oalib

Publish in OALib Journal

ISSN: 2333-9721

APC: Only $99

Submit

Any time

2019 ( 10 )

2018 ( 14 )

2017 ( 17 )

2016 ( 19 )

Custom range...

Search Results: 1 - 10 of 10167 matches for " Sergio Guadarrama "
All listed articles are free for downloading (OA Articles)
Page 1 /10167
Display every page Item
Compute Less to Get More: Using ORC to Improve Sparse Filtering
Johannes Lederer,Sergio Guadarrama
Computer Science , 2014,
Abstract: Sparse Filtering is a popular feature learning algorithm for image classification pipelines. In this paper, we connect the performance of Sparse Filtering with spectral properties of the corresponding feature matrices. This connection provides new insights into Sparse Filtering; in particular, it suggests early stopping of Sparse Filtering. We therefore introduce the Optimal Roundness Criterion (ORC), a novel stopping criterion for Sparse Filtering. We show that this stopping criterion is related with pre-processing procedures such as Statistical Whitening and demonstrate that it can make image classification with Sparse Filtering considerably faster and more accurate.
Using Soft Constraints To Learn Semantic Models Of Descriptions Of Shapes
Sergio Guadarrama,David P. Pancho
Computer Science , 2010,
Abstract: The contribution of this paper is to provide a semantic model (using soft constraints) of the words used by web-users to describe objects in a language game; a game in which one user describes a selected object of those composing the scene, and another user has to guess which object has been described. The given description needs to be non ambiguous and accurate enough to allow other users to guess the described shape correctly. To build these semantic models the descriptions need to be analyzed to extract the syntax and words' classes used. We have modeled the meaning of these descriptions using soft constraints as a way for grounding the meaning. The descriptions generated by the system took into account the context of the object to avoid ambiguous descriptions, and allowed users to guess the described object correctly 72% of the times.
Approximate Robotic Mapping from sonar data by modeling Perceptions with Antonyms
Sergio Guadarrama,Antonio Ruiz-Mayor
Computer Science , 2010,
Abstract: This work, inspired by the idea of "Computing with Words and Perceptions" proposed by Zadeh in 2001, focuses on how to transform measurements into perceptions for the problem of map building by Autonomous Mobile Robots. We propose to model the perceptions obtained from sonar-sensors as two grid maps: one for obstacles and another for empty spaces. The rules used to build and integrate these maps are expressed by linguistic descriptions and modeled by fuzzy rules. The main difference of this approach from other studies reported in the literature is that the method presented here is based on the hypothesis that the concepts "occupied" and "empty" are antonyms rather than complementary (as it happens in probabilistic approaches), or independent (as it happens in the previous fuzzy models). Controlled experimentation with a real robot in three representative indoor environments has been performed and the results presented. We offer a qualitative and quantitative comparison of the estimated maps obtained by the probabilistic approach, the previous fuzzy method and the new antonyms-based fuzzy approach. It is shown that the maps obtained with the antonyms-based approach are better defined, capture better the shape of the walls and of the empty-spaces, and contain less errors due to rebounds and short-echoes. Furthermore, in spite of noise and low resolution inherent to the sonar-sensors used, the maps obtained are accurate and tolerant to imprecision.
Diagnóstico precoz de embarazo en la atención primaria mediante determinación cualitativa de gonadotropina coriónica humana
Armando Lozano Guadarrama,Francisco Martínez Moreira,Sergio Santana Porbeu,Remigio Coto Rodeiro
Revista Cubana de Medicina General Integral , 1998,
