Modular non-computational-connectionist-hybrid neural network approach to robotic systems

Spiking neural networks are usually limited in their applications due to their complex mathematical models and the lack of intuitive learning algorithms. In this paper, a simpler, novel neural network derived from a leaky integrate and fire neuron model, the ‘cavalcade’ neuron, is presented. A simulation for the neural network has been developed and two basic learning algorithms implemented within the environment. These algorithms successfully learn some basic temporal and instantaneous problems. Inspiration for neural network structures from these experiments are then taken and applied to process sensor information so as to successfully control a mobile robot.

NeMo: a platform for neural modelling of spiking neurons using GPUs

Simulating spiking neural networks is of great interest to scientists wanting to model the functioning of the brain. However, large-scale models are expensive to simulate due to the number and interconnectedness of neurons in the brain. Furthermore, where such simulations are used in an embodied setting, the simulation must be real-time in order to be useful. In this paper we present NeMo, a platform for such simulations which achieves high performance through the use of highly parallel commodity hardware in the form of graphics processing units (GPUs). NeMo makes use of the Izhikevich neuron model which provides a range of realistic spiking dynamics while being computationally efficient. Our GPU kernel can deliver up to 400 million spikes per second. This corresponds to a real-time simulation of around 40 000 neurons under biologically plausible conditions with 1000 synapses per neuron and a mean firing rate of 10 Hz.

Mind wandering away from pain dynamically engages antinociceptive and default mode brain networks

Human minds often wander away from their immediate sensory environment. It remains unknown whether such mind wandering is unsystematic or whether it lawfully relates to an individual’s tendency to attend to salient stimuli such as pain and their associated brain structure/function. Studies of pain–cognition interactions typically examine explicit manipulation of attention rather than spontaneous mind wandering. Here we sought to better represent natural fluctuations in pain in daily life, so we assessed behavioral and neural aspects of spontaneous disengagement of attention from pain. We found that an individual’s tendency to attend to pain related to the disruptive effect of pain on his or her cognitive task performance. Next, we linked behavioral findings to neural networks with strikingly convergent evidence from functional magnetic resonance imaging during pain coupled with thought probes of mind wandering, dynamic resting state activity fluctuations, and diffusion MRI. We found that (i) pain-induced default mode network (DMN) deactivations were attenuated during mind wandering away from pain; (ii) functional connectivity fluctuations between the DMN and periaqueductal gray (PAG) dynamically tracked spontaneous attention away from pain; and (iii) across individuals, stronger PAG–DMN structural connectivity and more dynamic resting state PAG–DMN functional connectivity were associated with the tendency to mind wander away from pain. These data demonstrate that individual tendencies to mind wander away from pain, in the absence of explicit manipulation, are subserved by functional and structural connectivity within and between default mode and antinociceptive descending modulation networks.

B-spline neural network based single-carrier frequency domain equalisation for Hammerstein channels

A practical single-carrier (SC) block transmission with frequency domain equalisation (FDE) system can generally be modelled by the Hammerstein system that includes the nonlinear distortion effects of the high power amplifier (HPA) at transmitter. For such Hammerstein channels, the standard SC-FDE scheme no longer works. We propose a novel Bspline neural network based nonlinear SC-FDE scheme for Hammerstein channels. In particular, we model the nonlinear HPA, which represents the complex-valued static nonlinearity of the Hammerstein channel, by two real-valued B-spline neural networks, one for modelling the nonlinear amplitude response of the HPA and the other for the nonlinear phase response of the HPA. We then develop an efficient alternating least squares algorithm for estimating the parameters of the Hammerstein channel, including the channel impulse response coefficients and the parameters of the two B-spline models. Moreover, we also use another real-valued B-spline neural network to model the inversion of the HPA’s nonlinear amplitude response, and the parameters of this inverting B-spline model can be estimated using the standard least squares algorithm based on the pseudo training data obtained as a byproduct of the Hammerstein channel identification. Equalisation of the SC Hammerstein channel can then be accomplished by the usual one-tap linear equalisation in frequency domain as well as the inverse Bspline neural network model obtained in time domain. The effectiveness of our nonlinear SC-FDE scheme for Hammerstein channels is demonstrated in a simulation study.

