Pretraining Convolutional Neural Networks for Visual Recognition

Convolutional Neural Networks (CNN) have become the state-of-the-art methods on many large scale visual recognition tasks. For a lot of practical applications, CNN architectures have a restrictive requirement: A huge amount of labeled data are needed for training. The idea of generative pretraining is to obtain initial weights of the network by training the network in a completely unsupervised way and then fine-tune the weights for the task at hand using supervised learning. In this thesis, a general introduction to Deep Neural Networks and algorithms are given and these methods are applied to classification tasks of handwritten digits and natural images for developing unsupervised feature learning. The goal of this thesis is to find out if the effect of pretraining is damped by recent practical advances in optimization and regularization of CNN. The experimental results show that pretraining is still a substantial regularizer, however, not a necessary step in training Convolutional Neural Networks with rectified activations. On handwritten digits, the proposed pretraining model achieved a classification accuracy comparable to the state-of-the-art methods.

La vitrina, herramienta de negocios y promoción visual : Consejos prácticos

Bogotá Emprende

La vitrina: herramienta de negocios y promoción visual : Guía de consulta

Bogotá Emprende

Perceived effectiveness of alternative programming : a case study /

The topic of this research was alternative programming in secondary public education. The purpose of this research was to explore the perceived effectiveness of two public secondary programs that are aJternative to mainstream or "regular" education. Two case study sites were used to research diverse ends of the aJtemative programming continuum. The first case study demonstrated a gifted program and the second demonstrated a behavioral program. Student needs were examined in terms of academic needs, emotional needs, career needs, and social needs. Research conducted in these sites examined how the students, teachers, onsite staff, and program administrators perceived that individual needs were met and unmet in these two programs. The study was qualitative and exploratory, using deductive and inductive research techniques. Similar themes of best practice that were identified in the case study sites aided in the development of a teaching and learning model. Four themes were identified as important within the case study sites. These themes included the commitment and motivation of teachers and the support of administration in the gifted program, and the importance of location and the flow of information and communication in the behavior program. Six themes emerged that were similar across the case study sites. These themes included the individual nature of programming, recognition of student achievement, the alternative program as a place of safety and community, importance of interpersonal capacity, priority of basic needs, and, finally, matching student capacity with program expectations. The model incorporates these themes and is designed as a resource for teachers, program administrators, parents, and policy makers of alternative educational programs.

From inference to affordance : the problem of visual depth-perception in the optical writings of Descartes, Berkeley, and Gibson

This thesis explores the debate and issues regarding the status of visual ;,iferellces in the optical writings of Rene Descartes, George Berkeley and James 1. Gibson. It gathers arguments from across their works and synthesizes an account of visual depthperception that accurately reflects the larger, metaphysical implications of their philosophical theories. Chapters 1 and 2 address the Cartesian and Berkelean theories of depth-perception, respectively. For Descartes and Berkeley the debate can be put in the following way: How is it possible that we experience objects as appearing outside of us, at various distances, if objects appear inside of us, in the representations of the individual's mind? Thus, the Descartes-Berkeley component of the debate takes place exclusively within a representationalist setting. Representational theories of depthperception are rooted in the scientific discovery that objects project a merely twodimensional patchwork of forms on the retina. I call this the "flat image" problem. This poses the problem of depth in terms of a difference between two- and three-dimensional orders (i.e., a gap to be bridged by one inferential procedure or another). Chapter 3 addresses Gibson's ecological response to the debate. Gibson argues that the perceiver cannot be flattened out into a passive, two-dimensional sensory surface. Perception is possible precisely because the body and the environment already have depth. Accordingly, the problem cannot be reduced to a gap between two- and threedimensional givens, a gap crossed with a projective geometry. The crucial difference is not one of a dimensional degree. Chapter 3 explores this theme and attempts to excavate the empirical and philosophical suppositions that lead Descartes and Berkeley to their respective theories of indirect perception. Gibson argues that the notion of visual inference, which is necessary to substantiate representational theories of indirect perception, is highly problematic. To elucidate this point, the thesis steps into the representationalist tradition, in order to show that problems that arise within it demand a tum toward Gibson's information-based doctrine of ecological specificity (which is to say, the theory of direct perception). Chapter 3 concludes with a careful examination of Gibsonian affordallces as the sole objects of direct perceptual experience. The final section provides an account of affordances that locates the moving, perceiving body at the heart of the experience of depth; an experience which emerges in the dynamical structures that cross the body and the world.

