Neural Network Approaches to Visual Motion Perception

A multilayer neural nerwork model for the perception of rotational motion has been developed using Reichardt's motion detector array of correlation type, Kohonen's self-organized feature map and Schuster-Wagner's oscillating neural network. It is shown that the unsupervised learning could make the neurons on the second layer of the network tend to be self-organized in a form resembling columnar organization of selective directions in area MT of the primate's visual cortex. The output layer can interpret rotation information and give the directions and velocities of rotational motion. The computer simulation results are in agreement with some psychophysical observations of rotational perception. It is demonstrated that the temporal correlation between the oscillating neurons would be powerful for solving the "binding problem" of shear components of rotational motion.

Objective: To detect the pathogenetic mechanism of motion-sensitive cortical deficit in response to motion stimuli in children with anisometropic amblyopia using a blood oxygenation level-dependent functional magnetic resonance imaging technique (BOLD-fMRI). Methods: This was a case series study. Patients were collected from June to December 2017 at Tianjin Eye Hospital. Twenty-five patients who were diagnosed with anisometropic amblyopia as amblyopia group and twenty-five normal volunteers were examined as control group. A BOLD-fMRI technique on a 1.5T MRI and a horizontally moving sinusoidal grating block design were used for task conditions. All data were processed with SPM5 software, were analyzed by t test. Results: Significant fMRI activation and comparable right and left eye activation were found in the middle temporal area (MT), and Brodmann areas 19 and 37, in all control subjects; Lesser cortical activation in area MT and Brodmann areas 37, 19, and greater activation in the frontal gyrus of the lazy eye group were detected compared to the control group. Lesser cortical activation in Brodmann area 37, 18 of the contralateral eye of the amblyopic group was detected compared to the control group. Lesser cortical activation in area MT and Brodmann areas 19, 18, and greater activation in the frontal lobes of the anisometropic amblyopic eyes were detected compared to the contralateral eyes. Conclusions: The spatial extent and intensity of the visual cortex activation in the visual cortex decreases in the amblyopic eye compared to the normal control. Decreased cortical activation in the fellow eye is prevalent. A greater visual cortex area is activated when stimulating the amblyopic eye. Key words: Anisometropia; amblyopia; magnetic resonance imaging; visual motion; cortical deficit

Identification of lithofacies using Kohonen self-organizing maps

With an onset of social network amount of data is increasing day by day. In order to analyze the data and extract useful information, the data mining technology can be used. Clustering is one of the popular method of data mining. Clustering can be used for visualizing and analyzing of data. We are discussing Kohonen SOM. We are using neural networks, as a data mining tool which provides statistical observation and layout from big data-sets. We determine how Self-Organizing Kohonen Maps, can be efficiently used for data mining purposes. The Self Organizing Map (SOM) unsupervised learning is an effective computational tool in data mining processes. Self-Organizing Maps (SOMs) used to visualize social network dataset. We used Self-Organizing Map for clustering and analyzing high-dimensional and complex social network datasets. This paper also visualizes SOM neighbor connection, SOM neighbor weight distance, SOM weight position. We perform self organizing map algorithm for social network dataset in matlab.

With the proliferation of low-cost, consumer level, head-mounted displays (HMDs) such as Oculus VR or Sony's Morpheus, we are witnessing a reappearance of virtual reality. However, there are still important stumbling blocks that hinder the development of applications and reduce the visual quality of the results. Knowledge of human perception in virtual environments can help overcome these limitations. In this paper, within the much-studied area of perception in virtual environments, we chose to look into the less explored area of crossmodal perception, that is, the interaction of different senses when perceiving the environment. In particular, we looked at the influence of sound on visual motion perception in a virtual reality scenario. We first replicated a well-known crossmodal perception experiment, carried out on a conventional 2D display, and then extended it to a 3D head-mounted display (HMD). Next, we performed an additional experiment in which we increased the complexity of the stimuli of the previous experiment, to test whether the effects observed would hold in more realistic scenes. We found that the trend which was previously observed in 2D displays is maintained in HMDs, but with an observed reduction of the crossmodal effect. With more complex stimuli the trend holds, and the crossmodal effect is further reduced, possibly due to the presence of additional visual cues.