Cross-situational learning of object-word mapping using Neural Modeling Fields

The issue of how children learn the meaning of words is fundamental to developmental psychology. The recent attempts to develop or evolve efficient communication protocols among interacting robots or Virtual agents have brought that issue to a central place in more applied research fields, such as computational linguistics and neural networks, as well. An attractive approach to learning an object-word mapping is the so-called cross-situational learning. This learning scenario is based on the intuitive notion that a learner can determine the meaning of a word by finding something in common across all observed uses of that word. Here we show how the deterministic Neural Modeling Fields (NMF) categorization mechanism can be used by the learner as an efficient algorithm to infer the correct object-word mapping. To achieve that we first reduce the original on-line learning problem to a batch learning problem where the inputs to the NMF mechanism are all possible object-word associations that Could be inferred from the cross-situational learning scenario. Since many of those associations are incorrect, they are considered as clutter or noise and discarded automatically by a clutter detector model included in our NMF implementation. With these two key ingredients - batch learning and clutter detection - the NMF mechanism was capable to infer perfectly the correct object-word mapping. (C) 2009 Elsevier Ltd. All rights reserved.

How language can help discrimination in the Neural Modelling Fields framework

The relationship between thought and language and, in particular, the issue of whether and how language influences thought is still a matter of fierce debate. Here we consider a discrimination task scenario to study language acquisition in which an agent receives linguistic input from an external teacher, in addition to sensory stimuli from the objects that exemplify the overlapping categories that make up the environment. Sensory and linguistic input signals are fused using the Neural Modelling Fields (NMF) categorization algorithm. We find that the agent with language is capable of differentiating object features that it could not distinguish without language. In this sense, the linguistic stimuli prompt the agent to redefine and refine the discrimination capacity of its sensory channels. (C) 2007 Elsevier Ltd. All rights reserved.

A multi-GPU algorithm for large-scale neuronal networks

Large-scale simulations of parts of the brain using detailed neuronal models to improve our understanding of brain functions are becoming a reality with the usage of supercomputers and large clusters. However, the high acquisition and maintenance cost of these computers, including the physical space, air conditioning, and electrical power, limits the number of simulations of this kind that scientists can perform. Modern commodity graphical cards, based on the CUDA platform, contain graphical processing units (GPUs) composed of hundreds of processors that can simultaneously execute thousands of threads and thus constitute a low-cost solution for many high-performance computing applications. In this work, we present a CUDA algorithm that enables the execution, on multiple GPUs, of simulations of large-scale networks composed of biologically realistic Hodgkin-Huxley neurons. The algorithm represents each neuron as a CUDA thread, which solves the set of coupled differential equations that model each neuron. Communication among neurons located in different GPUs is coordinated by the CPU. We obtained speedups of 40 for the simulation of 200k neurons that received random external input and speedups of 9 for a network with 200k neurons and 20M neuronal connections, in a single computer with two graphic boards with two GPUs each, when compared with a modern quad-core CPU. Copyright (C) 2010 John Wiley & Sons, Ltd.

ANALYSIS & STUDY OF AI TECHNIQUES FORAUTOMATIC CONDITION MONITORING OFRAILWAY TRACK INFRASTRUCTURE : Artificial Intelligence Techniques

