Machine Super Intelligence

نویسندگان

  • Shane Legg
  • Marcus Hutter
  • Jürgen Schmidhuber
  • Fernando Pedone
  • Fabio Crestani
چکیده

thinking, 6action space, 41actions, 40, 72Acton, Lord, 137Adams, S., 136Adaptive Intelligence Inc., 19agentactive, 39AIXI, 48, 82, 93, 109, 137choose own goals, 92formal, 42human, 83informal, 40optimal, 45passive, 39random, 78self-optimising, 50, 64simple, 80specialised, 79super intelligent, 82agent-environment model, 39AI winter, 125Albus, J. S., 9aliens, 135alphabet, 41Anastasi, A., 7aperiodic, 63Artificial general intelligence(AGI), 126axons, 127 backgammon, 126Bayes’ rule, 25Bayes, T., 25Bellman equation, 46Binet, A., 4, 13Bingham, W. V., 5Block, N., 16Blockhead argument, 89BlueBrain project, 132BlueGene supercomputer, 132Boring, E. G., 9brain, 128brain simulation, 130Bringsjord, S., 19Brooks, R., 136 C-Test, 20Carroll, J. B., 4Cattell, R. B., 4, 10Chaitin, G., 20, 105checkers, 127chess, 2, 40, 126Chinese room argument, 89coenumerable function, 33Colvin, 5communicating class, 63competitive games, 19complexityKolmogorov, 20, 31, 34, 98Levin, 20, 93of environments, 76of prediction, 102time, 21, 104computable binary sequence, 97computable function, 33consciousness, 90, 127control theory, 41, 73cortex, 131creativity, 90

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

TDR System - A Multi-Level Slow Intelligence System for Personal Health Care

This paper describes the design of an experimental multi-level slow intelligence system for health care, called the TDR system, consisting of interacting super-components each with different computation cycles specified by an abstract machine model. The TDR system has three major super-components: Tian (Heaven), Di (Earth) and Ren (Human), which are the essential ingredients of a human-centric ...

متن کامل

Chess Isn't Tough Enough: Better Games for Mind-Machine Competition

That Strong AI is still alive may have a lot to do with its avoidancc of true tests. When Kasparov sits down to face the meanest chcssbot in town: hc has the deck stacked against him: his play may involve super-computatiom but we know that perfect chess can be played by a finite-state automaton: so Kasparov loses if the engineers arc suificiently clever ... [(Bringsjord: 1997b), p. 9; paraphras...

متن کامل

The universal evolutionary computer based on super-recursive algorithms of evolvability

The bacteria are great champions of evolutionary success. They can survive in the boiling water full of sulfer and salt, in the ice, the high exposures to desiccation and dehydration, under the very high pressure in the sea depths, in the cooling water of nuclear reactors, they have become resistant to the entire arsenal of human made antibiotics and they have even survived experimentaly achiev...

متن کامل

Social Network Models for the TDR System

The TDR system is an experimental multi-level slow intelligence system for personal health care. The TDR system can be used by a single user or a group of users who will interact to understand, maintain and improve each other’s state of health. In this paper, we simulate social networks by applying the Abstract Machine model. Two social network models are described: the Circulated Model and the...

متن کامل

Beating the World's Best at Super Smash Bros. with Deep Reinforcement Learning

There has been a recent explosion in the capabilities of game-playing artificial intelligence. Many classes of RL tasks, from Atari games to motor control to board games, are now solvable by fairly generic algorithms, based on deep learning, that learn to play from experience with minimal knowledge of the specific domain of interest. In this work, we will investigate the performance of these me...

متن کامل

Human-computer super-intelligence

The concept of human intelligence includes several types of intellectual activity – rational thinking, emotional thinking, unconscious thinking, intuitive thinking, and automatic control of the biological systems. Rational thinking refers to the cognition of the phenomena and laws of the animate and the inanimate nature. It is realized through the processing of mostly visual images and is there...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2011