sets the “frame of reference” for an entire episode, Type II context. The prefrontal cortex in mammals has been hypothesized to perform this function, but it has been difficult to incorporate this into neural network models. In the present chapter, we describe an approach called latent attractors that allows self-organizing neural systems to simultaneously incorporate both Type I and Type II context dependency. We demonstrate this by applying the approach to a series of problems requiring one or both types of context. We also argue that the latent attractor approach is a general and flexible method for incorporating multi-scale temporal dependence into neural systems, and possibly other self-organized

While most existing research efforts in the area of wireless sensor networks have focused on networks with identical nodes, deploying sensors with different capabilities has become a feasible choice. In this paper, we focus on sensor networks with two types of nodes that differ in their capabilities, and discuss the effects of heterogeneity of sensing and transmission ranges on the network coverage and broadcast reachability. Our work characterizes how the introduction of a few sensor nodes with better capabilities can reduce the number of total required sensors without sacrificing the coverage and the broadcast reachability. Analytical results are validated via simulations. This work can serve as a guideline for designing large-scale sensor networks cost-effectively. It can also be extended to more complicated heterogeneous wireless sensor networks with more than two types of sensors.

Much of the research in the area of sensor networks is focused on homogeneous networks. Of late, there has been a steadily increasing amount of work on heterogeneous networks, mainly due to their flexibility and better fit into potential applications. In this paper, we present a heuristic, developed using a reverse engineering approach, that can be used to build efficient heterogeneous ad-hoc sensor networks based on a generic network model. A genetic algorithm is used to generate a set of heterogeneous sensor networks optimized for short paths and congestion. A thorough analysis of the optimal network set is done to extract rules and a heuristic is developed to embody these rules. The heuristic is then used to produce high-performance networks without genetic algorithms. We present simulation results and analysis of the heuristic networks and compare their performance with optimal heterogeneous networks as well as homogeneous networks.

In recent years, scientists have applied the principles of complex systems science to increasingly diverse fields. The results have been nothing short of remarkable: their novel approaches have provided answers to long-standing questions in biology, ecology, physics, engineering, computer science, economics, psychology and sociology. The Third International Conference on Complex Systems attracted over 400 researchers from around the world. The conference aimed to encourage cross-fertilization between the many disciplines represented and to deepen our understanding of the properties common to all complex systems.

In recent years, scientists have applied the principles of complex systems science to increasingly diverse fields. The results have been nothing short of remarkable: their novel approaches have provided answers to long-standing questions in biology, ecology, physics, engineering, computer science, economics, psychology and sociology. The Third International Conference on Complex Systems attracted over 400 researchers from around the world. The conference aimed to encourage cross-fertilization between the many disciplines represented and to deepen our understanding of the properties common to all complex systems.

This paper addresses the map building problem for cooperative search by a team of uninhabited air vehicles (UAVs) operating in an unknown and uncertain environment . We present and compare two evidential map-building approaches based on Bayesian theory and Dempster-Shafer theory respectively. We illustrate how to utilize the generated maps into the UAVs path planning procedure so that they could cooperatively localize targets in the environment. The simulation results illustrate the effectiveness of the proposed strategies.

The paper presents a neural model for learning sequences of relevant patterns embedded in distractors. A contextual episode is a sequence of relevant patterns - always in the same order - intermixed with distractors. By repeated presentations of all contextual episodes, the model discovers for each episode the set of relevant patterns and their order. The problem is solved in two stages: (a) by eliminating distractors, and (b) by learning the order between relevant patterns. The model uses the concept of latent attractors - essential in creating different neural representations for same patterns in distinct episodes. No external teacher and only Hebbian type learning rules are used.

Most algorithms for motion-based segmentation depend on the system's ability to estimate optic flow from successive image frames. Block-matching is often used for this, but it faces the problems of noise-sensitivity and texture-insufficiency. Recently, we proposed a two-pathway approach based on locally coupled neural networks to address this issue. The system uses a pixel-level (P) pathway to perform robust block-matching in regions with sufficient texture, and a region-level (R) pathway to estimate motion from feature matching in low-texture regions. The fused optic-flow from the P and R pathways is then segmented by a pulse-coupled neural network (PCNN). The algorithm has produced very good results on synthetic and natural images. We show that its performance shows significant robustness to additive noise in the images.