Since the last decade the problem of surface inspection has been receiving great attention from the scientific community, the quality control and the maintenance of products are key points in several industrial applications.The railway associations spent much money to check the railway infrastructure. The railway infrastructure is a particular field in which the periodical surface inspection can help the operator to prevent critical situations. The maintenance and monitoring of this infrastructure is an important aspect for railway association.That is why the surface inspection of railway also makes importance to the railroad authority to investigate track components, identify problems and finding out the way that how to solve these problems. In railway industry, usually the problems find in railway sleepers, overhead, fastener, rail head, switching and crossing and in ballast section as well. In this thesis work, I have reviewed some research papers based on AI techniques together with NDT techniques which are able to collect data from the test object without making any damage. The research works which I have reviewed and demonstrated that by adopting the AI based system, it is almost possible to solve all the problems and this system is very much reliable and efficient for diagnose problems of this transportation domain. I have reviewed solutions provided by different companies based on AI techniques, their products and reviewed some white papers provided by some of those companies. AI based techniques likemachine vision, stereo vision, laser based techniques and neural network are used in most cases to solve the problems which are performed by the railway engineers.The problems in railway handled by the AI based techniques performed by NDT approach which is a very broad, interdisciplinary field that plays a critical role in assuring that structural components and systems perform their function in a reliable and cost effective fashion. The NDT approach ensures the uniformity, quality and serviceability of materials without causing any damage of that materials is being tested. This testing methods use some way to test product like, Visual and Optical testing, Radiography, Magnetic particle testing, Ultrasonic testing, Penetrate testing, electro mechanic testing and acoustic emission testing etc. The inspection procedure has done periodically because of better maintenance. This inspection procedure done by the railway engineers manually with the aid of AI based techniques.The main idea of thesis work is to demonstrate how the problems can be reduced of thistransportation area based on the works done by different researchers and companies. And I have also provided some ideas and comments according to those works and trying to provide some proposal to use better inspection method where it is needed.The scope of this thesis work is automatic interpretation of data from NDT, with the goal of detecting flaws accurately and efficiently. AI techniques such as neural networks, machine vision, knowledge-based systems and fuzzy logic were applied to a wide spectrum of problems in this area. Another scope is to provide an insight into possible research methods concerning railway sleeper, fastener, ballast and overhead inspection by automatic interpretation of data.In this thesis work, I have discussed about problems which are arise in railway sleepers,fastener, and overhead and ballasted track. For this reason I have reviewed some research papers related with these areas and demonstrated how their systems works and the results of those systems. After all the demonstrations were taking place of the advantages of using AI techniques in contrast with those manual systems exist previously.This work aims to summarize the findings of a large number of research papers deploying artificial intelligence (AI) techniques for the automatic interpretation of data from nondestructive testing (NDT). Problems in rail transport domain are mainly discussed in this work. The overall work of this paper goes to the inspection of railway sleepers, fastener, ballast and overhead.

Financial time series analysis : Chaos and neurodynamics approach

This work aims at combining the Chaos theory postulates and Artificial Neural Networks classification and predictive capability, in the field of financial time series prediction. Chaos theory, provides valuable qualitative and quantitative tools to decide on the predictability of a chaotic system. Quantitative measurements based on Chaos theory, are used, to decide a-priori whether a time series, or a portion of a time series is predictable, while Chaos theory based qualitative tools are used to provide further observations and analysis on the predictability, in cases where measurements provide negative answers. Phase space reconstruction is achieved by time delay embedding resulting in multiple embedded vectors. The cognitive approach suggested, is inspired by the capability of some chartists to predict the direction of an index by looking at the price time series. Thus, in this work, the calculation of the embedding dimension and the separation, in Takens‘ embedding theorem for phase space reconstruction, is not limited to False Nearest Neighbor, Differential Entropy or other specific method, rather, this work is interested in all embedding dimensions and separations that are regarded as different ways of looking at a time series by different chartists, based on their expectations. Prior to the prediction, the embedded vectors of the phase space are classified with Fuzzy-ART, then, for each class a back propagation Neural Network is trained to predict the last element of each vector, whereas all previous elements of a vector are used as features.

Soft computing in biometrics : a pragmatic appraisal

The ever increasing spurt in digital crimes such as image manipulation, image tampering, signature forgery, image forgery, illegal transaction, etc. have hard pressed the demand to combat these forms of criminal activities. In this direction, biometrics - the computer-based validation of a persons' identity is becoming more and more essential particularly for high security systems. The essence of biometrics is the measurement of person’s physiological or behavioral characteristics, it enables authentication of a person’s identity. Biometric-based authentication is also becoming increasingly important in computer-based applications because the amount of sensitive data stored in such systems is growing. The new demands of biometric systems are robustness, high recognition rates, capability to handle imprecision, uncertainties of non-statistical kind and magnanimous flexibility. It is exactly here that, the role of soft computing techniques comes to play. The main aim of this write-up is to present a pragmatic view on applications of soft computing techniques in biometrics and to analyze its impact. It is found that soft computing has already made inroads in terms of individual methods or in combination. Applications of varieties of neural networks top the list followed by fuzzy logic and evolutionary algorithms. In a nutshell, the soft computing paradigms are used for biometric tasks such as feature extraction, dimensionality reduction, pattern identification, pattern mapping and the like.

