A Detailed Look at Scale and Translation Invariance in a Hierarchical Neural Model of Visual Object Recognition

The HMAX model has recently been proposed by Riesenhuber & Poggio as a hierarchical model of position- and size-invariant object recognition in visual cortex. It has also turned out to model successfully a number of other properties of the ventral visual stream (the visual pathway thought to be crucial for object recognition in cortex), and particularly of (view-tuned) neurons in macaque inferotemporal cortex, the brain area at the top of the ventral stream. The original modeling study only used ``paperclip'' stimuli, as in the corresponding physiology experiment, and did not explore systematically how model units' invariance properties depended on model parameters. In this study, we aimed at a deeper understanding of the inner workings of HMAX and its performance for various parameter settings and ``natural'' stimulus classes. We examined HMAX responses for different stimulus sizes and positions systematically and found a dependence of model units' responses on stimulus position for which a quantitative description is offered. Interestingly, we find that scale invariance properties of hierarchical neural models are not independent of stimulus class, as opposed to translation invariance, even though both are affine transformations within the image plane.

Neural Networks

We present an overview of current research on artificial neural networks, emphasizing a statistical perspective. We view neural networks as parameterized graphs that make probabilistic assumptions about data, and view learning algorithms as methods for finding parameter values that look probable in the light of the data. We discuss basic issues in representation and learning, and treat some of the practical issues that arise in fitting networks to data. We also discuss links between neural networks and the general formalism of graphical models.

Forecasting Global Temperature Variations by Neural Networks

Global temperature variations between 1861 and 1984 are forecast usingsregularization networks, multilayer perceptrons and linearsautoregression. The regularization network, optimized by stochasticsgradient descent associated with colored noise, gives the bestsforecasts. For all the models, prediction errors noticeably increasesafter 1965. These results are consistent with the hypothesis that thesclimate dynamics is characterized by low-dimensional chaos and thatsthe it may have changed at some point after 1965, which is alsosconsistent with the recent idea of climate change.s

Biologically Plausible Neural Circuits for Realization of Maximum Operations

Object recognition in the visual cortex is based on a hierarchical architecture, in which specialized brain regions along the ventral pathway extract object features of increasing levels of complexity, accompanied by greater invariance in stimulus size, position, and orientation. Recent theoretical studies postulate a non-linear pooling function, such as the maximum (MAX) operation could be fundamental in achieving such invariance. In this paper, we are concerned with neurally plausible mechanisms that may be involved in realizing the MAX operation. Four canonical circuits are proposed, each based on neural mechanisms that have been previously discussed in the context of cortical processing. Through simulations and mathematical analysis, we examine the relative performance and robustness of these mechanisms. We derive experimentally verifiable predictions for each circuit and discuss their respective physiological considerations.

Biologically Plausible Neural Model for the Recognition of Biological Motion and Actions

The visual recognition of complex movements and actions is crucial for communication and survival in many species. Remarkable sensitivity and robustness of biological motion perception have been demonstrated in psychophysical experiments. In recent years, neurons and cortical areas involved in action recognition have been identified in neurophysiological and imaging studies. However, the detailed neural mechanisms that underlie the recognition of such complex movement patterns remain largely unknown. This paper reviews the experimental results and summarizes them in terms of a biologically plausible neural model. The model is based on the key assumption that action recognition is based on learned prototypical patterns and exploits information from the ventral and the dorsal pathway. The model makes specific predictions that motivate new experiments.

Exact Solution of the Nonlinear Dynamics of Recurrent Neural Mechanisms for Direction Selectivity

Different theoretical models have tried to investigate the feasibility of recurrent neural mechanisms for achieving direction selectivity in the visual cortex. The mathematical analysis of such models has been restricted so far to the case of purely linear networks. We present an exact analytical solution of the nonlinear dynamics of a class of direction selective recurrent neural models with threshold nonlinearity. Our mathematical analysis shows that such networks have form-stable stimulus-locked traveling pulse solutions that are appropriate for modeling the responses of direction selective cortical neurons. Our analysis shows also that the stability of such solutions can break down giving raise to a different class of solutions ("lurching activity waves") that are characterized by a specific spatio-temporal periodicity. These solutions cannot arise in models for direction selectivity with purely linear spatio-temporal filtering.

