Theory

Introduction In my previous post I wrote about the cognitive architecture ACT-R, mainly putting together what I learnt by research over the topic. In this post, I would like to go more in depth about how ACT-R works, the concepts behind and try to provide my interpretation of some technical examples, regarding coding of the modeling and everything related. What really is ACT-R ACT-R is a production system theory that tries to explain human cognition by developing a model of the knowledge structures that underlie cognition. There are two types of knowledge representation in ACT-R: ...

Introduction I’ve always been fascinated about cognitive systems and all the theories about them. Unfortunately, I never had the chance to actively work on a cognitive architecture: making experiments over these technologies is difficult because it’s difficult to me even only think about some possible toyproblem to solve. So this article is more about the basics, or at least what I found interesting about the topic. ACT-R One of the most famous cognitive architecture is ACT-R: ACT-R a.k.a. “Adaptive Control of Thought—Rational” is a cognitive architecture mainly developed by John Robert Anderson at Carnegie Mellon University. If you don’t know Anderson, no worries but from now on keep in mind that he obtained a B.A. from the University of British Columbia in 1968, a Ph.D. in Psychology from Stanford in 1972 to finally become an assistant professor at Yale in 1972. This in the first 25 years of his life. This is to say: if you don’t understand anything about what you will read, it’s most probably not your fault, neither mine’s…and neither Anderson’s actually - it seems there’s a bug in Matrix. ...

Much more than a post What is the quantum theory? As said by quantumexperience official site by IBM, it’s an elegant mathematical theory able to explain the counterintuitive behavior of subatomic particles, most notably the phenomenon of entanglement. In the late twentieth century it was discovered that quantum theory applies not only to atoms and molecules, but to bits and logic operations in a computer. This realization has been bringing about a revolution in the science and technology of information processing: I decided to write some notes to better explain, from a physics-agnostic computer scientist’s point of view XD, what I understood - and it is certainly wrong - about Q until now and why I think it’s an amazing field for computer science. For skilled guys, here latex source (and here pdf pre-compiled version) that collect my personal notes about IBM Q platform, in general the quantum-computing world. I was also invited in Verona by the Quantum Research Group of the Department of Computer Science - why? don’t know, maybe the coolest guys were sick 😂 - to talk about the platform and we had a really interesting brain-storming conversation about a quantum version of the Tris game I am working on 😎 ...

A journey through the network - Layer 2 A month ago I started to wrote some posts about the network. For those who missed the previous posts, the introduction and the physycal layer. For the previous post I had to go into details about how some parts of the physical layer work but, by going forward with the layers, concepts belonging to separate historical standards - OSI and IP - will intertwine and this entails some troubles from a logical point of view. I will try, as far as possible, to keep only the basic concepts of this layer: I also remember that this layer, together with the physical layer, are - at least in part - joined together in what is called the network access layer in the TCP / IP model. As a main source I use Computer Networks and TCP/IP Illustrated. In this article, I will talk about layer 1, the data link layer in the ISO / OSI stack. Enjoy the reading! ...

Preamble Recently I became nostalgic and fascinated with stuff from the past, so I decided to create a Vagrantfile to work with FreeBSD1. Why FreeBSD? Because as a developer, I really like Docker and I started looking in the past to find its historical birth: in fact, as a concept, Docker is no so recent as you think, and I think it exists also because of the works of some other bigs from 80’, such as Poul-Henning Kamp2. Starting from its work and using a FreeBSD installation I did some experiments with jails, to understand better what they really are, how they works - how can you create what it will look like a vintage container - and why you should use them in a FreeBSD environment - at least, to learn something new. ...

A journey through the network - Layer 1 Before the Christmas holidays, I wrote an article about the network: yes. The network is that part of computer science that is no longer considered fundamental as it should, and I must admit that I learn it every day at my expense: as an old friend always says to me “the network is the concept on which everything is based, describes how the body works: after that, you can also become a gastroenterologist, but you will always need to know how the body works”. I think he’s right. As I was saying, I wrote an article about that: it’s a sort of overview and technical / historical introduction on the ISO / OSI and TCP / IP protocols. For those who missed the introduction, here the link. Despite my lack of experience, I promised myself, as far as possible, with the little time available, to retrace the various levels of the network from a theoretical point of view without going into too much detail, also trying to identify the most used commands, understand the level at which they operate and the functioning of the parameters supported by them. It took me a lot of time … but finally, the post on level one is ready. As a main source I use Computer Networks and TCP/IP Illustrated. In this article, I will talk about layer 0, the lowest in the ISO / OSI stack. Enjoy the reading! ...

A journey through the network - Introduction During the last year I understood one thing: sooner or later everyone should review network notions, so I decided to start writing articles about network fundamentals. As a main source I would use Computer Networks and TCP/IP Illustrated. In this article, I will talk about two important network architectures: the OSI reference model and the TCP/IP reference model. These two model has opposite characteristics, in particular: ...

History We can date the birth of artificial neural networks in 1958, with the introduction of Perceptron 1 by Frank Rosenblatt. It was the first algorithm created to reproduce the biological neuron. Conceptually, the easier perceptron that you might think of is made of a single neuron: when it’s exposed to a stimulus, it provides a binary response, just as would a biological neuron. This model differs greatly from the neural network involving billions of neurons in a biological brain. Shortly after his birth, the researchers showed the world the problems of Perceptron: in fact, it was quickly proved that perceptrons could not be trained to recognize many classes of input patterns. To get a more powerful network, it was necessary to take advantage of multiple level of units and create a multilayers perceptron, with more intermediates neurons used to solve linearly separable2 subproblems, whose outputs were combined together by the final level to provide a concrete response to original input problem. Even though the Perceptron was just a simple but severely limited binary classifier, it introduced a great innovation: the idea to simulate the basic computational unit of a complex biological system that exists in nature. ...

Why Java why now I recently followed a course1 on YouTube by Adib Saikali (NewCircle Instructor) about the key features introduced in Java > 8: it’s an old post regarding old stuff but…I collected some notes (mainly because I need to write down what I’m listening to to stay focused and learn new concepts) that I decided to share with you. This is to say, this post is for every one that had put aside Java for a while and is now looking for a quick overview of the key aspects - exactly like me some weeks ago - to improve his abilities in coding, taking advantage of the old (n.d.r.) features introduced a few years ago. For thus who missed the footnote before and want to jump directly to the lesson, here you can find the main source of the content of the next paragraphs. ...