RSS

stuhlmueller + ai   128

2nd International Conference on Algorithmic Decision Theory
"[This conference] will involve researchers from such disparate fields as decision theory, discrete mathematics, theoretical computer science, economics, and artificial intelligence, aiming to improve decision support in the presence of massive data bases, partial and/or uncertain information, and distributed decision makers."
decisiontheory  ai  conference 
december 2010 by stuhlmueller
A grand unified theory of AI
Popular account of some of the research in our lab.
ai  cogsci  church 
march 2010 by stuhlmueller
A Monte Carlo AIXI Approximation
Describes a scaled down AIXI agent that uses Monte Carlo Tree Search.
aixi  ai  hutter 
september 2009 by stuhlmueller
Harik Shazeer Labs 
Ex-Googlers working on AI via probabilistic programming.
ai  probabilistic-programming 
june 2009 by stuhlmueller
Paul Almond
Articles on ai, anthropics, minds and substrates, planning as modelling, Occam's razor and more.
ai  philosophy  mind  occam 
may 2009 by stuhlmueller
Machine Super Intelligence - Shane Legg (pdf)
Shane's thesis. Good intro to Bayesian sequence prediction, Solomonoff's universal prior and Solomonoff induction.
ai  aixi  intelligence 
august 2008 by stuhlmueller
Bayesian models of human inductive learning (talk by Josh Tenenbaum)
Convinced me that Bayesian inference over hierarchies of flexibly structured representations is a good model of human inductive learning.
mit  bayes  cogsci  machine  learning  ai  *interesting 
may 2008 by stuhlmueller
Polynomial Programming Language
Proposes a language in which only all polynomial time computable functions can be programmed. A useful constraint for artificial intelligence based on program search?
compsci  programming  complexity  ai 
april 2008 by stuhlmueller
Radio Electronics March 1949 — The Electronic Brain (pdf)
"But perhaps the most serious danger in such a machine will be its selfishness. Whatever the problem, it will judge the appropriateness of an action by how the feedback affects itself" — allopoiesis + intelligence = autopoiesis?
history  ai  ashby  cybernetics 
march 2008 by stuhlmueller
Machine Learning Summer School 2008 - Video Lectures
Topics: Introduction to Statistical Machine Learning, Foundations, Kernel Methods, Inference in Graphical Models, Contrast Data Mining.
ai  machinelearning  video 
march 2008 by stuhlmueller
Universal Self-Supervising Hierarchical Learning
"If such a universal [learning] algorithm exists, many variants likely also exist, some of which may be much more appropriate for implementation in silicon. This STTR is seeking proposals that identify and ultimately implement the best of these variants."
ai  machine  learning  grant  application 
february 2008 by stuhlmueller
A Computational Approximation to the AIXI Model (PDF)
Suggests Monte Carlo sampling of programs according to their (time-bound) algorithmic probability as an approximation for the optimal but incomputable AIXI theory. A few thoughts on how our environment should bias choice of hypotheses for induction.
ai  aixi  approximation 
january 2008 by stuhlmueller
A Proposed Design for Distributed Artificial Intelligence (Matt Mahoney)
Proposes to implement artificial intelligence as a large collection of narrowly specialized experts and a decentralized infrastructure for getting queries and updates to the right experts.
ai  design  proposal  mahoney 
december 2007 by stuhlmueller
Using Compassion and Respect to Motivate an Artificial Intelligence
"Presents a decision procedure that can, in principle, observe people's behavior and from that infer what they want."
ai  friendliness  singularity  freeman 
december 2007 by stuhlmueller
Gödel, Nagel, minds and machines (PDF)
On Gödel's and Nagel's contrasting views on the possible significance of Gödel’s theorems for minds vs. machines in the development of mathematics.
gödel  nagel  mind  ai  incompleteness 
october 2007 by stuhlmueller
RL Competition 2008
"A forum for reinforcement learning researchers to rigorously compare the performance of their methods on a suite of challenging domains."
machinelearning  reinforcement  learning  ai  competition 
october 2007 by stuhlmueller
Can Computers Think?