Efficient learning of reactive robot behaviors with a Neural-Q_learning approach

The purpose of this paper is to propose a Neural-Q_learning approach designed for online learning of simple and reactive robot behaviors. In this approach, the Q_function is generalized by a multi-layer neural network allowing the use of continuous states and actions. The algorithm uses a database of the most recent learning samples to accelerate and guarantee the convergence. Each Neural-Q_learning function represents an independent, reactive and adaptive behavior which maps sensorial states to robot control actions. A group of these behaviors constitutes a reactive control scheme designed to fulfill simple missions. The paper centers on the description of the Neural-Q_learning based behaviors showing their performance with an underwater robot in a target following task. Real experiments demonstrate the convergence and stability of the learning system, pointing out its suitability for online robot learning. Advantages and limitations are discussed

Semi-online neural-Q_leaming for real-time robot learning

Reinforcement learning (RL) is a very suitable technique for robot learning, as it can learn in unknown environments and in real-time computation. The main difficulties in adapting classic RL algorithms to robotic systems are the generalization problem and the correct observation of the Markovian state. This paper attempts to solve the generalization problem by proposing the semi-online neural-Q_learning algorithm (SONQL). The algorithm uses the classic Q_learning technique with two modifications. First, a neural network (NN) approximates the Q_function allowing the use of continuous states and actions. Second, a database of the most representative learning samples accelerates and stabilizes the convergence. The term semi-online is referred to the fact that the algorithm uses the current but also past learning samples. However, the algorithm is able to learn in real-time while the robot is interacting with the environment. The paper shows simulated results with the "mountain-car" benchmark and, also, real results with an underwater robot in a target following behavior

Correlación entre mediciones laríngeas externas con el tamaño del tubo endotraqueal en niños

La selección apropiada del tamaño de los tubos endotraqueales (TET) para utilizar en niños es importante en anestesia general y cuidado crítico. Se han descrito muchos métodos para determinar el tamaño requerido del TET para cada paciente que son usados en la práctica clínica en la actualidad. La fórmula que considera la edad y las técnicas basadas en características físicas del niño han sido ampliamente utilizadas, pero tienen poco valor en predecir el tamaño del TET en pacientes entre 2 a 8 años. En este estudio analítico se correlacionaron las dimensiones anatómicas externas de la laringe (diámetros externos) con el tamaño del tubo endotraqueal (diámetro interno de la laringe) en 110 pacientes pediátricos llevados a cirugía electiva bajo anestesia general; se tomaron las medidas en la superficie externa de la laringe y se registró el tamaño del tubo endotraqueal que fue adecuado en cada niño, no se controló la técnica anestésica la cual fue elegida por el anestesiólogo a cargo. Se encontró correlación estadísticamente significativa entre las de la medida del diámetro externo del cartílago tiroides con el tamaño del tubo endotraqueal en pacientes de género femenino. Con estos datos es posible calcular el tamaño apropiado del tubo endotraqueal en estos pacientes diseñando una herramienta que permita mostrar el número del tubo a utilizar tomando como referencia la medición de este diámetro.

Data-Driven Text Generation using Neural Networks & Provenance is Complicated and Boring — Is there a solution?

Title: Data-Driven Text Generation using Neural Networks Speaker: Pavlos Vougiouklis, University of Southampton Abstract: Recent work on neural networks shows their great potential at tackling a wide variety of Natural Language Processing (NLP) tasks. This talk will focus on the Natural Language Generation (NLG) problem and, more specifically, on the extend to which neural network language models could be employed for context-sensitive and data-driven text generation. In addition, a neural network architecture for response generation in social media along with the training methods that enable it to capture contextual information and effectively participate in public conversations will be discussed. Speaker Bio: Pavlos Vougiouklis obtained his 5-year Diploma in Electrical and Computer Engineering from the Aristotle University of Thessaloniki in 2013. He was awarded an MSc degree in Software Engineering from the University of Southampton in 2014. In 2015, he joined the Web and Internet Science (WAIS) research group of the University of Southampton and he is currently working towards the acquisition of his PhD degree in the field of Neural Network Approaches for Natural Language Processing. Title: Provenance is Complicated and Boring — Is there a solution? Speaker: Darren Richardson, University of Southampton Abstract: Paper trails, auditing, and accountability — arguably not the sexiest terms in computer science. But then you discover that you've possibly been eating horse-meat, and the importance of provenance becomes almost palpable. Having accepted that we should be creating provenance-enabled systems, the challenge of then communicating that provenance to casual users is not trivial: users should not have to have a detailed working knowledge of your system, and they certainly shouldn't be expected to understand the data model. So how, then, do you give users an insight into the provenance, without having to build a bespoke system for each and every different provenance installation? Speaker Bio: Darren is a final year Computer Science PhD student. He completed his undergraduate degree in Electronic Engineering at Southampton in 2012.

