1 Neural Networks and Statistics: Intelligence and the Self Prof Bruce Curry and Dr Peter Morgan Cardiff Business School, UK.

Slides:



Advertisements
Similar presentations
Nature and Construction of Knowledge in Mathematics
Advertisements

Approaches, Tools, and Applications Islam A. El-Shaarawy Shoubra Faculty of Eng.
Introduction: The General Linear Model b b The General Linear Model is a phrase used to indicate a class of statistical models which include simple linear.
A Brief History of Artificial Intelligence
Chapter 10: What am I?.
SEARLE THE CHINESE ROOM ARGUMENT: MAN BECOMES COMPUTER.
Shailesh Appukuttan : M.Tech 1st Year CS344 Seminar
CPSC 533 Philosophical Foundations of Artificial Intelligence Presented by: Arthur Fischer.
The Turing Test What Is Turing Test? A person and a computer, being separated in two rooms, answer the tester’s questions on-line. If the interrogator.
Connectionist models. Connectionist Models Motivated by Brain rather than Mind –A large number of very simple processing elements –A large number of weighted.
CS 357 – Intro to Artificial Intelligence  Learn about AI, search techniques, planning, optimization of choice, logic, Bayesian probability theory, learning,
Acting Humanly: The Turing test (1950) “Computing machinery and intelligence”:   Can machine’s think? or Can machines behave intelligently? An operational.
Humans, Computers, and Computational Complexity J. Winters Brock Nathan Kaplan Jason Thompson.
AI – CS364 Hybrid Intelligent Systems Overview of Hybrid Intelligent Systems 07 th November 2005 Dr Bogdan L. Vrusias
COMP 3009 Introduction to AI Dr Eleni Mangina
CPSC 322 Introduction to Artificial Intelligence September 10, 2004.
Artificial Neural Networks - Introduction -
The Computational Theory of Mind. COMPUTATION Functions.
Philosophical Foundations Chapter 26. Searle v. Dreyfus argument §Dreyfus argues that computers will never be able to simulate intelligence §Searle, on.
Artificial Intelligence Reasoning. Reasoning is the process of deriving logical conclusions from given facts. Durkin defines reasoning as ‘the process.
Calculus With Tech I Instructor: Dr. Chekad Sarami.
CSCI 4410 Introduction to Artificial Intelligence.
Chapter 6: Objections to the Physical Symbol System Hypothesis.
Artificial Intelligence Introduction (2). What is Artificial Intelligence ?  making computers that think?  the automation of activities we associate.
Chapter 14: Artificial Intelligence Invitation to Computer Science, C++ Version, Third Edition.
Turing Test and other amusements. Read this! The Actual Article by Turing.
计算机科学概述 Introduction to Computer Science 陆嘉恒 中国人民大学 信息学院
Connectionism. ASSOCIATIONISM Associationism David Hume ( ) was one of the first philosophers to develop a detailed theory of mental processes.
Mestrado em Ciência de Computadores Mestrado Integrado em Engenharia de Redes e Sistemas Informáticos VC 14/15 – TP19 Neural Networks & SVMs Miguel Tavares.
Bloom County on Strong AI THE CHINESE ROOM l Searle’s target: “Strong AI” An appropriately programmed computer is a mind—capable of understanding and.
The Recursion Theorem Pages 217– ADVANCED TOPICS IN C O M P U T A B I L I T Y THEORY.
110/19/2015CS360 AI & Robotics AI Application Areas  Neural Networks and Genetic Algorithms  These model the structure of neurons in the brain  Humans.
For Friday Read chapter 27 Program 5 due.
For Friday Read chapter 27 Program 5 due. Program 5 Any questions?
For Friday Read chapter 27 Program 5 due. Program 5 Any questions?
A New Artificial Intelligence 5 Kevin Warwick. Philosophy of AI II Here we will look afresh at some of the arguments Here we will look afresh at some.
AI Philosophy: Computers and Their Limits G51IAI – Introduction to AI Andrew Parkes
How Solvable Is Intelligence? A brief introduction to AI Dr. Richard Fox Department of Computer Science Northern Kentucky University.
Chapter 13 Artificial Intelligence and Expert Systems.
1 Introduction to Artificial Intelligence (Lecture 1)
1 CS 385 Fall 2006 Chapter 1 AI: Early History and Applications.
Godel’s proof Danny Brown. Outline of godel’s proof 1.Create a statement that says of itself that it is not provable 2.Show that this statement is provable.
Automated Reasoning Early AI explored how to automated several reasoning tasks – these were solved by what we might call weak problem solving methods as.
Artificial Intelligence “Introduction to Formal Logic” Jennifer J. Burg Department of Mathematics and Computer Science.
Incompleteness. System Relativity Soundness and completeness are properties of particular logical systems. There’s no sense to be made of the claim that.
1 Use graphs and not pure logic Variables represented by nodes and dependencies by edges. Common in our language: “threads of thoughts”, “lines of reasoning”,
Dialog Processing with Unsupervised Artificial Neural Networks Andrew Richardson Thomas Jefferson High School for Science and Technology Computer Systems.
Anselm & Aquinas. Anselm of Canterbury ( AD) The Ontological Argument for the Existence of God (Text, pp )
Artificial Intelligence, simulation and modelling.
Neural Networks. Background - Neural Networks can be : Biological - Biological models Artificial - Artificial models - Desire to produce artificial systems.
CHAPTER 15: Tests of Significance The Basics ESSENTIAL STATISTICS Second Edition David S. Moore, William I. Notz, and Michael A. Fligner Lecture Presentation.
Artificial Intelligence Knowledge Representation.
Computer Systems Architecture Edited by Original lecture by Ian Sunley Areas: Computer users Basic topics What is a computer?
Artificial Intelligence Skepticism by Josh Pippin.
Propositional Logic.
New Directions in Information Technology Lecture 5 John Lee
Lecture 1 – Formal Logic.
Unit 5: Hypothesis Testing
Universality of Computation
Dialog Processing with Unsupervised Artificial Neural Networks
Course Instructor: knza ch
Anselm & Aquinas December 23, 2005.
Significance Tests: The Basics
Significance Tests: The Basics
Searle on Artificial Intelligence Minds, Brains and Science Chapter 2
Fundamentals of Neural Networks Dr. Satinder Bal Gupta
Dialog Processing with Unsupervised Artificial Neural Networks
Information Retrieval
Habib Ullah qamar Mscs(se)
Presentation transcript:

