The processing of rough machining and semi-finishing of revolving body stone is studied, according to the particularity of stone machining. Based on the study of processing, the system of computer aided programming an...
详细信息
A generalization of an artificial neuron is introduced in this paper. Called the queron(1), this abstraction is the basic computational node of Queral Networks (QN). QNs are introduced as a parallel architecture expec...
详细信息
ISBN:
(纸本)9780769543796
A generalization of an artificial neuron is introduced in this paper. Called the queron(1), this abstraction is the basic computational node of Queral Networks (QN). QNs are introduced as a parallel architecture expected to be an improvement upon Artificial Neural Networks (ANN). The fundamental properties of QNs are presented here: reusability, complexity management and human-readability. It is expected that this proposed architecture will allow the engineering of large, highly parallel computer systems with the computational benefits of ANNs while overcoming the challenge of developing ANNs. A brief case study is given to illustrate the QN concept.
To be able to represent FSM as a binary chromosome several restrictions are required. This paper analyzes and discuses the differences between classical FSMs and semantic FSA with evolutionary algorithms. To overcome ...
详细信息
ISBN:
(纸本)9789881925145
To be able to represent FSM as a binary chromosome several restrictions are required. This paper analyzes and discuses the differences between classical FSMs and semantic FSA with evolutionary algorithms. To overcome the limitation of classical Mealy and Moore machine, we use semantic FSA. It is presented that when the evolutionary process is based on the behavior of small building function, then better evolutionary algorithm is developed. In addition, the evolutionary process is highly enhanced by using fitness inheritance technique to constrain the depth of genetic programming tree to overcome its bloat problem.
When a robot is brought into a new environment, it has a very limited knowledge of what surrounds it and what it can do. One way to build up that knowledge is through exploration but it is a slow process. programming ...
详细信息
ISBN:
(纸本)9781612849904
When a robot is brought into a new environment, it has a very limited knowledge of what surrounds it and what it can do. One way to build up that knowledge is through exploration but it is a slow process. programming by demonstration is an efficient way to learn new things from interaction. A robot can imitate gestures it was shown through passive manipulation. Depending on the representation of the task, the robot may also be able to plan its actions and even adapt its representation when further interactions change its knowledge about the task to be done. In this paper we present a bio-inspired neural network used in a robot to learn arm gestures demonstrated through passive manipulation. It also allows the robot to plan arm movements according to activated goals. The model is applied to learning a pick-and-place task. The robot learns how to pick up objects at a specific location and drop them in two different boxes depending on their color. As our system is continuously learning, the behavior of the robot can always be adapted by the human interacting with it. This ability is demonstrated by teaching the robot to switch the goals for both types of objects.
In this paper, we present PATUS, a code generation and auto-tuning framework for stencil computations targeted at multi- and manycore processors, such as multicore CPUs and graphics processing units. PATUS, which stan...
详细信息
Model Driven Engineering (MDE) focuses on the automatic generation of code from system models, referred to as the Model-to-Code (M2C) transformation. Currently, M2C transformation relies on the transformation rules, m...
详细信息
In this paper, three asynchronous FIFO design styles, linear, square, and cubic, are investigated based on the Balsa synthesis system. These styles are designed with the key difference being the path by which data tra...
详细信息
Each refactoring implementation must check a number of conditions to guarantee behavior preservation. However, specifying and checking them are difficult. Sometimes refactoring tool developers may define overly strong...
详细信息
This paper describes a first attempt at automatically inducing object-oriented programs. The system implemented for this purpose uses a rule-based expert system to firstly derive an object-oriented design (OOD) for th...
详细信息
ISBN:
(纸本)9781595937759
This paper describes a first attempt at automatically inducing object-oriented programs. The system implemented for this purpose uses a rule-based expert system to firstly derive an object-oriented design (OOD) for the problem instance. Input to the system is a description of the entities in the given domain and their corresponding behaviors. The induced OOD is then input to a genetic programming (GP) system to automatically generate the programs representing the classes. Each class program is evolved in an internal representation language. In order to test the system a translator was developed to convert the evolved class programs to Java. The hybrid system was used to induce object-oriented programs typical of a first course on object-oriented programming (OOP). The paper presents a comparison of the evolved programs to that written by programmers. Copyright 2007 ACM.
Genetic programming (GP) is well-known as an evolutionary method for automatic programming. GP can optimize tree-structural programs. Cartesian GP (CGP) is one of the extensions of GP, which generates the graph struct...
详细信息
Genetic programming (GP) is well-known as an evolutionary method for automatic programming. GP can optimize tree-structural programs. Cartesian GP (CGP) is one of the extensions of GP, which generates the graph structural programs. By using the graph structure, the solutions can be represented by more compact programs. Therefore, CGP is widely applied to the various problems. As a different approach from the evolution, there is the Ant Colony Optimization (ACO), which is an optimization method for combinatorial optimization problems based on the cooperative behavior of ants. By using pheromone communication, the promising solution space can be searched intensively. In this paper, we propose a new automatic programming method, which combines CGP and ACO. In this method, ants generate programs by moving in the node-network used in CGP. We call this method, Cartesian Ant programming (CAP). We examined the effectiveness of CAP by comparing with CGP on the search performance in a symbolic regression and a classification problem.
暂无评论