scholarly journals From Grammar Inference to Semantic Inference—An Evolutionary Approach

Mathematics ◽  
2020 ◽  
Vol 8 (5) ◽  
pp. 816 ◽  
Author(s):  
Željko Kovačević ◽  
Marjan Mernik ◽  
Miha Ravber ◽  
Matej Črepinšek
Keyword(s):  
Evolutionary Computation ◽  
Research Work ◽  
Search Space ◽  
Evolutionary Approach ◽  
Main Task ◽  
Grammatical Structure ◽  
Grammar Inference ◽  
Semantic Inference ◽  
Language Semantics ◽  
First Results

This paper describes a research work on Semantic Inference, which can be regarded as an extension of Grammar Inference. The main task of Grammar Inference is to induce a grammatical structure from a set of positive samples (programs), which can sometimes also be accompanied by a set of negative samples. Successfully applying Grammar Inference can result only in identifying the correct syntax of a language. With the Semantic Inference a further step is realised, namely, towards inducing language semantics. When syntax and semantics can be inferred, a complete compiler/interpreter can be generated solely from samples. In this work Evolutionary Computation was employed to explore and exploit the enormous search space that appears in Semantic Inference. For the purpose of this research work the tool LISA.SI has been developed on the top of the compiler/interpreter generator tool LISA. The first results are encouraging, since we were able to infer the semantics only from samples and their associated meanings for several simple languages, including the Robot language.

A Comprehensive Survey of Neural Architecture Search

2021 ◽  
Vol 54 (4) ◽  
pp. 1-34
Author(s):  
Pengzhen Ren ◽  
Yun Xiao ◽  
Xiaojun Chang ◽  
Po-yao Huang ◽  
Zhihui Li ◽  
...  
Keyword(s):  
Research Work ◽  
Search Space ◽  
Feature Representation ◽  
Future Research ◽  
Related Research ◽  
Neural Architecture ◽  
Comprehensive Survey ◽  
Future Research Directions ◽  
Intuitive Idea ◽  
New Perspective

Deep learning has made substantial breakthroughs in many fields due to its powerful automatic representation capabilities. It has been proven that neural architecture design is crucial to the feature representation of data and the final performance. However, the design of the neural architecture heavily relies on the researchers’ prior knowledge and experience. And due to the limitations of humans’ inherent knowledge, it is difficult for people to jump out of their original thinking paradigm and design an optimal model. Therefore, an intuitive idea would be to reduce human intervention as much as possible and let the algorithm automatically design the neural architecture. Neural Architecture Search ( NAS ) is just such a revolutionary algorithm, and the related research work is complicated and rich. Therefore, a comprehensive and systematic survey on the NAS is essential. Previously related surveys have begun to classify existing work mainly based on the key components of NAS: search space, search strategy, and evaluation strategy. While this classification method is more intuitive, it is difficult for readers to grasp the challenges and the landmark work involved. Therefore, in this survey, we provide a new perspective: beginning with an overview of the characteristics of the earliest NAS algorithms, summarizing the problems in these early NAS algorithms, and then providing solutions for subsequent related research work. In addition, we conduct a detailed and comprehensive analysis, comparison, and summary of these works. Finally, we provide some possible future research directions.

Users' Fuzzy Cognition Knowledge Learning in Interactive Evolutionary Computation and its Application

2011 ◽  
Vol 204-210 ◽  
pp. 245-250
Author(s):  
Guo Sheng Hao ◽  
Xiang Jun Zhao ◽  
Yong Qing Huang
Keyword(s):  
Evolutionary Computation ◽  
Search Space ◽  
Interactive Evolutionary Computation ◽  
Sense Unit ◽  
Knowledge Learning

user in interactive evolutionary computation (IEC) has the characteristic of fuzzy cognition. Based on this, a method to learn users’ fuzzy cognition knowledge is given. The method includes the fuzzy expression of the basic elements of IEC such as search space, population, gene sense unit and so on. Then a method to increase the performance of IEC based on the knowledge of users’ fuzzy cognition is given. The above results enrich the researches of IEC users' cognition.

scholarly journals FRATs: Searching for fast radio transient in real-time with LOFAR

2012 ◽  
Vol 8 (S291) ◽  
pp. 233-233
Author(s):  
Heino Falcke ◽  
Keyword(s):  
Time Scales ◽  
Search Space ◽  
Large Field ◽  
New Radio ◽  
Wide Range ◽  
Imaging Observation ◽  
Previous Decade ◽  
First Results ◽  
Single Radio ◽  
Radio Transients