A set of 7 poster-sized argumentation maps that chart the entire history of the debate.
ai  philosophy  poster 
september 2007 by stuhlmueller
The Rise and Fall of Thinking Machines
A close up look at a doomed-yet-brilliant start-up computer company that never quite grasped the basics of business. From 1995.
history  business  thinking  machines  ai 
august 2007 by stuhlmueller
Generating Trading Agent Strategies
Presents methods for finding or approximating Nash equilibria for infinite games and for intractably large finite games.
ai  trading  agents  game-theory  :view 
july 2007 by stuhlmueller
Artificial General Intelligence: A Gentle Introduction
Outline of a talk by Pei Wang given at the "Mind and Machine" Seminar at Shanghai in June 2007.
ai  introduction 
june 2007 by stuhlmueller
Decade of the Mind Videos - George Mason University
Leading researchers on many disciplines of brain study – including neuroscience, neurobiology, computer science, robotics and economics – converged at Mason to discuss the urgent need for a decade-long research initiative into brain research.
ai  neuroscience  research  video 
june 2007 by stuhlmueller
MindRACES - from Reactive to Anticipatory Cognitive Embodied Systems
The goal of the Mind RACES project is to investigate different anticipatory cognitive mechanisms and architectures in order to build Cognitive Systems endowed with the ability to predict the outcome of their actions.
ai  research  prediction 
june 2007 by stuhlmueller
Ben Goertzel: Is Google Secretly Creating an AGI? (Reasons Why I Doubt It)
"The culture and mentality needed to create AGI seems to be different from the one needed to rapidly create a large and massively profitable company. My prediction is that if Google ever does get an AGI, they will buy it rather than build it."
ai  google  singularity  goertzel 
june 2007 by stuhlmueller
Trading Agent Competition
The Trading Agent Competition (TAC) is an international forum designed to promote and encourage research into the trading agent problem.
ai  trading  competition  research 
may 2007 by stuhlmueller
SL4: Donaldson, Tegmark and AGI
Eurisko stood for perhaps two decades as the most advanced AI ever created. And then Douglas Lenat abandoned it, decades ahead of the rest of us in the insight that recursive self-improvement is a mirage, there are no short cuts.
ai  recursion  lenat  eurisko  sl4 
may 2007 by stuhlmueller
What Smartness Means (Michael Anissimov)
If the smartest human we can throw at the problem is just about as good as anyone else, then we project the quality of hardness onto the problem - not onto the abstract recognition that “human intelligence isn’t good enough”.
ai  transhumanism  singularity 
may 2007 by stuhlmueller
The smartest (or the nuttiest) futurist on Earth (Fortune)
Peter Diamandis, creator of the X-Prize: "The Singularity, for anyone who stops and thinks about it, is completely obvious." And: Ray Kurzweil is running a Hedge fund guided by an artificial intelligence program. Billionaire Vinod Khosla invests.
ai  kurzweil  singularity  future 
may 2007 by stuhlmueller
AGI-08: The First Conference on Artificial General Intelligence
Date: March 1-3, 2008. Location: Memphis, Tennessee, USA. Call for Papers: Submission deadline: September 30, 2007.
ai  conference  agiri 
may 2007 by stuhlmueller
The Coming Technological Singularity (Vernor Vinge, 1993)
"Within thirty years, we will have the technological means to create superhuman intelligence. Shortly after, the human era will be ended. Is such progress avoidable? If not to be avoided, can events be guided so that we may survive?"
singularity  ai  vinge  future 
april 2007 by stuhlmueller
Absent Qualia, Fading Qualia, Dancing Qualia
Conclusion: Systems that duplicate our functional organization will be conscious even if they are made of silicon, constructed out of water-pipes, or instantiated in an entire population.
chalmers  philosophy  mind  ai  consciousness 
april 2007 by stuhlmueller
The AI Impact Initiative (Singularity Institute)
"We will form a multidisciplinary body of experts to bring a broad perspective to the critical issue of advanced AI."
