A Neural Network Model of Spatio-Temporal Pattern Recognition, Recall and Timing

This paper describes the design of a self~organizing, hierarchical neural network model of unsupervised serial learning. The model learns to recognize, store, and recall sequences of unitized patterns, using either short-term memory (STM) or both STM and long-term memory (LTM) mechanisms. Timing information is learned and recall {both from STM and from LTM) is performed with a learned rhythmical structure. The network, bearing similarities with ART (Carpenter & Grossberg 1987a), learns to map temporal sequences to unitized patterns, which makes it suitable for hierarchical operation. It is therefore capable of self-organizing codes for sequences of sequences. The capacity is only limited by the number of nodes provided. Selected simulation results are reported to illustrate system properties.

Store Working Memory Networks for Storage and Recall of Arbitrary Temporal Sequences

Neural network models of working memory, called Sustained Temporal Order REcurrent (STORE) models, are described. They encode the invariant temporal order of sequential events in short term memory (STM) in a way that mimics cognitive data about working memory, including primacy, recency, and bowed order and error gradients. As new items are presented, the pattern of previously stored items is invariant in the sense that, relative activations remain constant through time. This invariant temporal order code enables all possible groupings of sequential events to be stably learned and remembered in real time, even as new events perturb the system. Such a competence is needed to design self-organizing temporal recognition and planning systems in which any subsequence of events may need to be categorized in order to to control and predict future behavior or external events. STORE models show how arbitrary event sequences may be invariantly stored, including repeated events. A preprocessor interacts with the working memory to represent event repeats in spatially separate locations. It is shown why at least two processing levels are needed to invariantly store events presented with variable durations and interstimulus intervals. It is also shown how network parameters control the type and shape of primacy, recency, or bowed temporal order gradients that will be stored.

Collocation Games and Their Application to Distributed Resource Management

We introduce Collocation Games as the basis of a general framework for modeling, analyzing, and facilitating the interactions between the various stakeholders in distributed systems in general, and in cloud computing environments in particular. Cloud computing enables fixed-capacity (processing, communication, and storage) resources to be offered by infrastructure providers as commodities for sale at a fixed cost in an open marketplace to independent, rational parties (players) interested in setting up their own applications over the Internet. Virtualization technologies enable the partitioning of such fixed-capacity resources so as to allow each player to dynamically acquire appropriate fractions of the resources for unencumbered use. In such a paradigm, the resource management problem reduces to that of partitioning the entire set of applications (players) into subsets, each of which is assigned to fixed-capacity cloud resources. If the infrastructure and the various applications are under a single administrative domain, this partitioning reduces to an optimization problem whose objective is to minimize the overall deployment cost. In a marketplace, in which the infrastructure provider is interested in maximizing its own profit, and in which each player is interested in minimizing its own cost, it should be evident that a global optimization is precisely the wrong framework. Rather, in this paper we use a game-theoretic framework in which the assignment of players to fixed-capacity resources is the outcome of a strategic "Collocation Game". Although we show that determining the existence of an equilibrium for collocation games in general is NP-hard, we present a number of simplified, practically-motivated variants of the collocation game for which we establish convergence to a Nash Equilibrium, and for which we derive convergence and price of anarchy bounds. In addition to these analytical results, we present an experimental evaluation of implementations of some of these variants for cloud infrastructures consisting of a collection of multidimensional resources of homogeneous or heterogeneous capacities. Experimental results using trace-driven simulations and synthetically generated datasets corroborate our analytical results and also illustrate how collocation games offer a feasible distributed resource management alternative for autonomic/self-organizing systems, in which the adoption of a global optimization approach (centralized or distributed) would be neither practical nor justifiable.

Information Fusion and Hierarchical Knowledge Discovery by ARTMAP Neural Networks

Mapping novel terrain from sparse, complex data often requires the resolution of conflicting information from sensors working at different times, locations, and scales, and from experts with different goals and situations. Information fusion methods help resolve inconsistencies in order to distinguish correct from incorrect answers, as when evidence variously suggests that an object's class is car, truck, or airplane. The methods developed here consider a complementary problem, supposing that information from sensors and experts is reliable though inconsistent, as when evidence suggests that an objects class is car, vehicle, or man-made. Underlying relationships among objects are assumed to be unknown to the automated system of the human user. The ARTMAP information fusion system uses distributed code representations that exploit the neural network's capacity for one-to-many learning in order to produce self-organizing expert systems that discover hierarchial knowledge structures. The system infers multi-level relationships among groups of output classes, without any supervised labeling of these relationships. The procedure is illustrated with two image examples.

