Deep learning networks have achieved state-of-the-art accuracies on computer vision workloads like image classification and object detection. The performant systems, however, typically involve big models with numerous parameters. Once trained, a challenging aspect for such top performing models is deployment on resource constrained inference systems — the models (often deep networks or wide net...

A p l a n calculus is presented which is being used to represent p r o g r a m s and a l i b ra ry of standard data and control abstractions in t h e p r o g r a m m e r ' s apprent ice . Important features of this formalism i n c l u d e : p rogramming language independence, additivity, v e r i f i a b i l i t y and mult ip le points of v iew. The logical foundations of t h e r e p r e s e n t...

Learning interface agents search regularities in the user behavior and use them to predict user’s actions. We propose a new inductive concept learning approach, called IBHYS, to learn such regularities. This approach limits the hypothesis search to a small portion of the hypothesis space by letting each training example build a local approximation of the global target function. It allows to sim...

The aim of this cross-sectional study was to compare the blood lead levels of apprentices working in lead-related industries with those of non-apprentice controls and to evaluate the influence of such occupational exposure. The study was conducted between October 2004 and June 2005 in Bursa, Turkey. Subjects included 231 apprentices and 252 male controls, age ranging from 14-19 yr old. Inductiv...

There have been many recent efforts in contentbased retrieval to perform automatic classification of images/visual objects. Most approaches, however, have focused on using individual classifiers. In this paper, we study the way in which, in a dynamic framework, multiple classifiers can be combined when applying Visual Object Detectors. We propose a hybrid classifier combination approach, in whi...

The goal of imitation learning is for an apprentice to learn how to behave in a stochastic environment by observing a mentor demonstrating the correct behavior. Accurate prior knowledge about the correct behavior can reduce the need for demonstrations from the mentor. We present a novel approach to encoding prior knowledge about the correct behavior, where we assume that this prior knowledge ta...

It is well accepted that knowledge base development and maintenance costs are key obstacles to the further proliferation of knowledge-based systems. We consider here an approach to dramatically reduce this cost by developing learning apprentice systems: knowledge-based advisors which learn from their users throughout their life-cycle. In particular, we present a learning apprentice for calendar...

BACKGROUND In 2008 the Cystic Fibrosis (CF) Foundation launched the Respiratory Therapy Mentoring Program, which pairs a respiratory therapist (RT) relatively new to CF (apprentice) with a highly experienced RT (mentor) from a similar CF care center. We wished to determine if we had achieved our short-term goal of increasing CF-specific knowledge among the apprentices who participated in the pr...