AbstractLOFAR is an innovative new radio interferometer operating at low radio frequencies from 10 to 270 MHz. It combines a large field-of-view, high fractional bandwidth, rapid response, and a wide range of baselines from tens of meters to thousand kilometers. Its use of phased-array technology and its digital nature make LOFAR an extremely versatile instrument to search for transient radio phenomena on all time scales. Here we discuss in particular the search for fast radio transients (FRATs) at sub-second time scales. In fact, at these time scales the radio sky is rather dynamic due to coherent emission processes. Objects like pulsars, flaring stars, or planets like Jupiter are able to produce bright short flares. For pulsars, most previous detection strategies made use of the rotation of pulsars to detect them, using Fourier techniques, but it is also possible to detect pulsars and other objects through their single pulses. Such surveys have, e.g., led in the previous decade to the detection of Rapid Radio Transients (RRATS), but the unprobed search space is still rather large. LOFAR is now conducting a rather unique survey over the entire northern sky, searching for bright dispersed single radio pulses. This FRATs survey makes use of the LOFAR transient buffer boards (TBBs), which had initially been used to detect nanosecond radio pulses from cosmic rays. The TBBs store the radio data from each single receiver element of LOFAR and allow one to look back in time. A trigger system that runs parallel to normal imaging observation allows one to detect single pulses in an incoherent beam of all LOFAR stations, covering several tens to hundred square degrees at once. Once triggered, the data can be used to localize the pulse and to discriminate cosmic sources from terrestrial interference through 3D localization. The system has been successfully tested with known pulsars and first results of the ongoing survey will be presented.

Hydrostatic Collapse Pressure and Radial Collapse Force Comparisons for Ultra-Deepwater Pipelines

2014 ◽  
Author(s):  
Marco A. P. Rosas ◽  
Ana Paula F. Souza ◽  
Marcos V. Rodrigues ◽  
Danilo Machado L. da Silva
Keyword(s):  
Numerical Models ◽  
Research Work ◽  
Compressive Force ◽  
Quadratic Function ◽  
Radial Force ◽  
Small Scale ◽  
Collapse Pressure ◽  
First Results ◽  
Specimen Test ◽  
The Relationship

In this paper the behavior and the relationship between hydrostatic collapse pressure and diametrically opposed radial compressive force for pipelines were analyzed. This study presents an introduction of a research work aimed to assess the pipeline collapse pressure based on the radial collapse force. Initially the hydrostatic collapse pressure is analyzed, for pipes with different diameter to wall thickness ratio (D/t) and ovalities, using classical assessment (DNV method) and numerical models (FE). Then, the compressive radial force is also analyzed using numerical models validated by a small-scale ring specimen test. After that, the relationship between hydrostatic collapse pressure and compressive radial force is discussed. These first results show that the radial force is a quadratic function of the collapse pressure.

scholarly journals Digital Governance of Moroccan School Establishments

2021 ◽  
pp. 348-355
Author(s):  
Abderrazak Mazouak ◽  
Malika Tridane ◽  
Said Belaaouad
Keyword(s):  
Research Work ◽  
Project Planning ◽  
Pedagogical Practices ◽  
Third Phase ◽  
First Results ◽  
On Line ◽  
The One ◽  
Traditional Paradigm ◽  
And Control ◽  
Relationship Of

Digital technologies have come to shake up the traditional paradigm of learning, and to change the existing relationship of "know-teaching" to put in place a key concept of the time is "to accompany through digital tools Our intervention is part of a technical-pedagogical approach and will focus on an action research work in which we will try:First, to present on line an accessible digital device that facilitates and organizes project planning and provides means to govern and control the quality of administrative acts.Next, We will show the first results of the experimentation of this tool in our context of research represented by 355 directors of the secondary schools of the provincial delegation of Taza. Morocco, pointing out all the constraints and limitations that hampered its implementation.Finally, we confirm that the use of this device by our sampling has caused a triple effect on their pedagogical practices: the professionalization of strategic planning on the one hand, and the governance of resources and the rationalization of pedagogical decisions on the other hand and immediate evaluation and regulation in the third phase.