Neural networks of human nature and nurture

Neural network methods have facilitated the unification of several unfortunate splits in psychology, including nature versus nurture. We review the contributions of this methodology and then discuss tentative network theories of caring behavior, of uncaring behavior, and of how the frontal lobes are involved in the choices between them. The implications of our theory are optimistic about the prospects of society to encourage the human potential for caring. 

Comparación de la presión del manguito del tubo orotraqueal estimada por palpación frente a la medición tomada con un manómetro

La presión que ejerce el manguito del tubo orotraqueal (TOT) sobre la mucosa al ser insuflado debe mantenerse en un rango de seguridad que evite complicaciones por sobreinflación o por desinsuflación. En nuestro medio, los instrumentos de medición objetiva no son de uso común. Objetivo: evaluar la concordancia de la presión del manguito del TOT estimada por palpación frente al uso de un manómetro manual en pacientes adultos sometidos a anestesia general. Materiales y métodos: se realizó un estudio de corte transversal que incluyó a 40 pacientes, a quienes, una vez intubados, dos anestesiólogos enmascarados, diferentes al que los intubó, palparon el manguito del TOT categorizándolo como sobreinflado, normal o desinflado; posteriormente, uno de los investigadores registró la medida con un manómetro en fase inspiratoria y espiratoria. Se consideró como rango normal de 20 a 30 cm H2O. Resultados: la concordancia de la estimación por palpación entre los dos anestesiólogos fue débil (Kappa = 0,21, ES: 0,11). La concordancia entre la estimación por palpación y la medición con el manómetro manual fue muy débil. Entre el primer anestesiólogo y el investigador en fase inspiratoria, . 0,08 (ES: 0,09), y en espiración, . 0,08 (ES: 0,07). Entre el segundo anestesiólogo y el investigador, . 0,05 (ES: 0,07) y 0,02 (ES: 0,06), respectivamente. Conclusión: el estudio muestra que la concordancia entre los métodos subjetivo y objetivo para determinar si el manguito del TOT está adecuadamente inflado fue débil. Se sugiere el empleo de métodos más objetivos para su determinación.

Validación diagnóstica del test neural 1 para el síndrome de túnel del carpo

El objetivo de este estudio fue realizar una prueba de validez diagnostica del test neural 1 para el diagnóstico del Síndrome de Túnel del Carpo (STC) utilizando como prueba de referencia o de oro el test de conducción nerviosa. En este estudio participaron 115 sujetos, 230 manos con sospecha clínica de STC quienes fueron evaluados con el test de conducción nerviosa y el test neural 1. Se encontró una sensibilidad del 93.0% (IC 95%:88,21-96,79) y una especificidad del 6,67% (IC 95%:0,0-33,59), razón de verosimilitud positiva fue de 1,00 y razón de verosimilitud negativa de 1,05. Valor predictivo positivo de 86,9% y un valor predictivo negativo de 12,5%. Se concluye que el test neural 1 es una prueba clínica de alta sensibilidad y baja especificidad de gran utilidad para el monitoreo e identificación del STC. Es un procedimiento para el diagnóstico clínico de bajo costo que puede incluirse en los exámenes de rutina de los trabajadores como complemento a las pruebas clínicas sugeridas por las Gatiso para dar mayor precisión a la identificación temprana del STC. Se sugiere combinarla con otros test de mayor especificidad para ser aplicada en trabajadores en condiciones de riesgo o que presenten síntomas en miembros superiores y realizar otros estudios en donde participen sujetos sin diagnóstico clínico del STC.

Observación de la ley de Lenz con un imán y un tubo metálico

Resumen tomado de la publicación