We present an extensive experimental study of a Statistical Machine Translation system, Moses [14], from the point of view of its learning capabilities, and we discuss learning-theoretic aspects of these systems, including model selection, representation error, estimation error and hypothesis space. Very accurate Learning Curves are obtained, by using high-performance computing, and extrapolati...

Although case-based reasoning (CBR) was introduced as an alternative to rule-based reasoning (RBR), there is a growing interest in integrating it with other reasoning paradigms, including RBR. New hybrid approaches are being piloted to achieve new synergies and improve problem-solving capabilities. In our approach to integration, CBR is used to satisfy multiple numeric constraints, and RBR allo...

Modern embedding methods focus only on the words in the text. The word or sentence embeddings are trained to represent the semantic meaning of the raw texts. However, many quantified attributes associated with the text, such as numeric attributes associated with Yelp review text, are ignored in the vector representation learning process. Those quantified numeric attributes can provide important...

Numeric abstract domains are key to many verification problems. Their ability to scale hinges on using convex approximations of the possible variable valuations. In certain cases, this approximation is too coarse to verify certain verification conditions, namely those that require disjunctive invariants. A common approach to infer disjunctive invariants is to track a set of states. However, thi...

Automated planning is computationally hard even in its most basic form as STRIPS planning. We are interested in numeric planning with instantaneous actions, a problem that is not decidable in general. Relaxation is an approach to simplifying complex problems in order to obtain guidance in the original problem. We present a relaxation approach with intervals for numeric planning and show that pl...

This paper proposes a qualitative representation for robot kinematics in order to close the gap, raised by the perception–action problem, with a focus on intelligent connection of qualitative states to their corresponding numeric data in a robotic system. First, qualitative geometric primitives are introduced by combining a qualitative orientation component and qualitative translation component...

The excitation of high-frequency short-wavelength spin waves is a challenge limiting the application these propagating magnetization disturbances in information processing systems. We propose method local using non-linear nature dynamics. demonstrate with numeric simulations that an edge-localized wave can be used to excite plane obliquely from film's edge at doubled frequency and over twice sh...

The design of a novel curve microstripline 2x2 array antenna is presented in this research. In design, work X Band frequency. total size 40mm x 40mm. result indicates that the characteristics parametric showed by Voltage Standing Wave Ratio (VSWR≤2) proposed 1.06 (in simulated); 1.29 measured) and 1.20 numeric analyzed), bandwidth 260.0 MHz simulated) 310.0 reflection coefficient 0.03 0.17 retu...

Discretization can turn numeric attributes into discrete ones. Feature selection can eliminate some irrelevant attributes. This paper describes Chi2, a simple and general algorithm that uses the 2 statistic to discretize numeric attributes repeatedly until some inconsistencies are found in the data, and achieves feature selection via discretization. The empirical results demonstrate that Chi2 i...

Space-Air-GroundIntegrated Network (SAGIN) has been becoming a promising future network construction to enable the integration of terrestrial communications, aerial networks and satellite systems, for achieving high data rate wireless access seamless coverage. Focusing on space-to-air propagation, which is requiring transmitted signal large Doppler shift resilience in dynamic circumstances, pro...