By Topic

Neural Networks (IJCNN), The 2013 International Joint Conference on

Date 4-9 Aug. 2013

Filter Results

Displaying Results 1 - 25 of 437
  • [Title page]

    Page(s): 1 - 2
    Save to Project icon | Request Permissions | PDF file iconPDF (51 KB)  
    Freely Available from IEEE
  • [Copyright notice]

    Page(s): 1
    Save to Project icon | Request Permissions | PDF file iconPDF (60 KB)  
    Freely Available from IEEE
  • Approximate dynamic programming solutions of multi-agent graphical games using actor-critic network structures

    Page(s): 1 - 8
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1207 KB)  

    This paper studies a new class of multi-agent discrete-time dynamical graphical games, where interactions between agents are restricted by a communication graph structure. The paper brings together discrete Hamiltonian mechanics, optimal control theory, cooperative control, game theory, reinforcement learning, and neural network structures to solve the multi-agent dynamical graphical games. Graphical game Bellman equations are derived and shown to be equivalent to certain graphical game Hamilton Jacobi Bellman equations developed herein. Reinforcement Learning techniques are used to solve these dynamical graphical games. Heuristic Dynamic Programming and Dual Heuristic Programming, are extended to solve the graphical games using only neighborhood information. Online adaptive learning structure is implemented using actor-critic networks to solve these graphical games. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Behavioral economics and neuroeconomics: Cooperation, competition, preference, and decision making

    Page(s): 1 - 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (173 KB) |  | HTML iconHTML  

    Behavioral economics and neuroeconomics concern how humans process multiple alternatives to make their decisions, and propose how discoveries about how the brain works can inform models of economic behavior. This lecture will survey how results about cooperative-competitive and cognitive-emotional dynamics that were discovered to better understand how brains control behavior can shed light on issues of importance in economics, including results about the voting paradox, how to design stable economic markets, irrational decision making under risk (Prospect Theory), probabilistic decision making, preferences for previously unexperienced alternatives over rewarded experiences, and bounded rationality. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • John Gerald Taylor: Comrade, polymath, and consummate neuroscientist — Reminiscences of life together under the Aegis of INNS

    Page(s): 1 - 3
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (168 KB) |  | HTML iconHTML  

    The author reviews the career of the late neural network pioneer John Taylor, including reminiscences of twenty years of close professional association and friendship. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • John Taylor, learning, attention, and consciousness

    Page(s): 1 - 3
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (121 KB) |  | HTML iconHTML  

    This invited talk will begin with an appreciation of John Taylor and then present a review of classical and recent research results on topics that were of particular interest to John Taylor, notably neural models that contribute to our understanding of how attention and consciousness work. This extended abstract summarizes some of the main themes of the talk. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • The race to new mathematics of brains and consciousness — A tribute to John G. Taylor

    Page(s): 1 - 3
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (170 KB) |  | HTML iconHTML  

    This contribution presents a review of mathematical approaches to modeling brains and higher cognitive activity, including consciousness. We dedicate this paper to John Gerard Taylor on the somber occasion of remembering his lifelong contribution to science, with a focus on his pioneering work on neural networks and brain studies. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Cognitive models of the perception-action cycle: A view from the brain

    Page(s): 1 - 8
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (410 KB)  

    Perception-action cycle is the circular flow of information that takes place between an organism and its environment in the course of a sensory-guided sequence of actions towards a goal. Each action causes changes in the environment which are processed by the organism's sensory hierarchy and lead to the generation of further action by its motor effectors. These actions cause new changes that are sensory analyzed and lead to a new action, and so the cycle continues. The efficient and timely coordination of the sensory and motor structures involved will ensure the organism's survival in a dynamic environment. Two brain inspired cognitive models of the perception-action cycle are presented in this paper: (1) A cognitive model of visual saliency, overt attention and active visual search, and (2) A cognitive model of visuo-motor coordination of reaching and grasping. Both models are multi-modular. They share a number of features (visual saliency, focus of attention, recognition, expectation, resonance, value attribution), while at the same time have distinct properties. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • In search of the brain's executive

    Page(s): 1 - 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (229 KB) |  | HTML iconHTML  

    In unpublished work over about ten years starting in 1995, John Taylor, Raju Bapi, Guido Bugmann, Neill Taylor, and I developed a network theory of the cognitive functions of the frontal lobes. We dealt with the long popular notion of the prefrontal region as executive of the brain [1]. Some cognitive neuroscientists had called for abandoning the executive idea because the functions of planning, organizing, and controlling behavior were distributed over many brain regions and not run by a single “homunculus.” Yet we believed that the executive concept was still useful if we analyzed it in system terms, including the executive functions of the prefrontal's connections with other areas, notably basal ganglia and thalamus; parietal, premotor, and secondary sensory cortices; and amygdala. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Toward a cooperative brain: Continuing the work with John Taylor

