Andreu Sancho Homepage

Doing a PhD involves building walls and then demolish them and build them back learning something during the process.

Since the current world-wide crisis began scientists have had very difficult times. Cuts in budgets and grants are a common difficulty that researchers have to handle in order to progress with their projects. Nevertheless, curiosity and perseverance  are major forces that can drive a scientist towards their goal even in such a harsh condition. However, there is a critical boundary that can kill the bravest researcher and this happens when the manager in charge of science in your own country; the one who has to protect you as a researcher, tells in a prestigious media that " we must now stop talking about the importance of science, and instead commit ourselves to the need for excellence in science " and " we need to change the number of researchers by maintaining and improving the quality of the contracts while reducing the quantity. "  You can find  the full article in this link . Of course the response of the scientific community has been quick, and with ...

They can solve complex, multi-dimensional optimization problems, model and predict customer behavior, process huge volumes of data extracting novel and useful information, and even beat strong chess grandmasters. However, they lack a fundamental stuff; the thing that makes us special: machines fail at understanding the world---see the Chinese room argument , by John Searle. Can we devise a computer capable of performing arts by itself? Can a computer program write a poem from scratch, with feelings and passion; the human essence? Not yet. Of course we can write a program that selects words at random following the syntactical rules of, say, the English language, but for sure it will not be as good as the average Joe at it. The brittleness of this program will be obvious to us. Now imagine we have a machine that is conscious; a machine that has the properties of a fully developed mind. Because the nature of computers is so different from our biological reality, will we be able to...

Endless meanders in rivers of silver, synthetic in nature, makes us shiver. As old mathematicians long ago gone you keep counting alone. Now that the world is at your feet your eager beat is only for an elite. Many dreams of fame ephemeral thoughts, now a shame. I have taken you in adoption without considering any other option. In our sweet loneliness we see time passing by; tireless mess.

The discipline of machine learning (ML) can be understood as a particular study of data. Data is everything , and it contains patterns and a certain degree of uncertainty. The aim of the field is to identify those and exploit them to solve complex problems. Often algorithms for obtaining such patterns are not easy to implement, involving abstract mathematical concepts and vague descriptions of the internal processes that guide the learning mechanisms. In this particularly discouraging environment there are several useful tools to help with the understanding of the ML techniques. Octave is such a tool. Octave allows the extensive use of vectorization to exploit parallelism and modeling complex algorithms in a very fourth-generation programming language fashion. I started with Octave due to Standord's ml-class course and I have to say that the experience has been very positive. In one of the exercises we had to implement a handwritten character recognizer, that is, a type of percep...

" Machine learning is the science of getting computers to act without being explicitly programmed. " This is a very good definition of what ML is. But let's see what topics are included in the course: (1) supervised learning, (2) unsupervised learning, (3) best practices in machine learning, and (4) reinforcement learning (the course syllabus and the scheduling is found here .) A quite complete course; I only miss evolutive computation, anyway I think this course is a good way to enter to this wonderful discipline. You can sign up freely here (I did and I will post the experience here.) Stanford also offers another two free online courses: introduction to artificial intelligence and introduction to data bases .

After nearly a two years' trip into the deep mysteries of LCSs one expects to comprehend the intrinsics of these family of techniques. Dozens of papers and unimaginable hours behind and I am, still, hooked with the very basics. These are the thoughts of a wannabe researcher that makes baby steps into the research world. But first let me introduce myself briefly: I have spent a reasonable amount of time and effort with XCS-alike algorithms. I implemented myself, from the very scratch, the most relevant ones, and tested them uncountable times. But I am still learning about the basics. Every single time. Recently I re-implemented the good old XCSR, and I found a lot of trouble with it. Devil is in every detail, and I get him face to face. What is one supposed to do when stuck with a technique he is supposed to be a master of (or, at least, with a certain amount of experience behind with)? I confess I was very upset with myself. Depressed, with thoughts of failure flooding i...