ai  singularity  singinst 
april 2007 by stuhlmueller
The Singularity (by Lyle Burkhead)
'There isn't going to be an "intelligence explosion," as conceived by Vernor Vinge, but there could still be an event beyond which human affairs as we know them could not continue. Such an event could come from the advent of artificial life.'
singularity  ai  artificiallife  criticism 
april 2007 by stuhlmueller
SL4 Wiki: Starglider/Quotes
"These are mainly quotes that I have collected during my AI research, plus a few I encountered under other circumstances. They all struck me as relevant to Seed AI, Friendly AI or the Singularity in general."
ai  wilson  starglider  quotes 
march 2007 by stuhlmueller
Come Celebrate the Joy of Programming, with the World's Most Unbureaucratic Computers. | Don Hopkins
An essay written a while ago (1986 or so) by Richard M Stallman (RMS), about his experiences at the MIT AI Lab, and the story of the Lisp Machine Wars.
lisp  stallman  mit  history  ai 
march 2007 by stuhlmueller
Artificial intelligence within our lifetime? No idle speculation
Attempts to argue that there are several ways by which artificial intelligence may be developed in the near future, and that the probability of this happening is high enough that the possibility needs to be considered when making plans for the future.
ai  future  singularity 
march 2007 by stuhlmueller
Why evolution? Why not neuroscience? - GreyThumb.Blog
"There are really two big promising directions in machine learning/AI today: evolutionary computation and brain reverse-engineering. Some readers might be curious as to why I'm working on evolutionary computation and not neuroscience-based approaches."
evolution  neuroscience  ai 
march 2007 by stuhlmueller
TP: Simulation, Consciousness, Existence
Our descendants may develop means to venture far from the comfortable realms we consider reality, into arbitrarily strange volumes of the all-possible library. Perhaps we can stretch our imaginations enough to peer a short distance into this territory.
simulation  consciousness  ai  singularity 
march 2007 by stuhlmueller
Design and control of self-organizing systems (PDF)
Thesis that proposes a methodology to aid engineers in the design and control of complex self-organizing systems.
complexity  design  compsci  ai 
march 2007 by stuhlmueller
Darwin - A Theorem Prover for the Model Evolution Calculus
Darwin is an automated theorem prover for first order clausal logic and the first implementation of the Model Evolution Calculus.
logic  proof  evolution  ai 
march 2007 by stuhlmueller
Reflexive Induktive Inferenz (PDF)
Skript bestehend aus den für die Vorlesung "Algorithmisches Lernen" (TU Darmstadt) relevanten Kapiteln der Dissertation "Selbsteinschätzende Lernverfahren: Möglichkeiten und Grenzen." von G. Grieser.
induction  solomonoff  ai  compsci  learning 
march 2007 by stuhlmueller
Optimal sequential decisions based on algorithmic probability (Hutter's thesis)
The major theme of the thesis is to develop a mathematical foundation of Artificial Intelligence and, more specifically, to develop a theory for rational agents acting optimally in any environment.
ai  probabilitytheory  information  theory  prediction  *interesting 
march 2007 by stuhlmueller
Grundlagen algorithmischer Informationstheorie (PDF)
Soweit fürs maschinelle Lernen relevant. Stichwortartige Beilage zur Vorlesung "Maschinelles Lernen II" (SS 2005).
schmidhuber  ai  information  theory 
march 2007 by stuhlmueller
Solomonoff Induction by Shane Legg (PDF)
Solomonoff ’s induction method is a theoretical model of what could be considered a perfect inductive inference system. Incomputable.
solomonoff  induction  prediction  ai  math 
march 2007 by stuhlmueller
Asymptotic Calibration (.ps)
Can we forecast the probability of an arbitrary sequence of events happening so that the stated probability of an event happening is close to its empirical probability?
prediction  probabilitytheory  ai 
march 2007 by stuhlmueller
Numenta - Software
The Numenta Platform for Intelligent Computing is now available. NuPIC implements a hierarchical temporal memory system (HTM) patterned after the human neocortex.