    Page(s): 1 - 5
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (942 KB) |  | HTML iconHTML  

    I propose a three-step discussion following a research path shared in part with John Taylor where the leitmotif is to understand the cooperation between thinking agents: the pRAM architecture, the butler paradigm, and the networked intelligence. All three steps comprise keystones of European projects which one of us has coordinated. The principled philosophy is to “start simple and insert progressive complexity”. The results I discuss only go as far as the “start simple” point. The final goal is to find a bias that underpins the entire research effort. In this paper I will move within the connectionist paradigm at various scales, the largest being one that encompasses an Internet of Things instantiation. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Cognitive computation: A case study in cognitive control of autonomous systems and some future directions

    Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (3150 KB) |  | HTML iconHTML  

    Cognitive computation is an emerging discipline linking together neurobiology, cognitive psychology and artificial intelligence. Springer Neuroscience has launched a journal in this exciting multidisciplinary topic, which seeks to publish biologically inspired theoretical, computational, experimental and integrative accounts of all aspects of natural and artificial cognitive systems. In this keynote, we outline and build on some of the pioneering work of the late Professor John Taylor, who was also founding Advisory Board Chair of Cognitive Computation, specifically his proposal on how to create a cognitive machine equipped with multi-modal cognitive capabilities. In this context, we first present a novel modular cognitive control framework for autonomous systems that could potentially realize the required cognitive action-selection and learning capabilities in Professor Taylor's envisaged cognitive machine. An ongoing case study in autonomous vehicle control is described, as a benchmark problem, with encouraging preliminary results in a range of realistic driving scenarios - and with significant potential fuel and emission economy implications, compared to conventional control systems. Finally, possible future avenues are explored, including our ongoing work aimed at developing a general modular cognitive framework incorporating multiple modalities, including vision, motor action, language and emotion, required for enabling multi-modal social cognitive and affective behavioral capabilities in future autonomous agents. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • On the interplay between “learning, memory, prospection and abstraction” in cumulatively learning baby humanoids

    Page(s): 1 - 10
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1711 KB) |  | HTML iconHTML  

    We all `inhabit' continuously changing unstructured worlds where neither everything can be known nor can everything be experienced. The lifelong interplay between neural mechanisms associated with learning, memory, prospection and abstraction play a fundamental role in enabling cognitive agents to effortlessly connect their `past' with the `available present' and `possible future', most often in the context of realization of one's internal goals (and taking into account neurobiological and physical constraints related to one's embodiment). Investigation into the computational and neural basis underlying such mechanisms have value both from an intrinsic viewpoint of better understanding our own selves and at the same time creating artifacts that can flexibly assist us in the environments we inhabit and create (domestic, industrial, several others). Simply put, beyond a certain point a software programmer cannot travel the journey of a cognitive robot, they must learn to do it themselves! Enabling them to do so offers us with a unique opportunity to reenact the gradual process of infant developmental learning and investigate deeper into the underlying interplay between multiple fundamental cognitive processes from the perspective of an “integrated system” (human or humanoid that perceives, acts, learns, forgets and reasons). The article reports some advanced experiments conducted on the baby humanoid iCub to this effect, mainly 1. Learning to push and begin to anticipate how objects move, use this knowledge and 2. Learning to build the tallest possible stack given a random set of objects to play with (learning going on cumulatively in an open ended fashion). These playful experiments are used to summarize the gradually evolving cognitive architecture of the young EU funded project DARWIN. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Bubbles in the robot

    Page(s): 1 - 2
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (289 KB) |  | HTML iconHTML  

    Dynamic Neural Field models have been used extensively to model brain functions, but mostly through computer simulations. However, there are recent examples of applications in robotics that I will discuss in this presentation. I will also discuss neurocognitive robotics that has the aim of understanding brain functions in contrast to neuromorphic robotics that has mainly the aim of solving robotics tasks with biologically inspired method. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Point cloud data filtering and downsampling using growing neural gas

    Page(s): 1 - 8
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1198 KB) |  | HTML iconHTML  

    3D sensors provide valuable information for mobile robotic tasks like scene classification or object recognition, but these sensors often produce noisy data that makes impossible applying classical keypoint detection and feature extraction techniques. Therefore, noise removal and downsampling have become essential steps in 3D data processing. In this work, we propose the use of a 3D filtering and downsampling technique based on a Growing Neural Gas (GNG) network. GNG method is able to deal with outliers presents in the input data. These features allows to represent 3D spaces, obtaining an induced Delaunay Triangulation of the input space. Experiments show how GNG method yields better input space adaptation to noisy data than other filtering and downsampling methods like Voxel Grid. It is also demonstrated how the state-of-the-art keypoint detectors improve their performance using filtered data with GNG network. Descriptors extracted on improved keypoints perform better matching in robotics applications as 3D scene registration. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A semi-parametric approach for football video annotation