In this paper, we consider a heterogeneous team of UAVs drawn from several distinct classes and engaged in a search and destroy mission over an extended battlefield. Several different types of targets are considered. Some target locations are suspected a priori with a certain probability, while the others are initially unknown. During the mission, the UAVs perform Search, Confirm, Attack and Battle Damage Assessment (BDA) tasks at various locations. The target locations are detected gradually through search, while the tasks are determined in real-time by the actions of all UAVs and their results (e.g., sensor readings), which makes the task dynamics stochastic. The tasks must, therefore, be allocated to UAVs in real-time as they arise. Each class of UAVs has its own sensing and attack capabilities with respect to the different target types, so the need for appropriate and efficient assignment is paramount. We present a simple cooperative approach to this problem, based on distributed assignment mediated through centralized mission status information. Using this information, each UAV assesses the task opportunities available to it, and makes commitments through a phased incremental process. This produces a simple, flexible, scalable and inherently decentralizable method for task allocation. Concurrently, every UAV also monitors the degree to which various parts of the environment have been searched, and accommodates this information in planning its paths. We study the effect of various decision parameters, target distributions, and UAV team characteristics on the performance of our approach.

Latent attractor networks have been proposed as a possible mechanism for representing episodic context in the hippocampus, and as general purpose models of episodic context-dependent encoding in neural networks. These are recurrent neural networks with attractors that never fully manifest themselves, but bias the network's response to external stimuli. While each attractor in the original latent attractor model was triggered by unique context patterns specific to the context, this model was later extended to the case where contexts were triggered progressively by the sequential presentation of several stimulus patterns without regard to order, simulating the more realistic situation where a context is identified by a sequentially scanned combination of landmarks. In this paper, we describe a network model that can select among contexts identified by overlapping sequences of different lengths, even if the relevant stimulus patterns are interspersed among patterns irrelevant to context selection.

This paper addresses the problem of cooperative search in a given environment by a team of unmanned aerial vehicles (UAVs). We present a decentralized control model for cooperative search and develop a real-time approach for online cooperation among vehicles, which is based on treating the possible paths of other vehicles as "soft obstacles" to be avoided. Using the approach of "rivaling force" between vehicles to enhance cooperation, each UAV takes into account the possible actions of other UAVs such that the overall information about the environment is increased. The simulation results illustrate the effectiveness of the proposed strategy.

Uninhabited autonomous vehicles(UAVs) are an increasingly important part of battlefield environments, and may soon be common in civilian applications such as disaster relief, environmental monitoring and planetary exploration. Such vehicles may be airborne, land-based or aquatic, though the focus so far has been on airborne vehicles for military applications, and this is the focus of the research presented here. We consider a heterogeneous group of UAVs drawn from several distinct classes and engaged in a search and destroy mission over an extended battlefield. During the mission, the UAVs perform Search,Confirm, Attack andBattle Damage Assessment (BDA) tasks at various locations. The tasks are determined in real-time by the actions of all UAVs and their consequences (e.g.,sensor readings), so that the task dynamics are stochastic. The tasks must, therefore, be allocated to UAVs in real-time as they arise, while ensuring that appropriate vehicles are assigned to each task. Each class of UAVs has its own sensing and attack capabilities, so the need for appropriate assignment is paramount.

In this paper, we consider a heterogeneous team of UAVs drawn from several distinct classes and engaged in a search and destroy mission over a spatially extended battlefield with targets of several types. Some target locations are suspected a priori with a certain probability, while the rest need to be detected gradually through search. The tasks are determined in real-time by the actions of all UAVs and their consequences (e.g., sensor readings), which makes the task dynamics stochastic. The tasks must, therefore, be allocated to UAVs in real-time as they arise. Quick response is more important for known targets, while efficient search is necessary to discover hidden targets. Prediction may help when most targets are known a priori, but could hurt when they are not. In this paper, we study how the benefit of such prediction may depend on the number of targets and UAVs. In particular, we show that there is a trade-off between search and task response in the context of prediction. Based on the results, we propose a hybrid algorithm which balances the search and task response. The performance of proposed algorithms is evaluated through Monte Carlo simulations.