Abstract: Se presentan los resultados de la aplicación de un método cualitativo no instrumental, auxiliar de la práctica clínica para el diagnóstico del embarazo en un consultorio médico. El ensayo se basó en la detección de la hormona gonadotropina coriónica en la orina de mujeres fértiles con amenorrea, mediante un immunoensayo enzimático desarrollado en el Instituto Nacional de Endocrinología. La determinación se caracterizó por una sensibilidad del 85 %, una especificidad del 95 % y una exactitud del 90 %(para un límite de clasifiación positivo de 100 UI de HC g/L). La coincidencia del método cualitativo con uno cuantitativo fue del 90 %. Aunque la sensibilidad del método cualitativo fue inferior a los requerimientos expuestos en la literatura especializada revisada, se recomienda su uso por los médicos de la familia, como una arma auxiliar en el diagnóstico precoz del embarazo, por su elevada especificidad, buena correlación con el método cuantitativo y su relativa sencillez operacional The results of the implementation of a non-instrumental qualitative method, a clinical practical aid for the diagnosis of pregnancy at a family physician consulting room is presented. The trial consisted of detecting chorionic gonadotropin hormone in urie of amenorrheic fertile women through an enzime-based inmunoassay developed at the National Endocrinology Institute. This determination was characterization by 85 % sensitivity, 95 % specificity and 90 % accuracy (for a positive classification limit of 100 UI Hc g/L). There was 90 % coincidence between the qualitative and quantitative methods. Although this qualitative method sensitivity was lower than that required in the reviewed specialized literature, its use by family physicians is recommended as an auxiliary tool for the early diagnosis of pregnancy because of its high specificity, good correlation with the quantitative method and relative operational simplicity
Long-term Recurrent Convolutional Networks for Visual Recognition and Description
Jeff Donahue,Lisa Anne Hendricks,Sergio Guadarrama,Marcus Rohrbach,Subhashini Venugopalan,Kate Saenko,Trevor Darrell
Computer Science , 2014,
Abstract: Models based on deep convolutional networks have dominated recent image interpretation tasks; we investigate whether models which are also recurrent, or "temporally deep", are effective for tasks involving sequences, visual and otherwise. We develop a novel recurrent convolutional architecture suitable for large-scale visual learning which is end-to-end trainable, and demonstrate the value of these models on benchmark video recognition tasks, image description and retrieval problems, and video narration challenges. In contrast to current models which assume a fixed spatio-temporal receptive field or simple temporal averaging for sequential processing, recurrent convolutional models are "doubly deep"' in that they can be compositional in spatial and temporal "layers". Such models may have advantages when target concepts are complex and/or training data are limited. Learning long-term dependencies is possible when nonlinearities are incorporated into the network state updates. Long-term RNN models are appealing in that they directly can map variable-length inputs (e.g., video frames) to variable length outputs (e.g., natural language text) and can model complex temporal dynamics; yet they can be optimized with backpropagation. Our recurrent long-term models are directly connected to modern visual convnet models and can be jointly trained to simultaneously learn temporal dynamics and convolutional perceptual representations. Our results show such models have distinct advantages over state-of-the-art models for recognition or generation which are separately defined and/or optimized.
LSDA: Large Scale Detection Through Adaptation
Judy Hoffman,Sergio Guadarrama,Eric Tzeng,Ronghang Hu,Jeff Donahue,Ross Girshick,Trevor Darrell,Kate Saenko
Computer Science , 2014,
Abstract: A major challenge in scaling object detection is the difficulty of obtaining labeled images for large numbers of categories. Recently, deep convolutional neural networks (CNNs) have emerged as clear winners on object classification benchmarks, in part due to training with 1.2M+ labeled classification images. Unfortunately, only a small fraction of those labels are available for the detection task. It is much cheaper and easier to collect large quantities of image-level labels from search engines than it is to collect detection data and label it with precise bounding boxes. In this paper, we propose Large Scale Detection through Adaptation (LSDA), an algorithm which learns the difference between the two tasks and transfers this knowledge to classifiers for categories without bounding box annotated data, turning them into detectors. Our method has the potential to enable detection for the tens of thousands of categories that lack bounding box annotations, yet have plenty of classification data. Evaluation on the ImageNet LSVRC-2013 detection challenge demonstrates the efficacy of our approach. This algorithm enables us to produce a >7.6K detector by using available classification data from leaf nodes in the ImageNet tree. We additionally demonstrate how to modify our architecture to produce a fast detector (running at 2fps for the 7.6K detector). Models and software are available at
