Assistant Professor
University of Huelva, Engineering School
Jose Carpio joined the University of Huelva in the fall of 2004, having previously work at the Granada University for two years as a predoctoral researcher. He teaches a wide variety of Computer Science courses including cloud computing, declarative programming, artificial intelligence and knowledge representation. He particularly enjoys with aspects related to declarative programming, artificial intelligent, cloud computing and big data.
University of Huelva, Engineering School
Ph.D. Computer Science
University of Granada, Spain
Bachelor of Computer Science
University of Granda, Spain
I would like to highlight the work experience from the curriculum content as Director of the IT Department of the company Novarsis Europa. This work experience in the private company has been fundamental for my later work in college. In teaching I would like to highlight the fourteen years of experience of teaching in the area of Computer Science and Artificial Intelligence, in a young University that has allowed me to develop a methodology of constant innovation teacher who has given as fruit the realization of a doctoral thesis in a little field usual in my environment such as Computational Intelligence and Education. This path researcher arose from a research vocation taken to the field of teaching. The thesis is born as a result of the exploration of different paths in the field of Artificial Intelligence, Social Networks and Data Mining, as well as a search for motivating elements that enhance the qualities of our students. Fruit of this search I have participated in 14 R + D + I projects funded in competitive calls, I have participated in the elaboration of 9 scientific publications and 15 works for congresses. During this same period I have made three stays in one of the reference centers European level in the area of Computer Science as it is the Research Center in Information and Communication Technologies of the University of Granada (CITIC-UGR). My scientific development has been marked by the commitment to the "Grupo Geneura" of the University of Granada that opened the door to the world of research and the search for new lines of research with colleagues from the University of Huelva much younger but with a human team of great value.
The material presented here aims to guide the student in the study of the Logical Programming and Functional Programming, both paradigms included in the Declarative Programming. This material has an eminently practical approach. We have minimized the theoretical concepts, including only the elements that we consider essential to understand that what declarative programming means. We have included the basic theoretical knowledge so that the student can begin to program declaratively from the first session. The material is divided into fourteen theoretical sessions and nine practical sessions with an approximate duration of one hour and a half per session. The theoretical sessions include exercises that serve to reinforce the theoretical concepts. In the practical sessions a series of exercises is proposed that the student must program using the computer and the compiler or interpreter of Prolog or Haskell according to the case.
Limitations of formal learning (e.g., one‐way communication, rigid methodology, results‐oriented approach) can significantly influence the motivation and expectation of students, thus resulting in an academic progress reduction. In order to make learning processes more playful and motivating, this paper presents a new educational experience developed by two groups of Computer Science students at the University of Huelva (Spain). As a result, an authentic real experience was incorporated into the classical teaching of Artificial Intelligence courses where classroom sessions were changed during some days for an international online competition. A comprehensive study considering the competition ranking, the students' opinion and their academic progress was analysed to assess the followed methodology. We found out that the educational experience improved the students' motivation, thereby enhancing their academic performance and personal skills as a result of learning through play. Moreover, additional teaching goals (e.g., learning new programming languages or increasing exam attendance) were obtained because of the positive motivation experienced by the competition. As a conclusion, this paradigm of real‐life experience – not otherwise provided by traditional practical lessons – allowed us to ascertain that the process is more important than the outcome, which could be adapted to different teaching scenarios within an institution.
This paper presents an educational experience developed in the fourth year of Computer Science degree at Huelva University (Spain). To make Artificial Intelligent (AI) learning processes more captivating, a new educational project was incorporated into classical teaching of Artificial Intelligence and Knowledge Engineering subject. In this paper, we present the experience fulfilled with a group of college students. Here it is related how they changed for some days their classroom lessons for the robotic competition arena. With this project we have extended regular classroom lessons with additional work that could be useful and cannot be provided by traditional practical lessons, the real life experience. As a real example about how the work was accomplished we describe the mechanical construction of the mobile robots as well as the software development process.
Limitations of formal learning (e.g., one‐way communication, rigid methodology, results‐oriented approach) can significantly influence the motivation and expectation of students, thus resulting in an academic progress reduction. In order to make learning processes more playful and motivating, this paper presents a new educational experience developed by two groups of Computer Science students at the University of Huelva (Spain). As a result, an authentic real experience was incorporated into the classical teaching of Artificial Intelligence courses where classroom sessions were changed during some days for an international online competition. A comprehensive study considering the competition ranking, the students' opinion and their academic progress was analysed to assess the followed methodology. We found out that the educational experience improved the students' motivation, thereby enhancing their academic performance and personal skills as a result of learning through play. Moreover, additional teaching goals (e.g., learning new programming languages or increasing exam attendance) were obtained because of the positive motivation experienced by the competition. As a conclusion, this paradigm of real‐life experience – not otherwise provided by traditional practical lessons – allowed us to ascertain that the process is more important than the outcome, which could be adapted to different teaching scenarios within an institution.
The design of fuzzy logic systems (FLS) generally involves determining the structure of the rules and the parameters of the membership functions. In this paper we present a methodology based on evolutionary computation for simultaneously designing membership functions and appropriate rule sets. This property makes it different from many techniques that address these goals separately with the result of suboptimal solutions because the design elements are mutually dependent. We also apply a new approach in which the evolutionary algorithm is applied directly to a FLS data structure instead of a binary or other codification. Results on function approximation show improvements over other incremental and analytical methods.
This paper proposes a new version of a method (G-Prop, genetic backpropagation) that attempts to solve the problem of finding appropriate initial weights and learning parameters for a single hidden layer Multilayer Perceptron (MLP) by combining an evolutionary algorithm (EA) and backpropagation (BP). The EA selects the MLP initial weights, the learning rate and changes the number of neurons in the hidden layer through the application of specific genetic operators, one of which is BP training. The EA works on the initial weights and structure of the MLP, which is then trained using QuickProp; thus G-Prop combines the advantages of the global search performed by the EA over the MLP parameter space and the local search of the BP algorithm. The application of the G-Prop algorithm to several real-world and benchmark problems shows that MLPs evolved using G-Prop are smaller and achieve a higher level of generalization than other perceptron training algorithms, such as QuickPropagation or RPROP, and other evolutive algorithms. It also shows some improvement over previous versions of the algorithm.
Computer Science Engineer’s Degree
Computer Science Engineer’s Degree
Computer Science Master’s Degree
Computer Science Master’s Degree
Diploma in Computer Management and Diploma in Computer Systems Technology
Diploma in Computer Management and Diploma in Computer Systems Technology
Computer Science Engineer’s Degree
Diploma in Computer Management
Computer Science Engineer’s Degree
I would be happy to talk to you if you need my assistance.
You can find me at my office located at University of Huelva Engineering School, office number 145, Campus del Carmen, 21007 Huelva.
I am at my office thursday and wednesday from 9:30 until 12:30 am, but you may consider to send and email to fix an appointment.