Describes a series of experiments on using Kohonen self-organizing maps and hybrid systems for continuous speech recognition. Experiments with different nonlinear transformations on the signal before using a neural network has been done and results compared. The hybrid system developed by the authors combines self-organizing feature maps with dynamic time warping. The experiments suggest that the combination has better performance than either of the two methods applied individually. >

Spiking Self-organizing Maps for Classification Problem

The article presents neural network for recognition of driving strategies based on interactions between drivers in road traffic. It analyzes the architecture of the model implemented as a self-organizing map (SOM), consisting of a group of neural networks based on radial basis functions (RBF). It is a training model grounded in the biological foundations of artificial neural networks, in which the training set should consist exclusively of input vectors; wherein the network training algorithm adjusts itself the network's weights to obtain consistent output vectors (i.e. to make presenting sufficiently close input vectors result into the same outputs).\nThe article presents the results of using a new generation of the neural network developed by us, which includes an adaptive learning algorithm to reduce the effect of re-training (overfitting) and false recognition, as well as to improve the determination of the boundaries between clusters.\nThe aim of the research is to outline architecture and structure of the neural network model that allows recognizing strategical characteristics of driving and can identify strategies of interactions between vehicles (their drivers) in road traffic as well as identify behavioral patterns This paper considers driving strategies that characterize the interaction of dyads of vehicles (drivers) moving in road traffic. The research results show that the SOM RBF neural networks can recognize and classify types of interactions in road traffic based on modelling of the analysis of vehicle movement trajectories. Experimental results demonstrate the neural networks architecture and networks learning involving 400 iterations of streaming the training data representing 500 possible simulated interaction situations. This paper presents a novel neural network model for recognition of drivers' behaviour patterns and for classification of driving strategies into five general classes: (1) competition strategy, (2) contest strategy, (3) evasion strategy, (4) compromise strategy, and (5) active confrontation strategy. This neural network has demonstrated a high rate of recognition and concise clusterization of similar driving strategies. The key contribution of this paper: it proposes a neural network model based on Kohonen's Self-Organizing Map (SOM) for detecting drivers' behaviours from vehicle movement patterns - driving strategies - instead of monitoring driver's specific activities.

Objective To research the recovery of the visual cortical function mediating visual motion perception in ametropic amblyopia after regular amblyopia treatment using 3.0 Tesla functional MRI (fMRI).Methods In this prospective study,blocks-designed fMRI experiment was performed on nine children with first was diagnosed as ametropic amblyopia,and review fMRI after one week,two weeks and one month.During the study,the patients were asked to view stimuli through rotating the checkerboard,which contrast ratio approach to 100％ and frequency approach to 8 Hz,Functional MRI data were processed by using SPM8 which based on the Matlab 7.12.The matrix data of each treatment stage were acquired bv hypothesisdriven research,and before and after self-control study (matched t-test) was performed in each group to acquire average cerebral cortex activated functional images data.The different mapping between each group during visual motion stimulus was also acquired.Results The functional area that is bilateral occipital lobe (Mean t of the right BA18=1.236 1 ;Mean t of the left BA18=1.521 1; Mean t of the right BA19=1.6845; Mean t of the left BA19=1.591 7,P＜0.005) and the visual association area (V5) (The right BA37 was activated and Mean T=1.201 4;The right BA21 was activated and Mean t=1.145 0,P＜0.005) expanded in different levels after amblyopia treatment two weeks; After four weeks,the bilateral occipital lobe (Mean t of the right BA18=1.0024; Mean t of the left BA18=1.743 1; Mean t of the right BA19=1.2253; Mean t of the left BA19=1.181 3,P＜0.005) showed activation on the small area compare with two weeks ago.Conclusion In the early functional training of the older children's ametropic amblyopia,reconstruction the visual cortical function mediating visual motion perception was more difficulty and unstable. Key words: Children ; Amblyopia; Cerebral cortex ; Magnetic resonance imaging

Objects and processes classification is a common experimental problem. Its solution, first of all, is needed in automatic diagnosis systems, for example, to determine the equipment operation state through the diagnostic signal or to identify abnormalities with medical images. With the development of convolutional neural networks, new prospects for solving such problems have risen up. However, the classification accuracy that can be achieved on these networks is not sufficient enough for all diagnosis issues. It is subject to, for example, timely diagnosis of the onset of transient phenomena. At the same time, another type of neural network, Kohonen self-organizing maps, has a conceptual property for training on unclassified set of classes, that is, giving the opportunity to solve such an issue. Therefore, the accuracy enhancement of the classification on the basis of Kohonen networks implementation in the architecture of convolutional networks is a relevant objective and has practical significance. The article analyzes the means of improving the accuracy of convolutional neural networks and arising problems solution. The ways of increasing the proportion of correct clustering on Kohonen networks due to the ‘growth’ of its grid shape in determining new classes in the learning process are also given. It is this property that makes it possible to recognize transient phenomena. It is determined that the existing solutions of the combination of Kohonen networks and convolutional networks are aimed at improving the efficiency of only self-organizing maps, with the purpose to improve the accuracy of classification by convolutional networks, it became necessary to develop a new architecture. The paper provides a description of this issue. Since the initial information of the Kohonen networks is the weighting matrix values of the grid shape neurons, it was necessary to associate it with the representation of the images in order to process the diagnostic images. The paper proposes the concept of a built-in associative array block based on Kohonen networks. According to the proposed method, a software implementation of a hybrid neural network is developed. The formulation and results of computational experiments are presented. The efficiency of the proposed method is experimentally proved. Keywords: convolutional neural networks, CNN, Kohonen self-organizing maps, SOM, signal classification, image classification.

