Google
 


Records 1 to 10 of 12

Artificial intelligence

2007-06-09 15:05:54

Artificial Life.Traditionally Artificial intelligence has used a top down approach while alife generally works from the bottom up. Very related to weak alife, yet sometimes not considered as 'real artificial life', many optimization algorithms have been crafted which borrow from or closely mirror alife techniques. The primary difference lies in explicitly defining the fitness of an agent by its ability to solve a problem, instead of its ability to find food, reproduce, or avoid death.

Evolutionary art uses techniques and methods from artificial life to create new forms of art. Evolutionary music uses similar techniques, but applied to music instead of visual art.
 Poste by dir.xml-rss.com

Techniques

2007-06-09 15:05:03

Artificial Life,

  • Cellular automata are often used, especially in the history of artificial life, due to the ease of scalability and parallelization. Alife and cellular automata share a closely tied history.
  • Neural networks are sometimes used to model the brain of agents. Although traditionally more of an artificial intelligence technique, neural nets can be important for simulating population dynamics of higher organisms that can learn. The symbiosis between learning and evolution is central to theories about the development of instincts in higher organisms, for instance, as in the Baldwin effect.

 Poste by dir.xml-rss.com

Fiction

2007-06-09 15:03:17

Artificial Intelligence,

Cover art for I, Robot by Isaac Asimov.

Cover art for I, Robot by Isaac Asimov. In science fiction AI — almost always strong AI — is commonly portrayed as an upcoming power trying to overthrow human authority as in HAL 9000, Skynet, Colossus: The Forbin Project, and The Matrix, or as service humanoids like C-3PO, Marvin, KITT from Knight Rider, the Bicentennial Man, the Mechas in A.I. and Sonny in I, Robot. A notable exception is Mike in Robert A. Heinlein's The Moon Is a Harsh Mistress: a supercomputer that becomes aware and aids humans in a local revolution to overthrow the authority of other humans. A careful reading of Arthur C. Clarke's version of 2001 suggests that the HAL 9000 found himself/itself in a similar position of divided loyalties. On one hand, HAL needed to take care of the astronauts, on the other the humans who created HAL entrusted him with a secret to be withheld from the astronauts. The inevitability of world domination by out-of-control AI is also argued by some writers like Kevin Warwick. In works such as the Japanese manga Ghost in the Shell, the existence of intelligent machines questions the definition of life as organisms rather than a broader category of autonomous entities, establishing a notional concept of systemic intelligence. See list of fictional computers and list of fictional robots and androids. Author Frank Herbert explored the idea of a time when mankind might ban clever machines entirely. His Dune series makes mention of a rebellion called the Butlerian Jihad in which mankind defeats the smart machines of the future and then imposes a death penalty against any who would again create thinking machines. Often quoted from the fictional Orange Catholic Bible, "Thou shalt not make a machine in the likeness of a human mind." A similar idea is also explored in the re-imagined Battlestar Galactica, where artificial intelligence research is illegal after the Cylons, a species of intelligent machines created by man, had rebelled against their masters and tried to destroy them. The character Dr. Gaius Baltar is known for his controversial view that the ban on research in this area is outmoded and should be lifted. Artificial intelligence plays a major role in How to Make a Monster, where the fictional character Sol uses his sophisticated AI for the game's monster, which comes to life after the lightning strike. Golem XIV is an example of highly advanced supercomputer in Stanis?aw Lem's science-fiction novel Golem XIV. Golem XIV was a military artificial intelligence computer, which was originally invented to lead wars and to win them. Golem stops cooperating with humans on military level, because he considered wars and violence as illogical. His self-developing artificial intelligence refused to execute his primary task. Machine becomes a philosopher greater then any other born on Earth. Golem's intelligence advanced to a lot higher level then human intelligence which lead to conversation and information exchange problems.
 Poste by dir.xml-rss.com

Computer Science

2007-06-09 15:02:51

Artificial Intelligence, Notable examples include the languages LISP and Prolog, which were invented for AI research but are now used for non-AI tasks. Hacker culture first sprang from AI laboratories, in particular the MIT AI Lab, home at various times to such luminaries as John McCarthy, Marvin Minsky, Seymour Papert (who developed Logo there) and Terry Winograd (who abandoned AI after developing SHRDLU). Neuro-psychology Techniques and technologies in AI which have been directly derived from neuroscience include neural networks, Hebbian learning and the relatively new field of Hierarchical Temporal Memory which simulates the architecture of the neocortex.
 Poste by dir.xml-rss.com

Research challenges

2007-06-09 15:01:56

Artificial Intelligence,

Stanley, the winner of the 2005 DARPA Grand Challenge

Stanley, the winner of the 2005 DARPA Grand Challenge

A legged league game from RoboCup 2004 in Lisbon, Portugal.