What happens in the first 200 ms of word reading : ERP studies on visual word recognition with top-down and bottom-up approaches /

In this thesis, three main questions were addressed using event-related potentials (ERPs): (1) the timing of lexical semantic access, (2) the influence of "top-down" processes on visual word processing, and (3) the influence of "bottom-up" factors on visual word processing. The timing of lexical semantic access was investigated in two studies using different designs. In Study 1,14 participants completed two tasks: a standard lexical decision (LD) task which required a word/nonword decision to each target stimulus, and a semantically primed version (LS) of it using the same category of words (e.g., animal) within each block following which participants made a category judgment. In Study 2, another 12 participants performed a standard semantic priming task, where target stimulus words (e.g., nurse) could be either semantically related or unrelated to their primes (e.g., doctor, tree) but the order of presentation was randomized. We found evidence in both ERP studies that lexical semantic access might occur early within the first 200 ms (at about 170 ms for Study 1 and at about 160 ms for Study 2). Our results were consistent with more recent ERP and eye-tracking studies and are in contrast with the traditional research focus on the N400 component. "Top-down" processes, such as a person's expectation and strategic decisions, were possible in Study 1 because of the blocked design, but they were not for Study 2 with a randomized design. Comparing results from two studies, we found that visual word processing could be affected by a person's expectation and the effect occurred early at a sensory/perceptual stage: a semantic task effect in the PI component at about 100 ms in the ERP was found in Study 1 , but not in Study 2. Furthermore, we found that such "top-down" influence on visual word processing might be mediated through separate mechanisms depending on whether the stimulus was a word or a nonword. "Bottom-up" factors involve inherent characteristics of particular words, such as bigram frequency (the total frequency of two-letter combinations of a word), word frequency (the frequency of the written form of a word), and neighborhood density (the number of words that can be generated by changing one letter of an original word or nonword). A bigram frequency effect was found when comparing the results from Studies 1 and 2, but it was examined more closely in Study 3. Fourteen participants performed a similar standard lexical decision task but the words and nonwords were selected systematically to provide a greater range in the aforementioned factors. As a result, a total of 18 word conditions were created with 18 nonword conditions matched on neighborhood density and neighborhood frequency. Using multiple regression analyses, we foimd that the PI amplitude was significantly related to bigram frequency for both words and nonwords, consistent with results from Studies 1 and 2. In addition, word frequency and neighborhood frequency were also able to influence the PI amplitude separately for words and for nonwords and there appeared to be a spatial dissociation between the two effects: for words, the word frequency effect in PI was found at the left electrode site; for nonwords, the neighborhood frequency effect in PI was fovind at the right elecfrode site. The implications of otir findings are discussed.

Engineers and technicians : the effect of cognitive style and gender on visual information processing

The purpose of this project was to identify in a subject group of engineers and technicians (N = 62) a preferred mode of representation for facilitating correct recall of information from complex graphics. The modes of representation were black and white (b&w) block, b&w icon, color block, and color icon. The researcher's test instrument included twelve complex graphics (six b&w and six color - three per mode). Each graphics presentation was followed by two multiple-choice questions. Recall performance was better using b&w block mode graphics and color icon mode graphics. A standardized test, the Group Embedded Figures Test (GEFT) was used to identify a cognitive style preference (field dependence). Although engineers and technicians in the sample were strongly field-independent, they were not significantly more field-independent than the normative group in the Witkin, Oltman, Raskin, and Karp study (1971). Tests were also employed to look for any significant difference in cognitive style preference due to gender. None was found. Implications from the project results for the design of visuals and their use in technical training are discussed.

Sinister creativity: a phenomenological exploration of some of the experiences and perceptions of six lefthanded visual artists

Six lefthanded artist-educators were interviewed to attempt to discover any patterns t6 their perceptions and experiences. Artists have their own culture and priorities. According to the literature, lefthanded people appear more likely to suffer from dyslexia, allergies, asthma and other auto-immune diseases as well as machinery and equipment injuries. Patterns emerging suggested that lefthanded people indeed suffer more from dyslexia. More startling was the distinct possibility that many artists have traumatic childhood histories. This would commonly include negative school experiences, and for a significant number sexual assault, perceived or actual abandonment by parents, and/or consistently low selfesteem. The researcher discovered possible reasons why creative people frequently have problems at school, why they tend to be rebellious and anti-establishment oriented, how many of them perceive societal rules, and why they are more likely to be lefthanded. These characteristics all have significant implications for art school administrators.

Visual word learning in good and poor readers

Forty students from regular, grade five classes were divided into two groups of twenty, a good reader group and a' poor reader group, on the basis. of their reading scores on Canadian Achievement Tests. .The subjects took. part in four experimental conditions iM which they .learned lists of pronounceable and unprono~nceable pseudowords, some with semantic referents, and responded to questions designed tci test visual perceptu~l learning and lexical ·and semantic association learning. It' was hypothesized "that the good reade~ group would be able to make use of graphemic and phonemic redundancy patterns in order to improv~·visuSl perceptual learning and lexical and semantic association lea~ningto a greater extent. than would .the poor reader gr6up. The data supported this hypothesis, and also indicated that, although the poor readers were less adept at using familiar sound and letter patterns, they were more dependent on· such pa~terns as an aid to visual recognition memory and semantic recall than were the good readers. It wa.s postulated that poor readers are in a double- ~ . bind situatio~ of having to choose between using weak graphemic-semantic associations or gr~pheme-phoneme associations which are also weak and which have hindered them in developing automaticity in. reading.