Research on artificial neural networks (ANNs) has been carried out for more than five decades. A renewed interest appeared in the 80's with the finding of powerful models like J. Hopfield's recurrent networks, T. Kohonen's self-organizing feature maps, and the back-propagation rule. At that time, there was no platform that was at the same time versatile enough for any ANN model to be implemented and fast enough to solve large problems. Super-computers were the sole exception to this rule, but were prohibitively expensive for most applications. However, both research scientists and application engineers clearly identified the need for such a computing power. This triggered many projects in the field. In parallel, research on multi-processor systems started during the 60's. Systolic arrays have been proposed in 1979 as a means to fully exploit the possibilities of VLSI. Two previous theses, by F. Blayo and C. Lehmann, have studied the use of bi-dimensional systolic arrays for neural computation. At first, the presented system, called GENES, has been designed for the Hopfield model. Extensions to other ANNs have also been proposed. The goal of the present thesis is to study, design, build, and analyze an efficient accelerator for neural computation. In a first step, the GENES architecture has been extended towards generality and efficiency. This includes a thorough analysis of ANN models, of other neural computers, and of previous GENES implementations. The result of this work is the GENES IV integrated circuit, whose architecture has been co-designed by P. Ienne and the author. The main part of this thesis discusses the architecture, the design and the analysis of the MANTRA I machine, a neural computer based on a GENES IV array with up to 40 × 40 processing elements (PEs). The delta rule (and hence the Perceptron and Adaline rules), the back-propagation rule, the Hopfield model, and the Kohonen model can be implemented on this system. Although not a generic system, such a machine may be regarded as a multi-model neural computer. A prototype has been running for a year and is used daily by software designers. Several novel features distinguish the MANTRA I machine from other neural systems. First, it belongs to the few existing neural computers, contrary to the majority of implementations, which are specific to an application or to an algorithm. The machine does not hard-wire any algorithm, but provides the necessary primitives to implement the target models. This is a key feature for research, since several algorithms or versions of an algorithm can be tested on a problem. It is an important aspect for applications as well, because different ANN models are often cascaded to solve a problem. The GENES IV array — that is, the computing core of the MANTRA I machine — features synapse-level parallelism (i.e., one real or virtual PE is allocated per synapse or neural connection), while most other systems exploit only neuron-level parallelism (i.e., one PE per neuron). Hence, this system aims at a much finer parallelism grain and is well suited for massively parallel architectures. The problem size that can be computed by a neural accelerator should not be limited by the hardware (except for memory size). Therefore, it is essential to support time-sharing of PEs. On the MANTRA I machine, this is achieved by the concept of virtual arrays. Matrices are divided into sub-matrices that can be mapped onto the physical array, which is then time-shared among them. An efficient mechanism has been implemented to swap sub-matrices in background, while some other computation is performed. Since systolic arrays are pipelined systems, it is important to avoid emptying and re-filling them too often, in order to keep the hardware utilization rate high. Therefore, a systolic instruction flow has been implemented, so that each instruction follows the data for which it has been issued. Like any SIMD system, the MANTRA I machine is composed of a parallel or SIMD module and a control module. The SIMD module consists of the GENES IV array and a set of dedicated units designed for the computation that scales with the number of neurons and would poorly fit on a bi-dimensional array. A complex system of FIFOs and memories sustains the required input/output streams for the systolic array. The control module is a complete SISD system. Its tasks are (1) to control the SIMD module by dispatching instructions, (2) to manage data input and output, (3) to communicate with the external world, and (4) to perform data pre- and post-processing. The SIMD instructions are of the very long instruction word (VLIW) type. Synchronization between the two modules is achieved by an instruction FIFO. The performance of the MANTRA I machine has been analyzed using the delta rule. Measurements show that the sustained performance is very close to its peak value, as long as the problem fits in the memory banks connected to the GENES IV array. Experiments have also been run to investigate the impact of the constraints imposed by the hardware on the convergence of algorithms. Finally, the use of systolic arrays as neural accelerators is discussed in the light of the experience acquired with the GENES IV array and the MANTRA I machine. The weaknesses of the machine are analyzed, and several solutions are proposed to avoid them in a future design. A general discussion of the future of neural computers concludes this thesis.

