[1] www.robots.ox.ac.uk/ vgg/research/encoding eval. [2] J. Sivic and A. Zisserman. Proc. ICCV, 2003. [3] J. Philbin et al. Proc. CVPR, 2008. [4] J. C. van Gemert et al. Proc. ECCV, 2008. [5] J. Wang et al. Proc. CVPR, 2010. [6] F. Perronnin et al. Proc. ECCV, 2010. [7] X. Zhou et al. Proc. ECCV, 2010. Histogram (VQ) 8, 000 74.23± 0.65 Kernel Codebook (KCB) 8, 000 75.93± 0.57 Locality Constrain...

Recent investigations into the assessment and evaluation of “creative” systems in the field of computational creativity have disclosed several problems common to research within the field. We perform a practical evaluation of the latest iteration of the creative system, DARCI, attempting to address some of these problems using a specially designed, but generalizable, online human survey. Of not...

User development of computer-based applications (UDA) is a new phenomenon in organizations, and can provide benefits for both users and for data processing departments. The benefits of UDA to DP departments are consi.dered in this paper. The UDA literature suggests that the DP departments can expect to receive two major types of benefits: the backlog of DP appl ication devel opment projects sho...

This paper reviews empirical research on the use of evaluation from 1986 to 2005 using Cousins and Leithwood’s 1986 framework for categorizing empirical studies of evaluation use conducted since that time. The literature review located 41 empirical studies of evaluation use conducted between 1986 and 2005 that met minimum quality standards. The Cousins and Leithwood framework allowed a comparis...

Pairwise comparison data are used in various contexts including the generation of weight vectors for multiple criteria decision making problems. If this data is not sufficiently consistent, then the resulting weight vector cannot be considered to be a reliable reflection of the evaluator s opinion. Hence, it is necessary to measure its level of inconsistency. Different approaches have been prop...

We study a Bayesian game of two-sided incomplete information in which an agent, who owns a project of unknown quality, considers proposing it to an evaluator, who has the choice of whether or not to accept it. There exist two distinct tiers of evaluation that di¤er in the bene…ts they deliver to the agent upon acceptance of a project. The agent has to select the tier to which the project is sub...

Performance of machine learning algorithms depends critically on identifying a good set of hyperparameters. While recent approaches use Bayesian Optimization to adaptively select configurations, we focus on speeding up random search through adaptive resource allocation. We present HYPERBAND, a novel algorithm for hyperparameter optimization that is simple, flexible, and theoretically sound. HYP...

machine encoding −−−−−→ functional program program transformation −−−−−−−−−−−−→ tail-recursive functional program decoding −−−−−→ abstract machine Our method proposes a new tool for the ‘encoding’ part, as there are multiple choices of how one represents an abstract machine as a functional program. In particular, one can use different data structures to represent the type of the stack of the or...