SOVEREIGN: An Autonomous Neural System for Incrementally Learning Planned Action Sequence to Navigate Towards a Rewarded Goal

How do reactive and planned behaviors interact in real time? How are sequences of such behaviors released at appropriate times during autonomous navigation to realize valued goals? Controllers for both animals and mobile robots, or animats, need reactive mechanisms for exploration, and learned plans to reach goal objects once an environment becomes familiar. The SOVEREIGN (Self-Organizing, Vision, Expectation, Recognition, Emotion, Intelligent, Goaloriented Navigation) animat model embodies these capabilities, and is tested in a 3D virtual reality environment. SOVEREIGN includes several interacting subsystems which model complementary properties of cortical What and Where processing streams and which clarify similarities between mechanisms for navigation and arm movement control. As the animat explores an environment, visual inputs are processed by networks that are sensitive to visual form and motion in the What and Where streams, respectively. Position-invariant and sizeinvariant recognition categories are learned by real-time incremental learning in the What stream. Estimates of target position relative to the animat are computed in the Where stream, and can activate approach movements toward the target. Motion cues from animat locomotion can elicit head-orienting movements to bring a new target into view. Approach and orienting movements are alternately performed during animat navigation. Cumulative estimates of each movement are derived from interacting proprioceptive and visual cues. Movement sequences are stored within a motor working memory. Sequences of visual categories are stored in a sensory working memory. These working memories trigger learning of sensory and motor sequence categories, or plans, which together control planned movements. Predictively effective chunk combinations are selectively enhanced via reinforcement learning when the animat is rewarded. Selected planning chunks effect a gradual transition from variable reactive exploratory movements to efficient goal-oriented planned movement sequences. Volitional signals gate interactions between model subsystems and the release of overt behaviors. The model can control different motor sequences under different motivational states and learns more efficient sequences to rewarded goals as exploration proceeds.

Fusion Artmap: A Neural Network Architecture for Multi-Channel Data Fusion and Classification

Fusion ARTMAP is a self-organizing neural network architecture for multi-channel, or multi-sensor, data fusion. Single-channel Fusion ARTMAP is functionally equivalent to Fuzzy ART during unsupervised learning and to Fuzzy ARTMAP during supervised learning. The network has a symmetric organization such that each channel can be dynamically configured to serve as either a data input or a teaching input to the system. An ART module forms a compressed recognition code within each channel. These codes, in turn, become inputs to a single ART system that organizes the global recognition code. When a predictive error occurs, a process called paraellel match tracking simultaneously raises vigilances in multiple ART modules until reset is triggered in one of them. Parallel match tracking hereby resets only that portion of the recognition code with the poorest match, or minimum predictive confidence. This internally controlled selective reset process is a type of credit assignment that creates a parsimoniously connected learned network. Fusion ARTMAP's multi-channel coding is illustrated by simulations of the Quadruped Mammal database.

Rule Extraction, Fuzzy ARTMAP, and Medical Databases

This paper shows how knowledge, in the form of fuzzy rules, can be derived from a self-organizing supervised learning neural network called fuzzy ARTMAP. Rule extraction proceeds in two stages: pruning removes those recognition nodes whose confidence index falls below a selected threshold; and quantization of continuous learned weights allows the final system state to be translated into a usable set of rules. Simulations on a medical prediction problem, the Pima Indian Diabetes (PID) database, illustrate the method. In the simulations, pruned networks about 1/3 the size of the original actually show improved performance. Quantization yields comprehensible rules with only slight degradation in test set prediction performance.

Fusion ARTMAP: An Adaptive Fuzzy Network for Multi-Channel Classification

Fusion ARTMAP is a self-organizing neural network architecture for multi-channel, or multi-sensor, data fusion. Fusion ARTMAP generalizes the fuzzy ARTMAP architecture in order to adaptively classify multi-channel data. The network has a symmetric organization such that each channel can be dynamically configured to serve as either a data input or a teaching input to the system. An ART module forms a compressed recognition code within each channel. These codes, in turn, beco1ne inputs to a single ART system that organizes the global recognition code. When a predictive error occurs, a process called parallel match tracking simultaneously raises vigilances in multiple ART modules until reset is triggered in one of thmn. Parallel match tracking hereby resets only that portion of the recognition code with the poorest match, or minimum predictive confidence. This internally controlled selective reset process is a type of credit assignment that creates a parsimoniously connected learned network.