Severe Acute Respiratory Syndrome (SARS) is a highly infectious disease caused by a coronavirus. Screening to detect potential SARS-infected subjects with elevated body temperature plays an important role in preventing the spread of SARS. Thermography is being used with ANN/AI to analyse the data collected from the designated SARS hospital in Singapore, and conclusive results are drawn. The current work evaluates the correlations (and classifications) between facial skin temperatures, including eye range and forehead, to aural temperature using a neural network (NN) approach, namely training backpropagation (BP) and Kohonen self-organizing map (SOM), to confirm the suitability of thermal imagers for human temperature screening. Both BP and SOM can form an opinion about the type of network that is better able to complement thermogram technology in fever diagnosis. This can produce better parameters for reducing the size of the NN classifier, while maintaining good classification accuracy. We observe that BP performs better than SOM NN. Confusion matrix (CM), an alternative display instrument, is able to process a high volume of input data and show the clustered output rapidly and accurately. The current research application will remain an interesting and useful reference for both local and overseas manufacturers of thermal scanners, users and various government and private establishments. As the elevation of body temperature is a common presenting symptom for many illnesses, including infectious diseases such as SARS, thermal imagers are useful and essential tools for mass screening of body temperature. This is true not only for SARS but also during other public health crises where widespread transmission of infection such as the danger of avian flu pandemic is a concern, in particular at places like hospitals and cross-border checkpoints.

1: Architectures.- Scale Independence in the Visual System.- Dynamic Neuronal Information Processing of Vowel Sounds in Auditory Cortex.- Convolutional Spiking Neural Network for Robust Object Detection with Population Code using Structured Pulse Packets.- Networks Constructed of Neuroid Elements Capable of Temporal Summation of Signals.- Predictive Synchrony Organized by Spike-Based Hebbian Learning with Time-Representing Synfire Activities.- Improving Chow-Liu Tree Performance by Mining Association Rules.- A Reconstructed Missing Data-Finite Impulse Response Selective Ensemble (RMD-FSE) Network.- Higher Order Multidirectional Associative Memory with Decreasing Energy Function.- Fast Indexing of Codebook Vectors Using Dynamic Binary Search Trees with Fat Decision Hyperplanes.- 2: Learning Algorithms.- On Some External Characteristics of Brain-like Learning and Some Logical Flaws of Connectionism.- Superlinear Learning Algorithm Design.- Extension of Binary Neural Networks for Multi-class Output and Finite Automata.- A Memory-Based Reinforcement Learning Algorithm to Prevent Unlearning in Neural Networks.- Structural Optimization of Neural Networks by Genetic Algorithm with Degeneration (GAd).- Adaptive Training for Combining Classifier Ensembles.- Combination Strategies for Finding Optimal Neural Network Architecture and Weights.- 3: Applications.- Biologically Inspired Recognition System for Car Detection from Real-Time Video Streams.- Financial Time Series Prediction Using Non-Fixed and Asymmetrical Margin Setting with Momentum in Support Vector Regression.- A Method for Applying Neural Networks to Control of Nonlinear Systesm.- Robot Manipulator Control via Recurrent Neural Networks.- Gesture Recognition Based on SOM Using Multiple Sensors.- Enhanced Phrase-Based Document Clustering Using Self-Organizing Map (SOM) Architectures.- Discovering Gene Regulatory Networks from Gene Expression Data with the Use of Evolving Connectionist Systems.- Experimental Analysis of Knowledge Based Multiagent Credit Assignment.- Implementation of Visual Tracking System Using Artificial Retina Chip and Shape Memory Alloy Actuator.

QuestionCan a Kohonen's self‐organizing map, which is robust to non‐linear relationships between variables and their non‐normal distributions, be effective in patterning the data on plant communities investigated with the classical Braun‐Blanquet phytosociological method based on the ordinal scale? Does the application of the self‐organizing map make it possible to obtain new information from the analysed plant communities when compared to the Braun–Blanquet method alone?LocationThe Babsk nature reserve, Central Poland.MethodsThe analysed data were derived from two separate series of phytosociological studies on plant communities dating from periods 31 yr apart (1960 and 1991). The data consisted of 24 quantitative sampling lists of plant species (=phytosociological releves). The releves were analysed by the application of a Kohonen's self‐organizing map and the indicator value (IndVal).ResultsThe transformations from Querco roboris–Pinetum to Tilio cordatae–Carpinetum betuli in the vegetation in the Babsk nature reserve over 31 yr were determined precisely. Valuable new data were also obtained on: (1) significant associations of individual plant species with the previous and recent phytocoenoses, i.e. diagnostic groups of plant species for each phytocoenosis; (2) abiotic conditions (determined retrospectively in the two study periods on the basis of ecological indicators for vascular plants); and (3) the concordance of phytocoenoses with the biotope.ConclusionsThe Kohonen's self‐organizing map method and the IndVal made it possible to efficiently identify abiotic and biotic patterns for plant communities on the basis of the data expressed in the conventional Braun‐Blanquet scale.

Decomposition of interacting features using a Kohonen self-organizing feature map neural network