numenta  htm  neuroscience  simulation  ai 
march 2007 by stuhlmueller
Re: Safety of brain-like AGIs (SL4, Shane Legg)
"A lack of concrete AGI projects is not what worries me, it's the lack of concrete plans on how to keep these safe that worries me. A massive legion is being assembled at the gate, and the best response we have come up with is an all-star debate team."
ai  quotes  sl4 
march 2007 by stuhlmueller
Eric Baum on Jeff Hawkins' "On Intelligence"
"The really hard part of learning is getting started, e.g. discovering the initial inductive biases, and evolution had been working on that problem for many aeons before cortex was even invented."
ericbaum  onintelligence  ai  criticism 
february 2007 by stuhlmueller
Speed Prior (Jürgen Schmidhuber)
A new simplicity measure for near-optimal computable predictions (based on the fastest way of describing objects, not the shortest).
ai  compsci  schmidhuber  dallemolle 
february 2007 by stuhlmueller
On the existence and convergence of computable universal priors (.ps.gz)
A prior distribution summarises what is known about a variable in the absence of any observations. Solomonoffs universal prior combines Occam’s razor and the principle of multiple explanations. For which comp. classes do comp. universal priors exist?
compsci  ai  dallemolle 
february 2007 by stuhlmueller
Google at work on AI (CNet)
"We have some people at Google (who) are really trying to build artificial intelligence and to do it on a large scale," Page said to a packed Hilton ballroom of scientists. "It's not as far off as people think."
google  ai 
february 2007 by stuhlmueller
How to do research in the MIT AI lab
Heuristics that may be useful in picking up the specific skills needed for research (reading, writing, programming) and for understanding and enjoying the process itself (methodology, topic and advisor selection, and emotional factors).
research  education  ai  mit 
february 2007 by stuhlmueller
Competent Program Evolution by Moshe Looks (PDF)
How can we automatically build a problem-specific representation that is more tractable than the general space?
ai  compsci  learning  algorithms 
february 2007 by stuhlmueller
Peter Norvig: Theorizing from data: Avoiding the capital mistake
"Rather than argue about whether this algorithm is better than that algorithm, all you have to do is get ten times more training data. And now all of a sudden, the worst algorithm ... is performing better than the best algorithm on less training data."
google  ai  data  norvig 
february 2007 by stuhlmueller
Yudkowsky's talk from the Singularity Summit of 2006 (MOV)
Endow computer with general intelligence. Apply intelligence to improve upon itself. Lather, rinse, repeat. FOOM! Intelligence explosion.
ai  singularity  yudkowsky  singinst 
january 2007 by stuhlmueller
Andiamo by Shane Legg
"Finally, after so many years thinking about doing it, tonight at Bar Tra in Lugano, I, along with two other guys, launched a project to build an AGI. [..] 2007 is going to be a very interesting year."
ai  singularity  dallemolle 
january 2007 by stuhlmueller
Polyscheme (Nick Cassimatis)
Polyscheme is a cognitive architecture designed to model and achieve human-level intelligence by integrating multiple methods of representation, reasoning and problem solving.
ai  research 
january 2007 by stuhlmueller
Human-Level Intelligence Laboratory (Nick Cassimatis)
The goal of the Human-Level Intelligence Laboratory is to explain human intelligence and design machines with human-level intelligence.
ai  research 
january 2007 by stuhlmueller
Formal frameworks for circular phenomena (by Kai-Uwe Kuehnberger, Osnabrück) (PDF)
Possibilities of modeling pathological expressions in formal and natural languages. May in part be relevant for models where classical decision theory breaks down due to infinite recursion.
ai  logic  philosophy  decisiontheory  osnabrück 
january 2007 by stuhlmueller
Artificial Intelligence as a Positive and Negative Factor in Global Risk (PDF)
If prophets of 1900 AD - never mind 1000 AD - had tried to bound the powers of human civilization a billion years later, some of those impossibilities would have been accomplished before the century was out.