Towards a Unified Theory of Neocortex: Laminar Cortical Circuits for Vision and Cognition

A key goal of computational neuroscience is to link brain mechanisms to behavioral functions. The present article describes recent progress towards explaining how laminar neocortical circuits give rise to biological intelligence. These circuits embody two new and revolutionary computational paradigms: Complementary Computing and Laminar Computing. Circuit properties include a novel synthesis of feedforward and feedback processing, of digital and analog processing, and of pre-attentive and attentive processing. This synthesis clarifies the appeal of Bayesian approaches but has a far greater predictive range that naturally extends to self-organizing processes. Examples from vision and cognition are summarized. A LAMINART architecture unifies properties of visual development, learning, perceptual grouping, attention, and 3D vision. A key modeling theme is that the mechanisms which enable development and learning to occur in a stable way imply properties of adult behavior. It is noted how higher-order attentional constraints can influence multiple cortical regions, and how spatial and object attention work together to learn view-invariant object categories. In particular, a form-fitting spatial attentional shroud can allow an emerging view-invariant object category to remain active while multiple view categories are associated with it during sequences of saccadic eye movements. Finally, the chapter summarizes recent work on the LIST PARSE model of cognitive information processing by the laminar circuits of prefrontal cortex. LIST PARSE models the short-term storage of event sequences in working memory, their unitization through learning into sequence, or list, chunks, and their read-out in planned sequential performance that is under volitional control. LIST PARSE provides a laminar embodiment of Item and Order working memories, also called Competitive Queuing models, that have been supported by both psychophysical and neurobiological data. These examples show how variations of a common laminar cortical design can embody properties of visual and cognitive intelligence that seem, at least on the surface, to be mechanistically unrelated.

Working Memory Networks for Learning Multiple Groupings of Temporarily Ordered Events: Applications to 3-D Visual Object Recognition

Working memory neural networks are characterized which encode the invariant temporal order of sequential events that may be presented at widely differing speeds, durations, and interstimulus intervals. This temporal order code is designed to enable all possible groupings of sequential events to be stably learned and remembered in real time, even as new events perturb the system. Such a competence is needed in neural architectures which self-organize learned codes for variable-rate speech perception, sensory-motor planning, or 3-D visual object recognition. Using such a working memory, a self-organizing architecture for invariant 3-D visual object recognition is described that is based on the model of Seibert and Waxman [1].

ART 2-A: An Adaptive Resonance Algorithm for Rapid Category Learning and Recognition

This article introduces ART 2-A, an efficient algorithm that emulates the self-organizing pattern recognition and hypothesis testing properties of the ART 2 neural network architecture, but at a speed two to three orders of magnitude faster. Analysis and simulations show how the ART 2-A systems correspond to ART 2 dynamics at both the fast-learn limit and at intermediate learning rates. Intermediate learning rates permit fast commitment of category nodes but slow recoding, analogous to properties of word frequency effects, encoding specificity effects, and episodic memory. Better noise tolerance is hereby achieved without a loss of learning stability. The ART 2 and ART 2-A systems are contrasted with the leader algorithm. The speed of ART 2-A makes practical the use of ART 2 modules in large-scale neural computation.

A Neural Network Architecture for Figure-ground Separation of Connected Scenic Figures