Caffe: Convolutional Architecture for Fast Feature Embedding
Yangqing Jia,Evan Shelhamer,Jeff Donahue,Sergey Karayev,Jonathan Long,Ross Girshick,Sergio Guadarrama,Trevor Darrell
Computer Science , 2014,
Abstract: Caffe provides multimedia scientists and practitioners with a clean and modifiable framework for state-of-the-art deep learning algorithms and a collection of reference models. The framework is a BSD-licensed C++ library with Python and MATLAB bindings for training and deploying general-purpose convolutional neural networks and other deep models efficiently on commodity architectures. Caffe fits industry and internet-scale media needs by CUDA GPU computation, processing over 40 million images a day on a single K40 or Titan GPU ($\approx$ 2.5 ms per image). By separating model representation from actual implementation, Caffe allows experimentation and seamless switching among platforms for ease of development and deployment from prototyping machines to cloud environments. Caffe is maintained and developed by the Berkeley Vision and Learning Center (BVLC) with the help of an active community of contributors on GitHub. It powers ongoing research projects, large-scale industrial applications, and startup prototypes in vision, speech, and multimedia.
Rese a de "Pobreza urbana: perspectivas globales, nacionales y locales" del Gobierno del Estado de México
Gloria Guadarrama
Economía, sociedad y territorio , 2003,
Abstract:
Diagnóstico precoz de embarazo en la atención primaria mediante determinación cualitativa de gonadotropina coriónica humana
Lozano Guadarrama,Armando; Martínez Moreira,Francisco; Santana Porbeu,Sergio; Coto Rodeiro,Remigio; García Dafonte,Gema;
Revista Cubana de Medicina General Integral , 1998,
Abstract: the results of the implementation of a non-instrumental qualitative method, a clinical practical aid for the diagnosis of pregnancy at a family physician consulting room is presented. the trial consisted of detecting chorionic gonadotropin hormone in urie of amenorrheic fertile women through an enzime-based inmunoassay developed at the national endocrinology institute. this determination was characterization by 85 % sensitivity, 95 % specificity and 90 % accuracy (for a positive classification limit of 100 ui hc g/l). there was 90 % coincidence between the qualitative and quantitative methods. although this qualitative method sensitivity was lower than that required in the reviewed specialized literature, its use by family physicians is recommended as an auxiliary tool for the early diagnosis of pregnancy because of its high specificity, good correlation with the quantitative method and relative operational simplicity
FACTORES DE RIESGO DE ANOREXIA Y BULIMIA NERVIOSA EN ESTUDIANTES DE PREPARATORIA: UN ANáLISIS POR SEXO
Rosalinda Guadarrama Guadarrama,Sheila Adriana Mendoza Mojica
Ense?anza e Investigación en Psicología , 2011,
Abstract: Este estudio identifica los factores de riesgo de anorexia y bulimia nerviosa en estudiantes de preparatoria de acuerdo a su sexo. Se trabajó con 316 alumnos de ambos sexos de una escuela privada del nivel medio superior. Los instrumentos aplicados fueron el Test de Bulit y el Test de Actitudes Alimentarias, los cuales cuentan con propiedades psicométricas adecuadas a la población mexicana. Los resultados muestran que 17% de la muestra estudiada mostró síntomas de trastorno alimentario, predominando la anorexia y siendo mayor en las mujeres, siendo estas el grupo que estableció las diferencias estadísticamente significativas en ambas variables. Los resultados permiten concluir que los adolescentes de zonas externas a las grandes urbes pudieran ser propensos a desarrollar este tipo de trastornos, siendo las mujeres el grupo más afectado.
Page 1 /10167
Display every page Item


Home
Copyright © 2008-2017 Open Access Library. All rights reserved.