    Page(s): 1 - 7
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1515 KB) |  | HTML iconHTML  

    Automatic sports video segmentation is a fast growth area of research in the visual information retrieval field. This paper presents a semi-parametric algorithm for parsing football video structures. The approach works on a two interleaved based process that closely collaborate towards a common goal. The core part of the proposed method focus performs a fast automatic football video annotation by looking at the enhance entropy variance within a series of shot frames. The entropy is extracted on the Hue parameter from the HSV color system, not as a global feature but in spatial domain to identify regions within a shot that will characterize a certain activity within the shot period. The second part of the algorithm works towards the identification of dominant color regions that could represent players and playfield for further activity recognition. Experimental results shows that the proposed football video segmentation algorithm performs with high accuracy. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Alignment-based transfer learning for robot models

    Page(s): 1 - 7
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1147 KB) |  | HTML iconHTML  

    Robot manipulation tasks require on robot models. When exact physical parameters of the robot are not available, learning robot models from data becomes an appealing alternative. Most learning approaches are formulated in a supervised learning framework and are based on clearly defined training sets. We propose a method that improves the learning process by using additional data obtained from other experiments of the robot or even from experiments with different robot architectures. Incorporating experiences from other experiments requires transfer learning that has been used with success in machine learning. The proposed method can be used for arbitrary robot model, together with any type of learning algorithm. Experimental results indicate that task transfer between different robot architectures is a sound concept. Furthermore, clear improvement is gained on forward kinematics model learning in a task-space control task. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Novelty estimation in developmental networks: Acetylcholine and norepinephrine

    Page(s): 1 - 8
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1160 KB) |  | HTML iconHTML  

    The receiver operating characteristic (ROC) curve has been widely applied to classifiers to show how the threshold value for acceptance changes the true positive rate and the false positive rate of the detection jointly. However, it is largely unknown how a biological brain autonomously selects a confidence value for each detection case. In the reported work, we investigated this issue based on the class of Developmental Networks (DNs) which have a power of abstraction similar to symbolic finite automata (FA) but all the DN's representations are emergent (i.e., numeric from the physical world and non-symbolic). Our theory is based on two types of neurotransmitters: Acetylcholine (Ach) and Norepinephrine (NE). Inspired by studies that proposed Ach and NE represent uncertainty and unpredicted uncertainty, respectively, we model how a DN uses Ach and NE to allow neurons to collectively decide acceptance or rejection by estimated novelty based on past experience, instead of using a single threshold value. This is a neural network, distributed, incremental, automatic version of ROC. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Learning topological image transforms using cellular simultaneous recurrent networks

    Page(s): 1 - 9
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (194 KB) |  | HTML iconHTML  

    In this work, we investigate cellular simultaneous recurrent networks (CSRNs) to learn topological image mappings, particularly those of the affine transformations. While affine image transformation in conventional image processing is a relatively simple task, learning these transformations is an important part of having neural networks (NNs) function as generalized image processors. We introduce the CSRN and discuss its adaptation for image processing tasks. We report results for translation, rotation and scaling of both binary and grey-scale images. Our results suggest that the CSRN is capable of learning and performing these basic topological transformations. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Human behaviour recognition based on trajectory analysis using neural networks

    Page(s): 1 - 7
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1124 KB)  

    Automated human behaviour analysis has been, and still remains, a challenging problem. It has been dealt from different points of views: from primitive actions to human interaction recognition. This paper is focused on trajectory analysis which allows a simple high level understanding of complex human behaviour. It is proposed a novel representation method of trajectory data, called Activity Description Vector (ADV) based on the number of occurrences of a person is in a specific point of the scenario and the local movements that perform in it. The ADV is calculated for each cell of the scenario in which it is spatially sampled obtaining a cue for different clustering methods. The ADV representation has been tested as the input of several classic classifiers and compared to other approaches using CAVIAR dataset sequences obtaining great accuracy in the recognition of the behaviour of people in a Shopping Centre. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • An incremental self-organizing neural network based on enhanced competitive Hebbian learning

    Page(s): 1 - 8
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2401 KB) |  | HTML iconHTML  

    Self-organizing neural networks are important tools for realizing unsupervised learning. Recently, a difficult task has involved the incremental, efficient and robust learning in noisy environments. Most of the existing techniques are poor in this regard. In this paper, we first propose a new topology generating method called enhanced competitive Hebbian learning (enhanced CHL), and then propose a novel incremental self-organizing neural network based on the enhanced CHL method, called enhanced incremental growing neural gas (Hi-GNG). The experiments presented in this paper show that the Hi-GNG algorithm can automatically and efficiently generate a topological structure with a suitable number of neurons and that the proposed algorithm is robust to noisy data. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Clustering the self-organizing map through the identification of core neuron regions