Uninhabited autonomous vehicles (UAVs) have many useful military applications, including reconnaissance, search-and-destroy, and search-and-rescue missions in hazardous environments such as battlefields or disaster areas. Recently, there has been considerable interest in the possibility of using large teams (swarms) of UAVs functioning cooperatively to accomplish a large number of tasks (e.g., finding and attacking targets). However, this requires the assignment of multiple spatially distributed tasks to each UAV along with a feasible path that minimizes effort and avoids threats.

A decentralized cooperative strategy for cooperative search by a team of mobile agents (of particular interest is the case of unmanned air vehicles) is presented, where cooperation is accomplished by having each agent take into account the other agents' possible actions. The preliminary associated analysis shows that the proposed strategy guarantees a complete global search of the environment, gives a lower bound on the search time and shows that it is finite.

Latent attractor networks are recurrent neural networks with weak attractors that bias the network's response to external stimuli but never fully manifest themselves. Such networks have been used to model context-dependent place representations in the hippocampus, and to encode context-dependent stimuli in neural networks. In the original latent attractor model, each attractor was triggered by a unique context pattern representing a stimulus that uniquely identified the context of the subsequent episode. This model was later extended to the case where contexts were triggered progressively by the sequential presentation of several stimulus patterns without regard to order. In this paper, we describe a network model that can select contexts even if the triggering stimulus patterns are interspersed among patterns irrelevant to context selection. This is closer to the way such a process would occur cognitively, where contexts are typically recognized based on a subset of sequentially perceived identifiers or cues among a larger set of perceived items.

Searching a spatially extended environment using autonomous mobile agents is a problem that arises in many applications, e.g., search-and-rescue, search-and-destroy, intelligence gathering, surveillance, disaster response, exploration, etc. Since agents such as UAV's are often energy-limited and operate in a hostile environment, there is a premium on efficient cooperative search without superfluous communication. In this paper, we consider how a group of mobile agents, using only limited messages and incomplete information, can learn to search an environment efficiently. In particular, we consider the issue of centralized vs. decentralized intelligence and the effect of opportunistic sharing of learned information on search performance.

Attractor networks have been one of the most successful paradigms in neural computation, and have been used as models of computation in the nervous system. Recently, we proposed a paradigm called 'latent attractors' where attractors embedded in a recurrent network via Hebbian learning are used to channel network response to external input rather than becoming manifest themselves. This allows the network to generate context-sensitive internal codes in complex situations. Latent attractors are particularly helpful in explaining computations within the hippocampus--a brain region of fundamental significance for memory and spatial learning. Latent attractor networks are a special case of associative memory networks. The model studied here consists of a two-layer recurrent network with attractors stored in the recurrent connections using a clipped Hebbian learning rule. The firing in both layers is competitive--K winners take all firing. The number of neurons allowed to fire, K, is smaller than the size of the active set of the stored attractors. The performance of latent attractor networks depends on the number of such attractors that a network can sustain. In this paper, we use signal-to-noise methods developed for standard associative memory networks to do a theoretical and computational analysis of the capacity and dynamics of latent attractor networks. This is an important first step in making latent attractors a viable tool in the repertoire of neural computation. The method developed here leads to numerical estimates of capacity limits and dynamics of latent attractor networks. The technique represents a general approach to analyse standard associative memory networks with competitive firing. The theoretical analysis is based on estimates of the dendritic sum distributions using Gaussian approximation. Because of the competitive firing property, the capacity results are estimated only numerically by iteratively computing the probability of erroneous firings. The analysis contains two cases: the simple case analysis which accounts for the correlations between weights due to shared patterns and the detailed case analysis which includes also the temporal correlations between the network's present and previous state. The latter case predicts better the dynamics of the network state for non-zero initial spurious firing. The theoretical analysis also shows the influence of the main parameters of the model on the storage capacity.

An approach for the secure transmission of encrypted messages using chaos and noise is presented in this paper. The method is based on the synchronization of certain types of chaotic oscillators in response to a common noise input. This allows two distant oscillators to generate identical output which can be used as a key for encryption and decryption of a message signal. The noiselike synchronizing input-which contains no message information-is communicated to identical oscillators in the transmitter and the receiver over a public channel. The encrypted message is also sent over a public channel, while the key is never transmitted at all. The chaotic nature of the oscillators which generate the key and the randomness of the signal driving the process combine to make the recovery of the key by an eavesdropper extremely difficult. We evaluate system performance with respect to security and robustness and show that a robust and secure system can be obtained. (c) 1998 American Institute of Physics.