In this paper we argue that most commercially available authoring systems are not powerful enough for the development of specialized presentations such as courseware for teaching computer science. We briefly review several existing authoring systems and show their weak points. Then, we describe the design and implementation of OBJECTOR, an object-oriented authoring system. OBJECTOR is an author...

We present a method for object detection that combines AdaBoost learning with local histogram features. On the side of learning we improve the performance by designing a weak learner for multi-valued features based on Weighted Fisher Linear Discriminant. Evaluation on the recent benchmark for object detection confirms the superior performance of our method compared to the state-of-the-art. In p...

Class binarizations are effective methods for improving weak learners by decomposing multi-class problems into several two-class problems. This paper analyzes how these methods can be applied to a Naive Bayes learner. The key result is that the pairwise variant of Naive Bayes is equivalent to a regular Naive Bayes. This result holds for several aggregation techniques for combining the predictio...

Weak Line Water Vapor Spectra in the Region 13 200–15 000 cm−1 Roland Schermaul,∗ Richard C. M. Learner,∗,1 A. A. D. Canas,† J. W. Brault,† Oleg L. Polyansky,‡,2 Djedjiga Belmiloud,‡ Nikolai F. Zobov,‡,2 and Jonathan Tennyson,‡,3 ∗Laser Optics & Spectroscopy, Blackett Laboratory, Imperial College of Science, Technology and Medicine, Prince Consort Road, London SW7 2BW, United Kingdom; †LASP (Sp...

This paper develops a novel methodology for using symbolic knowledge in deep learning. We define a semantic loss function that bridges between neural output vectors and logical constraints. This loss function captures how close the neural network is to satisfying the constraints on its output. An experimental evaluation shows that our semantic loss function effectively guides the learner to ach...

In this paper, we establish the convergence of the Optimal AdaBoost classifier under mild conditions. We frame AdaBoost as a dynamical system, and provide sufficient conditions for the existence of an invariant measure. Employing tools from ergodic theory, we show that the margin for every example converges. More generally, we prove that the time average of any function of the weights over the ...

A blind learner needs some method other than Venn diagrams to test syllogisms for validity. I present here a sketch of a three-dimensional apparatus, Sylloid, invented to fill this need and to inculcate deep learning rather than the mere ability to get answers right. What one learns in the design process is then used in designing a successor, Son of Sylloid, for sighted users that is pedagogica...

this study investigated the effect of applying the dynamic system theory (dst) and cognitive linguistics (cl) insights into grammar instruction on efl learners’ learning of english prepositions and learner autonomy. sixty iranian efl learners at the lower-intermediate level of language proficiency were randomly assigned to 1 experimental and 1 control group. the 2 groups filled out an autonomy ...

Modifying standard gradient boosting by replacing the embedded weak learner in favor of a strong(er) one, we present SyRBo: Symbolic-Regression Boosting. Experiments over 98 regression datasets show that adding small number stages -- between 2--5 to symbolic regressor, statistically significant improvements can often be attained. We note coding SyRBo on top any regressor is straightforward, and...

This study attempted to investigate the relationship among learning strategy, autonomy and language proficiency of Chinese university EFL students. To achieve this objective, purposive sampling and cluster sampling methods were used to select 422 non-English major students as participants in three universities, Henan province, China. Oxford’s (1990) Strategy Inventory for Language Learning (SIL...