Explanation-Based Learning for Image Understanding
نویسندگان
چکیده
Existing prior domain knowledge represents a valuable source of information for image interpretation problems such as classifying handwritten characters. Such domain knowledge must be translated into a form understandable by the learner. Translation can be realized with Explanation-Based Learning (EBL) which provides a kind of dynamic inductive bias, combining domain knowledge and training examples. The dynamic bias formed by the interaction of domain knowledge with training examples can yield solution knowledge of potential higher quality than can be anticipated by the static bias designer without seeing training examples. We detail how EBL can be used to dynamically integrate domain knowledge, training examples, and the learning mechanism, and describe the two EBL approaches in (Sun & DeJong 2005a) and (Sun & DeJong 2005b).
منابع مشابه
Enhancement of Learning Based Image Matting Method with Different Background/Foreground Weights
The problem of accurate foreground estimation in images is called Image Matting. In image matting methods, a map is used as learning data, which is produced by those pixels that are definitely foreground, definitely background ,and unknown. This three-level pixel map is often referred to as a trimap, which is produced manually in alpha matte datasets. The true class of unknown pixels will be es...
متن کاملPhenomenological Explanation of Curriculum Principles of the Teaching Experience (Internship) in Farhangian University
The purpose of this study was to define the curriculum principles of Teaching Experience based on the lived experiences of the successful teachers. In this study, a qualitative method with a phenomenological approach was used. The participants were 9 teachers and professors who were selected purposefully. Data were collected by using in-depth interview and analyzed by thematic coding. Among the...
متن کاملExplanation of functional factors affecting the success of public spaces and providing a model for assessing success through its functional dimension (Case study: Imam Khomeini Street, Tabriz, Iran)
The condition that varieties of cities including Iranian cities are confronted makes the creation of successful public space a necessity. It is clear that for creating suitable public space first we should understand the influencing factors on space and simultaneously solve and improve the problems through understanding the environment. For achieving the factors that influence the success as a ...
متن کاملVision-Based Navigation and Deep-Learning Explanation for Autonomy
In this thesis, we investigate vision-based techniques to support robot mobile autonomy in human environments, including also understanding the important image features with respect to a classification task. Given this wide goal of transparent vision-based autonomy, the work proceeds along three main fronts. Our first algorithm enables a UAV to visually localize and navigate with respect to CoB...
متن کاملImage Classification via Sparse Representation and Subspace Alignment
Image representation is a crucial problem in image processing where there exist many low-level representations of image, i.e., SIFT, HOG and so on. But there is a missing link across low-level and high-level semantic representations. In fact, traditional machine learning approaches, e.g., non-negative matrix factorization, sparse representation and principle component analysis are employed to d...
متن کامل