Predicting worsted spinning performance with an artificial neural network model

For a given fiber spun to pre-determined yarn specifications, the spinning performance of the yarn usually varies from mill to mill. For this reason, it is necessary to develop an empirical model that can encompass all known processing variables that exist in different spinning mills, and then generalize this information and be able to accurately predict yarn quality for an individual mill. This paper reports a method for predicting worsted spinning performance with an artificial neural network (ANN) trained with backpropagation. The applicability of artificial neural networks for predicting spinning performance is first evaluated against a well established prediction and benchmarking tool (Sirolan YarnspecTM). The ANN is then subsequently trained with commercial mill data to assess the feasibility of the method as a mill-specific performance prediction tool. Incorporating mill-specific data results in an improved fit to the commercial mill data set, suggesting that the proposed method has the ability to predict the spinning performance of a specific mill accurately.

Predicting the pilling propensity of fabrics through artificial neural network modeling

Fabric pilling is affected by many interacting factors. This study uses artificial neural networks to model the multi-linear relationships between fiber, yarn and fabric properties and their effect on the pilling propensity of pure wool knitted fabrics. This tool shall enable the user to gauge the expected pilling performance of a fabric from a number of given inputs. It will also provide a means of improving current products by offering alternative material specification and/or selection. In addition to having the capability to predict pilling performance, the model will allow for clarification of major fiber, yarn and fabric attributes affecting fabric pilling.

Knowledge extraction from a mixed transfer function artificial neural network

One of the main problems with Artificial Neural Networks (ANNs) is that their results are not intuitively clear. For example, commonly used hidden neurons with sigmoid activation function can approximate any continuous function, including linear functions, but the coefficients (weights) of this approximation are rather meaningless. To address this problem, current paper presents a novel kind of a neural network that uses transfer functions of various complexities in contrast to mono-transfer functions used in sigmoid and hyperbolic tangent networks. The presence of transfer functions of various complexities in a Mixed Transfer Functions Artificial Neural Network (MTFANN) allow easy conversion of the full model into user-friendly equation format (similar to that of linear regression) without any pruning or simplification of the model. At the same time, MTFANN maintains similar generalization ability to mono-transfer function networks in a global optimization context. The performance and knowledge extraction of MTFANN were evaluated on a realistic simulation of the Puma 560 robot arm and compared to sigmoid, hyperbolic tangent, linear and sinusoidal networks.

Nonlinear identification of pneumatic servo-drive

Three nonlinear approaches to model the nonlinear pneumatic servo- drive are presented. The three nonlinear approaches are: (1) the multi input-single output (MISO) approach, which describes the single input-single output (SISO) nonlinear plant using a MISO linear representation which allows replacement of the nonlinear analysis by a linear one without approximation, and is studied in both time and frequency domains; (2) piecewise linearization, which systematically replaces, using artificial neural network, the nonlinear surface representing the plant in the hyper input-output space by a number of linear planes that are continuous over the boundaries between them; and (3) Adaptive Neuro-Fuzzy Inference System (ANFIS), in which the fuzzy rules are placed in a neural network structure, and which consequently utilizes neural networks learning rules to systematically tune the nonlinear fuzzy model. The superiority of these nonlinear models over the best model that can be developed using linear identification techniques is shown.

An agent-based hybrid intelligent system for financial investment planning

Many complex problems including financial investment planning require hybrid intelligent systems that integrate many intelligent techniques including expert systems, fuzzy logic, neural networks, and genetic algorithms. However, hybrid intelligent systems are difficult to develop due to complicated interactions and technique incompatibilities. This paper describes a hybrid intelligent system for financial investment planning that was built from agent points of view. This system currently consists of 13 different agents. The experimental results show that all agents in the system can work cooperatively to provide reasonable investment advice. The system is very flexible and robust. The success of the system indicates that agent technologies can significantly facilitate the construction of hybrid intelligent systems.