ai  existentialrisks  yudkowsky  singinst 
january 2007 by stuhlmueller
Elephants don't play chess by Rodney A. Brooks (PDF)
"We explore a research methodology which emphasizes ongoing physical interaction with the environment as the primary source of constraint on the design of intelligent systems."
brooks  ai  robots  planning 
january 2007 by stuhlmueller
Computers versus Common Sense - Google Video
Douglas Lenat: "[..] so we can achieve Sergey [Brin]'s goal of a general AI by 2020"
ai  cyc  lenat  google  video 
january 2007 by stuhlmueller
30th German Conference on Artificial Intelligence
Sep 10-13, 2007, in Osnabrück, Germany.
ai  conference  germany  osnabrück 
january 2007 by stuhlmueller
Foundations of Order by Eliezer Yudkowsky (PDF)
"What a strange thing a human must be - an intelligence inscribed entirely by evolution, a mind that wasn't constructed by another mind. We are one of the oddest and most awkward sights in the universe."
ai  singularity  yudkowsky  evolution  order 
january 2007 by stuhlmueller
Course: Machine Learning and Optimization II
From foundations of algorithmic information theory to asymptotically optimal yet infeasible methods showing the ultimate limits of machine learning, and all the way down to practically useful tricks for recurrent nets.
ai  compsci  machinelearning  schmidhuber  studium  tu  munich 
january 2007 by stuhlmueller
Course: Machine Learning and Optimization I
"We focus on learning agents interacting with an initially unknown world. Since the world is dynamic, unlike many other machine learning courses ours will put strong emphasis on learning to deal with sequential data."
ai  compsci  machinelearning  schmidhuber  studium  tu  munich 
january 2007 by stuhlmueller
Benjamin L Cordes
"Studying Artificial Intelligence in Zürich from Oktober 2006 on. My main interests are bioinspired AI, ALife, Logic-AI, AI in Games, Theory of Computation, Philsophy of AI."
people  ai  swiss 
january 2007 by stuhlmueller
The Evolution of Cybernetics
A Journal by Simon Funk
blog  ai  math  compsci 
january 2007 by stuhlmueller
What keeps Jaron Lanier awake at night (PDF)
On artificial intelligence, cybernetic totalism, and the loss of common sense. "We should do everything we can to avoid singularities. A singularity is a sign that we've failed."
lanier  ai  singularity  futurism  criticism 
january 2007 by stuhlmueller
Why AGI May Be Near (SL4 Wiki)
Reasons why general AI may be accomplished, with effective, diligent effort, within 10 to 30 years.
sl4  ai  future  reference 
december 2006 by stuhlmueller
Singularity Institute for Artificial Intelligence - Wikipedia, the free encyclopedia
Founding, early years and recent progress of SIAI.
ai  singularity  singinst  yudkowsky  reference 
december 2006 by stuhlmueller
Gödel vs. Artificial Intelligence
Gödel's Incompleteness Theorem is not an obstacle to Artificial Intelligence.
ai  gödel 
december 2006 by stuhlmueller
Ten Years to a Positive Singularity - If we Really, Really Try (Ben Goertzel)
"Why ten years? It’s a nice round number. Just like most of you, I have ten fingers on my hands. I could have said eight or thirteen instead. But I think ten years – or something in this order of magnitude – could really be achievable."
goertzel  singularity  ai  novamente 
december 2006 by stuhlmueller
“I have crushed his puny human mind!” (vetta.org)
"Deep Fritz was playing at a level which the best chess minds in the world were struggling just to understand, let alone beat."
ai  chess 
december 2006 by stuhlmueller
On runaway recursive self-improvement, AIs as children, economics (J. Storrs Hall)
"I think there's a level of universality, like a Turing machine for computation. The huge difference between us and animals is that we're universal and they're not [..]. 'superhuman' intelligence will be faster but not fundamentally different"
ai  rsi  singularity 
december 2006 by stuhlmueller
In Its Image
A non-profit corporation that wants to achieve life extension through the melding of human consciousness with machine intelligence -- "we have claimed the status of a church".