1 Neural Networks and Statistics: Intelligence and the Self Prof Bruce Curry and Dr Peter Morgan Cardiff Business School, UK

2 NEURAL NETWORKS ( NNs) Generally seen as part of the discipline of AI, although to us they are statistical devices. They originated as models of the workings of the brain ‘A Logical Calculus of Ideas Immanent in Nervous Activity’ This implies they are an alternative to symbolic computation, eg. rule based methods Rules and chaining methods, inference through formal logic. NNs carry out sub-symbolic computation They copy the physical workings of the brain Neurons + connections

3

4 Some Details Feedforward networks Inputs, Outputs, Hidden Nodes Hidden Node activation: step functions or sigmoids. These are fuzzified steps Hidden nodes provide the intelligence we seek to model They are like specialised parts of the brain brought into action when needed They can describe Fuzzy IF/THEN rules. Hence we don’t need a strict distinction between NNs and rule based methods.

5 NN learning Learning is an essential component of intelligence NN’s can learn rules Learning through weight adjustment and optimisation Minimum RMS (equivalent to least squares) Universal Approximation through use of a flexible functional form

6

7 Hence in statistical terms we have a form of nonlinear regression The network learns the underlying shape describing the relationship between Y and X. Example, Mexican Hat

8 NNs, Statistics and Intelligence Hence NNs are statistical devices Supervised and unsupervised learning NNs provide nonlinear alternatives to standard statistical methods They are applied to traditional statistical tasks

9 BUT Statistics, in its aims, is almost antithetical to intelligence The aim is automated judgment based on standard methods This is achieved by standard numerical measures, for example of the strength of a conclusion The prime example is testing hypotheses, where we have a significance level or ‘p value’ Everyone is supposed to agree that for example p =.001 gives a strong conclusion, with in fact less than 1% chance of being wrong This is in practice rather idealistic!!