Efficient Evolution of Modular Robot Control via Genetic Programming

2013 ◽  
pp. 59-85
Author(s):  
Tüze Kuyucu ◽  
Ivan Tanev ◽  
Katsunori Shimohara
Keyword(s):  
Multiobjective Optimization ◽  
Genetic Programming ◽  
Evolutionary Computation ◽  
Fast Moving ◽  
Search Space ◽  
Multiple Objectives ◽  
Experimental Results ◽  
Robotic Systems ◽  
Linear Fashion ◽  
Fast Evolution

In Genetic Programming (GP), most often the search space grows in a greater than linear fashion as the number of tasks required to be accomplished increases. This is a cause for one of the greatest problems in Evolutionary Computation (EC): scalability. The aim of the work presented here is to facilitate the evolution of control systems for complex robotic systems. The authors use a combination of mechanisms specifically designed to facilitate the fast evolution of systems with multiple objectives. These mechanisms are: a genetic transposition inspired seeding, a strongly-typed crossover, and a multiobjective optimization. The authors demonstrate that, when used together, these mechanisms not only improve the performance of GP but also the reliability of the final designs. They investigate the effect of the aforementioned mechanisms on the efficiency of GP employed for the coevolution of locomotion gaits and sensing of a simulated snake-like robot (Snakebot). Experimental results show that the mechanisms set forth contribute to significant increase in the efficiency of the evolution of fast moving and sensing Snakebots as well as the robustness of the final designs.

Genetic Algorithms and Multimodal Search

2011 ◽  
pp. 231-249
Author(s):  
Marcos Gestal ◽  
José Manuel Vázquez Naya ◽  
Norberto Ezquerra
Keyword(s):  
Genetic Algorithms ◽  
Evolutionary Computation ◽  
Unique Solution ◽  
Real World ◽  
Multiple Solutions ◽  
Global Solutions ◽  
Search Space ◽  
The Real ◽  
Local Solutions ◽  
Multimodal Problems

Traditionally, the Evolutionary Computation (EC) techniques, and more specifically the Genetic Algorithms (GAs), have proved to be efficient when solving various problems; however, as a possible lack, the GAs tend to provide a unique solution for the problem on which they are applied. Some non global solutions discarded during the search of the best one could be acceptable under certain circumstances. Most of the problems at the real world involve a search space with one or more global solutions and multiple local solutions; this means that they are multimodal problems and therefore, if it is desired to obtain multiple solutions by using GAs, it would be necessary to modify their classic functioning outline for adapting them correctly to the multimodality of such problems. The present chapter tries to establish, firstly, the characterisation of the multimodal problems will be attempted. A global view of some of the several approaches proposed for adapting the classic functioning of the GAs to the search of mu ltiple solutions will be also offered. Lastly, the contributions of the authors and a brief description of several practical cases of their performance at the real world will be also showed.

Object-Oriented Method of Constructing Electric Power System Domain Ontology Based on Protégé

2014 ◽  
Vol 997 ◽  
pp. 827-830
Author(s):  
Jian Xin Li ◽  
Gang Ke
Keyword(s):  
Power System ◽  
Semantic Annotation ◽  
Public Information ◽  
Object Oriented ◽  
Domain Ontology ◽  
Electric Power System ◽  
Main Task ◽  
Semantic Inference ◽  
Semantic Data ◽  
Ontology Tree

This paper presents a method for domain ontology of constructing power system based on Protégé . This paper describes how to package Interoperability Portlet into semantic Portlet, then create semantic data association between ontology-based semantic Portlet and using semantic inference rules to realize Portlet interoperability. The main task of this paper is to construct and deploy (service release) ontology, find out the concept of the power of public information model CIM about our project, create an XML format file with tools such as Protégé . This paper will elaborate on the use of object-oriented constructed method for constructing the ontology. The construction of the ontology tree provides the foundation of Web services’ semantic annotation.

At the Crossroads of Evolutionary Computation and Music: Self-Programming Synthesizers, Swarm Orchestras and the Origins of Melody

2004 ◽  
Vol 12 (2) ◽  
pp. 137-158 ◽  
Author(s):  
Eduardo Reck Miranda
Keyword(s):  
Genetic Algorithms ◽  
Cellular Automata ◽  
Evolutionary Computation ◽  
Research Work ◽  
Music Technology ◽  
Sound Synthesis ◽  
Engineering Applications ◽  
Ongoing Research ◽  
Musical Compositions

This paper introduces three approaches to using Evolutionary Computation (EC) in Music (namely, engineering, creative and musicological approaches) and discusses examples of representative systems that have been developed within the last decade, with emphasis on more recent and innovative works. We begin by reviewing engineering applications of EC in Music Technology such as Genetic Algorithms and Cellular Automata sound synthesis, followed by an introduction to applications where EC has been used to generate musical compositions. Next, we introduce ongoing research into EC models to study the origins of music and detail our own research work on modelling the evolution of melody.

Sign in / Sign up

Export Citation Format

Share Document