ai  consciousness  singularity  *dubious 
december 2006 by stuhlmueller
Rational Futurism
A Singularitarian blog with particular focus on issues of AI morality and existential risks.
ai  futurism  singularity  blog  existentialrisks 
november 2006 by stuhlmueller
Self-generating Systems (Ben Goertzel)
A model of self-referential dynamics.
rsi  ai  algorithms 
november 2006 by stuhlmueller
Mind Ontology - AGIRIwiki
A systematic ontology of concepts, projects and resources relevant to Artificial General Intelligence.
ai  reference  research  wiki 
november 2006 by stuhlmueller
Motivational Systems of an AI (Richard Loosemore)
"[..] the system could never learn autonomously from a low level of knowledge *because* it is using goals that are articulated using the system's own knowledge base."
ai  limitations  rsi 
november 2006 by stuhlmueller
Unified AI systems
Classification of AGI projects. Categories: Structure, behavior, capability, function and principle.
ai  singularity 
november 2006 by stuhlmueller
« earlier      

related tags

*argh ⊕  *dubious ⊕  *informative ⊕  *interesting ⊕  :view ⊕  agents ⊕  agiri ⊕  ai ⊖  aixi ⊕  algorithms ⊕  application ⊕  approximation ⊕  artificiallife ⊕  ashby ⊕  bayes ⊕  blog ⊕  book ⊕  brooks ⊕  business ⊕  chalmers ⊕  chess ⊕  church ⊕  cogsci ⊕  competition ⊕  complexity ⊕  compression ⊕  compsci ⊕  conference ⊕  consciousness ⊕  contest ⊕  criticism ⊕  cybernetics ⊕  cyc ⊕  dallemolle ⊕  data ⊕  deblanc ⊕  decisiontheory ⊕  degaris ⊕  design ⊕  education ⊕  ericbaum ⊕  essays ⊕  eurisko ⊕  evolution ⊕  existentialrisks ⊕  fiction ⊕  freeman ⊕  friendliness ⊕  future ⊕  futurism ⊕  game-theory ⊕  germany ⊕  goertzel ⊕  google ⊕  grant ⊕  gödel ⊕  history ⊕  htm ⊕  hutter ⊕  incompleteness ⊕  induction ⊕  information ⊕  intelligence ⊕  interview ⊕  introduction ⊕  jandrewrogers ⊕  kurzweil ⊕  lanier ⊕  learning ⊕  lenat ⊕  limitations ⊕  lisp ⊕  logic ⊕  machine ⊕  machinelearning ⊕  machines ⊕  mahoney ⊕  math ⊕  medina ⊕  mind ⊕  mit ⊕  munich ⊕  nagel ⊕  neuroscience ⊕  nickhay ⊕  norvig ⊕  novamente ⊕  numenta ⊕  occam ⊕  onintelligence ⊕  order ⊕  osnabrück ⊕  peiwang ⊕  people ⊕  philosophy ⊕  planning ⊕  poster ⊕  prediction ⊕  probabilistic-programming ⊕  probabilitytheory ⊕  programming ⊕  proof ⊕  proposal ⊕  psychology ⊕  quotes ⊕  recursion ⊕  reference ⊕  reinforcement ⊕  research ⊕  robots ⊕  rsi ⊕  schmidhuber ⊕  science ⊕  simulation ⊕  singinst ⊕  singularity ⊕  sl4 ⊕  solomonoff ⊕  stallman ⊕  starglider ⊕  stories ⊕  studium ⊕  swiss ⊕  technology ⊕  theory ⊕  thinking ⊕  trading ⊕  transhumanism ⊕  tu ⊕  video ⊕  vinge ⊕  webmind ⊕  wiki ⊕  wikipedia ⊕  wilson ⊕  yudkowsky ⊕ 

Copy this bookmark:



description:


tags: