INTELLIGENCE WITHOUT REPRESENTAION 인지과학 협동과정 98132-506 이광주.

Slides:



Advertisements
Similar presentations
ARCHITECTURES FOR ARTIFICIAL INTELLIGENCE SYSTEMS
Advertisements

Elephants Don’t Play Chess
Lecture 8: Three-Level Architectures CS 344R: Robotics Benjamin Kuipers.
5-1 Chapter 5: REACTIVE AND HYBRID ARCHITECTURES.
Intelligent Agents Russell and Norvig: 2
Jenkins — Modular Perception and Control Brown Computer — ROUGH DRAFT ( ) 1 Workshop Introduction: Modular Perception.
Lecturer: Sebastian Coope Ashton Building, Room G.18 COMP 201 web-page: Lecture.
A Summary of the Article “Intelligence Without Representation” by Rodney A. Brooks (1987) Presented by Dain Finn.
Intelligence without Reason
SWE Introduction to Software Engineering
Establishing the overall structure of a software system
Architectural Design Principles. Outline  Architectural level of design The design of the system in terms of components and connectors and their arrangements.
Summer 2011 Wednesday, 8/3. Biological Approaches to Understanding the Mind Connectionism is not the only approach to understanding the mind that draws.
A Robust Layered Control System for a Mobile Robot Rodney A. Brooks Presenter: Michael Vidal.
1 Chapter 19 Intelligent Agents. 2 Chapter 19 Contents (1) l Intelligence l Autonomy l Ability to Learn l Other Agent Properties l Reactive Agents l Utility-Based.
UNIVERSITY OF SOUTH CAROLINA Department of Computer Science and Engineering CSCE 580 Artificial Intelligence Ch.2 [P]: Agent Architectures and Hierarchical.
McGraw-Hill/Irwin ©2005 The McGraw-Hill Companies, All rights reserved ©2005 The McGraw-Hill Companies, All rights reserved McGraw-Hill/Irwin.
Course Instructor: Aisha Azeem
Architectural Design Establishing the overall structure of a software system Objectives To introduce architectural design and to discuss its importance.
©Ian Sommerville 2004Software Engineering, 7th edition. Chapter 11 Slide 1 Architectural Design.
What is Software Architecture?
Chapter 7: Architecture Design Omar Meqdadi SE 273 Lecture 7 Department of Computer Science and Software Engineering University of Wisconsin-Platteville.
Mobile Robot Control Architectures “A Robust Layered Control System for a Mobile Robot” -- Brooks 1986 “On Three-Layer Architectures” -- Gat 1998? Presented.
Introduction to Behavior- Based Robotics Based on the book Behavior- Based Robotics by Ronald C. Arkin.
Chapter 14: Artificial Intelligence Invitation to Computer Science, C++ Version, Third Edition.
计算机科学概述 Introduction to Computer Science 陆嘉恒 中国人民大学 信息学院
©Ian Sommerville 1995 Software Engineering, 5th edition. Chapter 13Slide 1 Architectural Design u Establishing the overall structure of a software system.
©Ian Sommerville 2000, Mejia-Alvarez 2009 Slide 1 Software Processes l Coherent sets of activities for specifying, designing, implementing and testing.
Architectural Design portions ©Ian Sommerville 1995 Establishing the overall structure of a software system.
 The most intelligent device - “Human Brain”.  The machine that revolutionized the whole world – “computer”.  Inefficiencies of the computer has lead.
©Ian Sommerville 2000 Software Engineering, 6th edition. Chapter 10Slide 1 Architectural Design l Establishing the overall structure of a software system.
Towards Cognitive Robotics Biointelligence Laboratory School of Computer Science and Engineering Seoul National University Christian.
Artificial Intelligence Chapter 25 Agent Architectures Biointelligence Lab School of Computer Sci. & Eng. Seoul National University.
SOFTWARE DESIGN.
Intelligent Systems Lecture 13 Intelligent robots.
Outline: Biological Metaphor Biological generalization How AI applied this Ramifications for HRI How the resulting AI architecture relates to automation.
©Ian Sommerville 2000 Software Engineering, 6th edition. Chapter 10Slide 1 Architectural Design l Establishing the overall structure of a software system.
Architectural Design Yonsei University 2 nd Semester, 2014 Sanghyun Park.
An Ontological Framework for Web Service Processes By Claus Pahl and Ronan Barrett.
Autonomy and Artificiality Margaret A. Boden Hojin Youn.
University of Windsor School of Computer Science Topics in Artificial Intelligence Fall 2008 Sept 11, 2008.
OOAD Unit – I OBJECT-ORIENTED ANALYSIS AND DESIGN With applications
Service Service metadata what Service is who responsible for service constraints service creation service maintenance service deployment rules rules processing.
Chapter 6 – Architectural Design Lecture 1 1Chapter 6 Architectural design.
Robotica Lecture Review Reactive control Complete control space Action selection The subsumption architecture –Vertical vs. horizontal decomposition.
Of 33 lecture 1: introduction. of 33 the semantic web vision today’s web (1) web content – for human consumption (no structural information) people search.
Brooks’ Subsumption Architecture EEL 6838 T. Ryan Fitz-Gibbon 1/24/2004.
Subsumption Architecture and Nouvelle AI Arpit Maheshwari Nihit Gupta Saransh Gupta Swapnil Srivastava.
Distributed Models for Decision Support Jose Cuena & Sascha Ossowski Pesented by: Gal Moshitch & Rica Gonen.
The single most important skill for a computer programmer is problem solving Problem solving means the ability to formulate problems, think creatively.
第 25 章 Agent 体系结构. 2 Outline Three-Level Architectures Goal Arbitration The Triple-Tower Architecture Bootstrapping Additional Readings and Discussion.
CS223: Software Engineering Lecture 14: Architectural Patterns.
Chapter 15. Cognitive Adequacy in Brain- Like Intelligence in Brain-Like Intelligence, Sendhoff et al. Course: Robots Learning from Humans Cinarel, Ceyda.
From NARS to a Thinking Machine Pei Wang Temple University.
Introduction to Cogsci April 07, Central Theme Cognitive Science was occuppied with the algorithmic level for much of its history: successive manipulation.
Slide 1 Chapter 8 Architectural Design. Slide 2 Topics covered l System structuring l Control models l Modular decomposition l Domain-specific architectures.
Robot Intelligence Technology Lab. Evolutionary Robotics Chapter 3. How to Evolve Robots Chi-Ho Lee.
Introduction to Machine Learning, its potential usage in network area,
Learning Fast and Slow John E. Laird
Artificial Intelligence Chapter 25 Agent Architectures
Part 3 Design What does design mean in different fields?
Build Intelligence from the bottom up!
Build Intelligence from the bottom up!
Artificial Intelligence
Non-Symbolic AI lecture 4
Build Intelligence from the bottom up!
Subsuption Architecture
Artificial Intelligence Chapter 25. Agent Architectures
CHAPTER I. of EVOLUTIONARY ROBOTICS Stefano Nolfi and Dario Floreano
Chapter 1: Computational Intelligence and Knowledge
Presentation transcript:

INTELLIGENCE WITHOUT REPRESENTAION 인지과학 협동과정 이광주

Contents Introduction Evolution of Intelligence Abstraction as a Dangerous weapon Incremental Intelligence Who Has the Representation? The Methodology in Practice What this is not Limits to Growth

Introduction Traditional AI  right subpieces?  right interface? My approach  Incrementally build up, having complete system at each step  At each step, we let the system loose in the real world to find upgrade point

Different approach to AI Conclusion  Simple level intelligence get explicit representation and models of the world in the way  Using the world as a model is better! Hypothesis  Representation is the wrong unit of abstraction in building the bulkiest parts of intelligent systems

The Evolution of Intelligence Intelligence is once very simple only has:  The ability to move around in a dynamic environment  The ability sensing the surroundings Mobility, acute vision and the ability to carry out survival related task in a dynamic environment is necessary basis for development of intelligence

Abstraction as a Dangerous weapon(1) In AI, Abstraction is used  as a mechanism for self-delusion  to factor out all aspects of perception and motor skills “Good representation is the key to AI”  Representing only the pertinent facts explicitly, the semantics of a world (which on the surface was quite complex) were reduced to a simple closed system.  Ex) Chair and Photograph  How can we capture all concept?  And what?

Abstraction as a Dangerous weapon(2) Input to most AI program is a restricted set of simple assertions deduced from the real data by humans This abstraction performed by humans is the essence of intelligence and the hard part of the problems being solved No clean division between perception(abstraction) and reasoning in the real world

Abstraction as a Dangerous weapon(3) The abstraction reduces the input data so that the program experiences the same perceptual world as humans(Merkwelt in von Uexküll 1921)  Robot has its own Merkwelt  The Merkwelt we provides may not be what we actually use internally

Incremental Intelligence “I wish to build completely autonomous mobile agents that co-exist in the world with humans, and are seen by those humans as intelligent beings in their own right. Consider the problem of building Creatures as an engineering problem Engineering scheme  Decompose a complex system into parts  Build the parts  Interface them into a complete system 이광주 : 묻지마 : how human work, application, philosophical implication 이광주 : 묻지마 : how human work, application, philosophical implication

The Requirement for Creatures A Creature must cope appropriately and in a timely fashion with changes in its dynamic environment A Creature should be robust with respect to its environment A Creature should be able to adapt to surroundings and capitalize on fortuitous circumstances A Creature should do something in the world; it should have some purpose in being

Decomposition by function Traditionally, Intelligent system has been a central system.  Perceptual modules - deliver a symbolic description of the world  Action modules - take a symbolic description of desired actions and make sure they happen in the world. Vision workers are not immune to earlier criticisms of AI workers. Most vision research is presented as a transformation from one image representation to another registered image.

Decomposition by function(2) Troubles  Needs a long chain of modules to connect perception to action  To test any of them, they all must first be built  Until realistic modules are built, we can hardly predict exactly what modules will be needed or what interfaces they will need

Decomposition by Activity Divided into activity producing subsystems  Each activity (behavior producing system) individually connects sensing to action  layer, skill  Each activity must decide when to act for themselves, not be subroutine to be invoked at call of some other layer Advantages  Gives an incremental path from very simple systems to complex autonomous intelligent system. 각 단계에서 얘들은 small piece 만 만들면 되고, 만든 담엔 이미 있던 intelligence 랑만 interface 하게 해 주면 된다.

Decomposition by Activity(2) Experiment  First, Build a simple complete autonomous system, test it in the real world  Mobile robot, which avoids hitting things  Two independent channels connecting sensing to action.  No single place where “perception” delivers a representation of the world  Next, Build an incremental layer of intelligence  Operates in parallel to the first system  Try to visit distant visible places

Who has the representation? The fact that there is no central representation helps the Creature meet goals  Low-level simple activity - quick and often  Multiple parallel activities and No central representation - Gradual degradation  Each Layer has its implicit purpose (or goal) and is using the world as its own model  No need of explicit representation of goals that some central process selects from. by observation By not trying to have an analogous model of the world, centrally located in the system, we are less likely to have built in a dependence on that model being completely accurate. Rather, individual layers extract only those aspects of the world which they find relevant- projections of a repr into a simple subspace. By not trying to have an analogous model of the world, centrally located in the system, we are less likely to have built in a dependence on that model being completely accurate. Rather, individual layers extract only those aspects of the world which they find relevant- projections of a repr into a simple subspace. Thanks to no complex repr. and need to maintain, reason about it.

No representation vs. No central representation No representation such as standard AI representation  No variables that need instantiation  No rules which need to be selected  No choice To a large extent, the state of the world determines the action of the Creature.  “The complexity of the behavior of a system was not necessarily inherent in the complexity of the creature, but perhaps in the complexityof the environment” (Simon, 1969)

The Methodology in Practice Maxims  Test the Creature in the real world  Each layer must be fully debugged Subsumption architecture  decomposition into layers  incremental composition through debugging

Architecture Each layer is composed of  a fixed topology network of simple finite state machine Each finite state machine  has Handful of states  has 1~2 internal registers  has 1~2 internal timers  has access to simple computational machines  run asynchronously.  Sending and receiving fixed length messages  No central locus of control & data-driven

Architecture(2) Interfaces between layers  suppression  inhibition

Some diagram

What This is not It isn’t connectionism It isn’t Neural Networks It isn’t Production Rules It isn’t a Blackboard It isn’t German Philosophy

Limit to Growth How many layers can be built before the interactions become too complex? How complex can the behaviors be without the aid of central representations? Is learning and such high-level functions possible?