10 CONTROVERSIES IN PHILOSOPHICAL ASPECTS OF COMPUTING (a) The nature of the Self and the Mind Body Problem. This includes issues involving consciousness. (b) The nature of Intelligence and the limits of Strong AI AI texts generally insist that the subject is concerned with computer models which operate in a way we would perceive as being intelligent. This has implications for the Turing test. A simple version of the test involving just outward behaviour or evidence would not be sufficient for intelligence. Interestingly, the attacks by Searle (through his ‘Chinese room’) on ‘Strong AI’ or ‘Computationalism’ have a similar flavour. It has been argued that a connectionist approach provides an escape from the problem.

11 (c) Gödel’s theorems and their implications for AI. The theorems serve to identify a difference between truth and provability, in which case machine intelligence inevitably has limitations. It has been argued that a system which can learn, for example a Neural Network, can escape from the implications of the Gödel theorems. However, because the difficulties arise specifically with self-referential statements in formal systems this is unlikely to be true.

12 DISCUSSION Our networks are detailed numeric models, which although based on some sophisticated methods are still quite simple and unintelligent They find optimal weight values through blind search They learn through weight adjustment They are statistical devices they also don’t embody intelligence They can be analysed using the standard tools of applied mathematics They are too detailed and too primitive to be regarded as models of intelligence as such ( as opposed to the underlying processes which produce intelligence) However, we can build specialised networks to model for example consciousness

13 The Self A Self is not necessary for intelligence, but it is for ‘higher’ levels of intelligence E.g. My cat is intelligent, an ant colony displays aspects of intelligence> neither has a self The self is the driver of the brain, but where and what is it? If we physically reverse engineer a brain, in such a way that the copy functions exactly as the original, where is the self? This is in fact a connectionist approach What happens with the self and NN’s? Our types of network are basic low level number processors, which can in fact be given higher level interpretations Can in fact simulate consciousness ( the self) in more specialised networks This is not ‘real’ but simulated consciousness. There can be a model of the self and consciousness of the self. Can we simulate a person who controls his/her self?

14 Searle Argument: Chinese Room Anti-computation view: passing Turing test does not necessarily imply intelligence ( test based on the end result not the process) Chinese language translation is just a mechanical linking of symbols, with syntactic rules. Maybe like an electronic dictionary. What about a human interpreter: does he/she operate mechanically? Symbols have no internal meaning, so AI is not attainable. (There is no self, to achieve understanding). But, we can simulate some of the process of human reasoning, eg. using Prolog. Partial simulation/ emulation of intelligence is attainable, even if the mind is not simply a digital computer But we must pass the Turing test in a way regarded as being intelligent.

15 NNs, Connectionism and Searle? As above, our own networks are just mechanical devices, without intelligence Connectionist answer to Searle? Intelligence as manifested in the brain consists of symbol manipulation plus lower level ( sub symbolic) processes). Therefore AI is possible. But, refer back to point above about perfect physical replica of the brain. Where in this perfect replica is intelligence and the self?

16 GOEDEL theorems These show distinction between truth + provability Hence incompleteness of any system of axioms Only arises with self referential statements: ‘This sentence is unprovable’ Show limitations of computationalist approach, but don’t destroy it. Can still simulate/emulate human thought processes to some degree

17 This is because it shows limitations of human intelligence Maths and reasoning are about derivation from initial axioms, therefore the truth of those axioms is unprovable. In this sense the Goedel theorems don’t do much damage. Theoretically possible to have computational intelligence which has proofs but also axioms/beliefs. Also, Goedel theorems deal with ‘perfect’ reasoning: human reasoning may be imperfect and this may be simulated.

18 Importance for NNs? Can’t argue that learning allows an escape: but learning of non self-referential statements is OK What happens with NN’s and self learning? Can simulate consciousness in the network, by having specialist nodes but isn’t this still limited by Goedel? Goedel theorems help with AI; they show that all reasoning is subject to limitations and axioms need to be ‘imported’.