Hasil untuk "Logic"

J. Torio, R. T. Bigueras, D. E. Maligat et al.

Gamification is the application of game design elements and game mechanics in a non-game context. This concept has been successfully used in several fields such as businesses and education. As such, the gamification e-learning approach could be used in education, particularly in a digital logic subject area, as a tool to improve student engagement. However, few research and design guidelines exist regarding a gamified learning approach for digital logic. The objective of this paper is to propose a complete framework for the development of a gamified learning application for digital logic gates that will improve student’s engagement. We first investigate the design, the principles, and parameters used to measure student engagement from a variety of related work and identify which design, principles and parameters that shall be applicable and significant in the development of a gamified learning application that will drive an engaged student. This framework shall provide the game developers a guide and shall help standardize the development process of a gamified learning approach in a digital logic subject area in the future.

Shawn M. Douglas, I. Bachelet, G. Church

J. Borghetti, G. Snider, P. Kuekes et al.

E. Clarke

R. Lusch, S. Vargo, Matthew O'Brien

P. Subramanyan, Sayak Ray, S. Malik

A. Przeworski, H. Teune

S. Muggleton, L. D. Raedt

Abstract Inductive Logic Programming (ILP) is a new discipline which investigates the inductive construction of first-order clausal theories from examples and background knowledge. We survey the most important theories and methods of this new field. First, various problem specifications of ILP are formalized in semantic settings for ILP, yielding a “model-theory” for ILP. Second, a generic ILP algorithm is presented. Third, the inference rules and corresponding operators used in ILP are presented, resulting in a “proof-theory” for ILP. Fourth, since inductive inference does not produce statements which are assured to follow from what is given, inductive inferences require an alternative form of justification. This can take the form of either probabilistic support or logical constraints on the hypothesis language. Information compression techniques used within ILP are presented within a unifying Bayesian approach to confirmation and corroboration of hypotheses. Also, different ways to constrain the hypothesis language or specify the declarative bias are presented. Fifth, some advanced topics in ILP are addressed. These include aspects of computational learning theory as applied to ILP, and the issue of predicate invention. Finally, we survey some applications and implementations of ILP. ILP applications fall under two different categories: first, scientific discovery and knowledge acquisition, and second, programming assistants.

M. Gelfond, V. Lifschitz

R. Lusch, S. Vargo

D. Hofmann

J. Jaffar, Michael J. Maher

M. Gordon, T. Melham

H. Enderton

N. N. Karnik, J. Mendel, Q. Liang

Q. Liang, J. Mendel

R. Lusch, S. Vargo

D. Allwood, Gang Xiong, C. Faulkner et al.

Zhiting Hu, Xuezhe Ma, Zhengzhong Liu et al.

Combining deep neural networks with structured logic rules is desirable to harness flexibility and reduce uninterpretability of the neural models. We propose a general framework capable of enhancing various types of neural networks (e.g., CNNs and RNNs) with declarative first-order logic rules. Specifically, we develop an iterative distillation method that transfers the structured information of logic rules into the weights of neural networks. We deploy the framework on a CNN for sentiment analysis, and an RNN for named entity recognition. With a few highly intuitive rules, we obtain substantial improvements and achieve state-of-the-art or comparable results to previous best-performing systems.

Peter A. Flach