A neural network model, called an FBF network, is proposed for automatic parallel separation of multiple image figures from each other and their backgrounds in noisy grayscale or multi-colored images. The figures can then be processed in parallel by an array of self-organizing Adaptive Resonance Theory (ART) neural networks for automatic target recognition. An FBF network can automatically separate the disconnected but interleaved spirals that Minsky and Papert introduced in their book Perceptrons. The network's design also clarifies why humans cannot rapidly separate interleaved spirals, yet can rapidly detect conjunctions of disparity and color, or of disparity and motion, that distinguish target figures from surrounding distractors. Figure-ground separation is accomplished by iterating operations of a Feature Contour System (FCS) and a Boundary Contour System (BCS) in the order FCS-BCS-FCS, hence the term FBF, that have been derived from an analysis of biological vision. The FCS operations include the use of nonlinear shunting networks to compensate for variable illumination and nonlinear diffusion networks to control filling-in. A key new feature of an FBF network is the use of filling-in for figure-ground separation. The BCS operations include oriented filters joined to competitive and cooperative interactions designed to detect, regularize, and complete boundaries in up to 50 percent noise, while suppressing the noise. A modified CORT-X filter is described which uses both on-cells and off-cells to generate a boundary segmentation from a noisy image.

Adaptive Resonance Associative Map: A Hierarchical ART System for Fast Stable Associative Learning

This paper introduces a new class of predictive ART architectures, called Adaptive Resonance Associative Map (ARAM) which performs rapid, yet stable heteroassociative learning in real time environment. ARAM can be visualized as two ART modules sharing a single recognition code layer. The unit for recruiting a recognition code is a pattern pair. Code stabilization is ensured by restricting coding to states where resonances are reached in both modules. Simulation results have shown that ARAM is capable of self-stabilizing association of arbitrary pattern pairs of arbitrary complexity appearing in arbitrary sequence by fast learning in real time environment. Due to the symmetrical network structure, associative recall can be performed in both directions.

Vector Associative Maps: Unsupervised Real-time Error-based Learning and Control of Movement Trajectories

This article describes neural network models for adaptive control of arm movement trajectories during visually guided reaching and, more generally, a framework for unsupervised real-time error-based learning. The models clarify how a child, or untrained robot, can learn to reach for objects that it sees. Piaget has provided basic insights with his concept of a circular reaction: As an infant makes internally generated movements of its hand, the eyes automatically follow this motion. A transformation is learned between the visual representation of hand position and the motor representation of hand position. Learning of this transformation eventually enables the child to accurately reach for visually detected targets. Grossberg and Kuperstein have shown how the eye movement system can use visual error signals to correct movement parameters via cerebellar learning. Here it is shown how endogenously generated arm movements lead to adaptive tuning of arm control parameters. These movements also activate the target position representations that are used to learn the visuo-motor transformation that controls visually guided reaching. The AVITE model presented here is an adaptive neural circuit based on the Vector Integration to Endpoint (VITE) model for arm and speech trajectory generation of Bullock and Grossberg. In the VITE model, a Target Position Command (TPC) represents the location of the desired target. The Present Position Command (PPC) encodes the present hand-arm configuration. The Difference Vector (DV) population continuously.computes the difference between the PPC and the TPC. A speed-controlling GO signal multiplies DV output. The PPC integrates the (DV)·(GO) product and generates an outflow command to the arm. Integration at the PPC continues at a rate dependent on GO signal size until the DV reaches zero, at which time the PPC equals the TPC. The AVITE model explains how self-consistent TPC and PPC coordinates are autonomously generated and learned. Learning of AVITE parameters is regulated by activation of a self-regulating Endogenous Random Generator (ERG) of training vectors. Each vector is integrated at the PPC, giving rise to a movement command. The generation of each vector induces a complementary postural phase during which ERG output stops and learning occurs. Then a new vector is generated and the cycle is repeated. This cyclic, biphasic behavior is controlled by a specialized gated dipole circuit. ERG output autonomously stops in such a way that, across trials, a broad sample of workspace target positions is generated. When the ERG shuts off, a modulator gate opens, copying the PPC into the TPC. Learning of a transformation from TPC to PPC occurs using the DV as an error signal that is zeroed due to learning. This learning scheme is called a Vector Associative Map, or VAM. The VAM model is a general-purpose device for autonomous real-time error-based learning and performance of associative maps. The DV stage serves the dual function of reading out new TPCs during performance and reading in new adaptive weights during learning, without a disruption of real-time operation. YAMs thus provide an on-line unsupervised alternative to the off-line properties of supervised error-correction learning algorithms. YAMs and VAM cascades for learning motor-to-motor and spatial-to-motor maps are described. YAM models and Adaptive Resonance Theory (ART) models exhibit complementary matching, learning, and performance properties that together provide a foundation for designing a total sensory-cognitive and cognitive-motor autonomous system.