Discriminative and Non-discriminative Knowledge
نویسندگان
چکیده
منابع مشابه
Discriminative Object Categorization with External Semantic Knowledge
Visual object category recognition is one of the most challenging problems in computer vision. While effortless for humans, it is inherently difficult for machines because of the visual variations such as lighting, pose, clutter and occlusion. Even assuming that we can obtain perfect instance-level visual representations, the object category recognition problem still remains difficult for machi...
متن کاملGenerative Prior Knowledge for Discriminative Classification
We present a novel framework for integrating prior knowledge into discriminative classifiers. Our framework allows discriminative classifiers such as Support Vector Machines (SVMs) to utilize prior knowledge specified in the generative setting. The dual objective of fitting the data and respecting prior knowledge is formulated as a bilevel program, which is solved (approximately) via iterative ...
متن کاملDiscriminative Information Retrieval for Knowledge Discovery
We propose a framework for discriminative Information Retrieval (IR) atop linguistic features, trained to improve the recall of tasks such as answer candidate passage retrieval, the initial step in text-based Question Answering (QA). We formalize this as an instance of linear feature-based IR (Metzler and Croft, 2007), illustrating how a variety of knowledge discovery tasks are captured under t...
متن کاملDiscriminative Pruning for Discriminative ITG Alignment
While Inversion Transduction Grammar (ITG) has regained more and more attention in recent years, it still suffers from the major obstacle of speed. We propose a discriminative ITG pruning framework using Minimum Error Rate Training and various features from previous work on ITG alignment. Experiment results show that it is superior to all existing heuristics in ITG pruning. On top of the prunin...
متن کاملDiscriminative skill and discriminative matching in perceptual recognition.
An important aspect of any recognition or identification task is one's knowledge of the set of alternative items from which the stimuli are drawn. In general, we can respond most accurately when we have the fullest knowledge of what stimulus events are possible. In many recognition experiments, however, the set of possible stimuli is left ambiguous at first and only after considerable experienc...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: JOURNAL OF INDIAN AND BUDDHIST STUDIES (INDOGAKU BUKKYOGAKU KENKYU)
سال: 1967
ISSN: 1884-0051,0019-4344
DOI: 10.4259/ibk.16.1