A legged league game from RoboCup 2004 in Lisbon, Portugal. The DARPA Grand Challenge was a race for a $2 million prize where cars had to drive themselves across several hundred miles of challenging desert terrain without any communication with humans, using GPS, computers and a sophisticated array of sensors. In 2005 the winning vehicles completed all 132 miles of the course in just under 7 hours. This was the first in a series of challenges aimed at a congressional mandate stating that by 2015 one-third of the operational ground combat vehicles of the US Armed Forces should be unmanned [[4]]. For November 2007, DARPA introduced the DARPA Urban Challenge. The course will involve a 60-mile urban area course. Darpa has secured the prize money for the challenge as $2 million for first place, $1 million for second and $500 thousand for third. A popular challenge amongst AI research groups is the RoboCup and FIRA annual international robot soccer competitions. Hiroaki Kitano has formulated the International RoboCup Federation challenge: 'In 2050 a team of fully autonomous humanoid robot soccer players shall win the soccer game, comply with the official rule of the FIFA, against the winner of the most recent World Cup' [[5]]. In the post-dot com boom era, some search engine websites use a simple form of AI to provide answers to questions entered by the visitor. Questions such as "What is the tallest building?" can be entered into the search engine's input form and a list of answers will be returned.

 Poste by dir.xml-rss.com

AI programming languages and styles

2007-06-09 15:01:29

Artificial Intelligence,AI research has led to many advances in programming languages including the first list processing language by Allen Newell et al., Lisp dialects, Planner, Actors, the Scientific Community Metaphor, production systems, and rule-based languages. GOFAI TEST research is often done in programming languages such as Prolog or Lisp. Matlab and Lush (a numerical dialect of Lisp) include many specialist probabilistic libraries for Bayesian systems. AI research often emphasise rapid development and prototyping, using such interpreted languages to empower rapid command-line testing and experimentation. Real-time systems are however likely to require dedicated optimized software. Many expert systems are organized collections of if-then such statements, called productions. These can include stocastic elements, producing intrinsic variation, or rely on variation produced in response to a dynamic environment.
 Poste by dir.xml-rss.com

Computational intelligence

2007-06-09 15:01:08

Artificial Intelligence,Computational intelligence involves iterative development or learning (e.g. parameter tuning e.g. in connectionist systems). Learning is based on empirical data and is associated with non-symbolic AI, scruffy AI and soft computing. Subjects in computational intelligence as defined by IEEE Computational Intelligence Society mainly include:

With hybrid intelligent systems attempts are made to combine these two groups. Expert inference rules can be generated through neural network or production rules from statistical learning such as in ACT-R. It is thought that the human brain uses multiple techniques to both formulate and cross-check results. Thus, systems integration is seen as promising and perhaps necessary for true AI.
 Poste by dir.xml-rss.com

Conventional AI

2007-06-09 15:00:43

Artificial Intelligence,Conventional AI mostly involves methods now classified as machine learning, characterized by formalism and statistical analysis. This is also known as symbolic AI, logical AI, neat AI and Good Old Fashioned Artificial Intelligence (GOFAI). (Also see semantics.) Methods include:

  • Expert systems: apply reasoning capabilities to reach a conclusion. An expert system can process large amounts of known information and provide conclusions based on them.
  • Case based reasoning: stores a set of problems and answers in an organized data structure called cases. A Case Based Reasoning system upon being presented with a problem finds a case in its knowledge base that is most closely related to the new problem and presents its solutions as an output with suitable modifications.[4]
  • Bayesian networks
  • Behavior based AI: a modular method building AI systems by hand.

 Poste by dir.xml-rss.com

Classifiers

2007-06-09 15:00:22

Artificial Intelligence,Classifiers are functions that can be tuned according to examples, making them very attractive for use in AI. These examples are known as observations or patterns. In supervised learning, each pattern belongs to a certain predefined class. A class can be seen as a decision that has to be made. All the observations combined with their class labels are known as a data set. When a new observation is received, the observation is classified based on previous experience. A classifier can be trained in various ways, there are mainly statistical and machine learning approaches. A wide range of classifiers are available, each with its strengths and weaknesses. Classifier performance depends greatly on the characteristics of the data to be classified. There is no single classifier that works best on all given problems; this is also referred to as the "no free lunch" theorem. Various empirical tests have been performed to compare classifier performance and to find the characteristics of data that determine classifier performance. Determining a suitable classifier for a given problem is however still more an art than science. The most widely used classifiers are the neural network, support vector machine, k-nearest neighbor algorithm, Gaussian mixture model, naive Bayes classifier, and decision tree.
 Poste by dir.xml-rss.com

Mechanisms

2007-06-09 14:59:57

Artificial Intelligence, Generally speaking AI systems are built around automated inference engines. Based on certain conditions ("if") the system infers certain consequences ("then"). AI applications are generally divided into two types, in terms of consequences: classifiers ("if shiny then diamond") and controllers ("if shiny then pick up"). Controllers do however also classify conditions before inferring actions and therefore classification form a central part of most AI systems. Classifiers make use of pattern recognition for condition matching. In many cases this does not imply absolute, but rather the closest match. Techniques to achieve this divides roughly into two schools of thought: Conventional AI and Computational intelligence (CI). Convential AI research focusses on attempts to mimic human intelligence through symbol manipulation and symbolically structured knowledge bases. This approach limits the situations to which conventional AI can be applied. Lotfi Zadeh stated that "we are also in possession of computational tools which are far more effective in the conception and design of intelligent systems that the predicate-logic-based methods, which form the core of traditional AI", techniques which has become known as soft computing. These often biologically inspired methods, stand in contrast to conventional AI and compensate for the shortcomings of symbolicism [2]. These two methodologies has also been labelled as neats vs. scruffies, with neats emphasising the use of logic and formal representation of knowledge while scruffies take an application-oriented heuristic bottom-up approach [3].
 Poste by dir.xml-rss.com

<< previous :: 1 | 2 :: next >>