    Page(s): 1 - 8
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1811 KB) |  | HTML iconHTML  

    This paper presents an automatic clustering algorithm applied to SOM neurons. In the proposed method, every neuron has associated with it a weight and a feature vector, where the latter contains information of local density and local distances. The neurons are able to move in the SOM output grid so as to reach positions related to small pairwise distance among neurons and high density of patterns, but also taking into account the path cost to reach it. The positions to where the neurons converge are then used as benchmark for pruning the grid and revealing the core of the clusters. The method was evaluated through its application to synthetic and real world data sets. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Hierarchical SOM-based detection of novel behavior for 3D human tracking

    Page(s): 1 - 8
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (2059 KB) |  | HTML iconHTML  

    We present a hierarchical SOM-based architecture for the detection of novel human behavior in indoor environments. The system can unsupervisedly learn normal activity and then report novel behavioral patterns as abnormal. The learning stage is based on the clustering of motion with self-organizing maps. With this approach, no domain-specific knowledge on normal actions is required. During the tracking stage, we extract human motion properties expressed in terms of multidimensional flow vectors. From this representation, three classes of motion descriptors are encoded: trajectories, body features and directions. During the training phase, SOM networks are responsible for learning a specific class of descriptors. For a more accurate clustering of motion, we detect and remove outliers from the training data. At detection time, we propose a hybrid neural-statistical method for 3D posture recognition in real time. New observations are tested for novelty and reported if they deviate from the learned behavior. Experiments were performed in two different tracking scenarios with fixed and mobile depth sensor. In order to exhibit the validity of the proposed methodology, several experimental setups and the evaluation of obtained results are presented. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Clustering iOS executable using self-organizing maps

    Page(s): 1 - 8
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (135 KB) |  | HTML iconHTML  

    We pioneer the study on applying both SOMs and GHSOMs to cluster mobile apps based on their behaviors, showing that the SOM family works well for clustering samples with more than ten thousands of attributes. The behaviors of apps are characterized by system method calls that are embedded in their executable, but may not be perceived by users. In the data preprocessing stage, we propose a novel static binary analysis to resolve and count implicit system method calls of iOS executable. Since an app can make thousands of system method calls, it is needed a large dimension of attributes to model their behaviors faithfully. On collecting 115 apps directly downloaded from Apple app store, the analysis result shows that each app sample is represented with 18000+ kinds of methods as their attributes. Theoretically, such a sample representation with more than ten thousand attributes raises a challenge to traditional clustering mechanisms. However, our experimental result shows that apps that have similar behaviors (due to having been developed from the same company or providing similar services) can be clustered together via both SOMs and GHSOMs. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Batch self-organizing maps for mixed feature-type symbolic data

    Page(s): 1 - 8
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (164 KB) |  | HTML iconHTML  

    The Kohonen Self-Organizing Map (SOM) is an unsupervised neural network method with a competitive learning strategy which has both clustering and visualization properties. In this paper, we present batch SOM algorithms based on adaptive and non-adaptive distances for mixed feature-type symbolic data that, for a fixed epoch, optimize a cost function. The performance, and usefulness of these SOM algorithms are illustrated with real mixed feature-type symbolic data sets. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Modified self-organizing mixture network for probability density estimation and classification

    Page(s): 1 - 6
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (285 KB) |  | HTML iconHTML  

    In this paper, a modified algorithm based on the Self-organizing Mixture Network (SOMN) is proposed to learn arbitrarily complex density functions accurately and effectively. The algorithm is derived based on the criterion of minimizing the Kullback-Leibler divergence, maximum likelihood approach and self-organizing principle. It has the advantages of stochastic approximation method such as fewer local optima and faster convergence speed and the prominent properties of the neural networks such as good generalization ability, and overcomes the limitations of the SOMN. These greatly improve its stability, applicability and computation performance. This algorithm also simplifies the competitive and cooperative mechanism used in the self-organizing map (SOM). This lets it has a well-defined objective function and helps to provide a general proof of convergence. Experiments show that this modified algorithm outperforms the Expectation-Maximization (EM) algorithm, the SOMN and the joint entropy maximization algorithm in estimation accuracy. It is far superior to the EM algorithm in terms of learning speed and computational cost. Experimental results show that when used to estimate large datasets, this algorithm is 30-80 times faster than the EM algorithm at least. Owing to its outstanding density estimation performance, this algorithm is very helpful to the construction of optimal classifiers. The effectiveness of the algorithm is demonstrated in several real-world applications. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.