Posts

7th Annual Conference of the Australasian Bayesian Network Modelling Society (ABNMS2015)

November 23 – 24, 2015: Pre-Conference Workshop
November 25 – 26, 2015: Conference

[Official Website Here]

Location: Monash University, Caulfield, Melbourne (Australia)
Promo vid | Contact: abnms2015@abnms.org

Keynote Speakers: The conference organisers are pleased to announce that Dr Bruce Marcot of the US Forest Service, Dan Ababei from Lighttwist Software, Netherlands and Assoc Prof Jonathan Keith from Monash University will deliver the keynote address.

You will be able to register for the tutorials and the conference separately or together.

Bayesian Intelligence blog about the conf

– Dr. Kevin B. Korb is a Director and co-founder of Bayesian Intelligence, and a reader at Monash University. He specializes in the theory and practice of causal discovery of Bayesian networks (aka data mining with BNs), machine learning, evaluation theory, the philosophy of scientific method and informal logic. Email: kevin.korb (at) bayesian-intelligence.com

Seventh Annual Conference of the Australasian Bayesian Network Modelling Society - Ann E Nicholson– Prof. Ann E. Nicholson is a Director and co-founder of Bayesian Intelligence and a professor at Monash University who specializes in Bayesian network modelling. She is an expert in dynamic Bayesian networks (BNs), planning under uncertainty, user modelling, Bayesian inference methods and knowledge engineering BNs. Email: ann (dot) nicholson (at) bayesian-intelligence (dot) com

Many thanks for watching!
– Support me via Patreon: https://www.patreon.com/scifuture
– Please Subscribe to this Channel: http://youtube.com/subscription_center?add_user=TheRationalFuture
– Science, Technology & the Future website: http://scifuture.org

Automating Science: Panel – Stephen Ames, John Wilkins, Greg Restall, Kevin Korb

A discussion among philosophers, mathematicians and AI experts on whether science can be automated, what it means to automate science, and the implications of automating science – including discussion on the technological singularity.

– implementing science in a computer – Bayesian methods – most promising normative standard for doing inductive inference
– vehicle : causal Bayesian networks – probability distributions over random variables showing causal relationships
– probabilifying relationships – tests whose evidence can raise the probability

05:23 does Bayesianism misrepresent the majority of what people do in science?

07:05 How to automate the generation of new hypotheses?
– Is there a clean dividing line between discovery and justification? (Popper’s view on the difference between the context of discovery and context of justification) Sure we discuss the difference between the concepts – but what is the difference between the implementation?

08:42 Automation of Science from beginning to end: concept formation, discovery of hypotheses, developing experiments, testing hypotheses, making inferences … hypotheses testing has been done – through concept formation is an interestingly difficult problem

Panel---Automating-Science-and-Artificial-Intelligence---Kevin-Korb,-Greg-Restall,-John-Wilkins,-Stephen-Ames-1920x10839:38 – does everyone on the panel agree that automation of science is possible? Stephen Ames: not yet, but the goal is imminent, until it’s done it’s an open question – Kevin/John: logically possible, question is will we do it – Greg Restall: Don’t know, can there be one formal system that can generate anything classed as science? A degree of open-endedness may be required, the system will need to represent itself etc (Godel!=mysticism, automation!=representing something in a formal deductive theory)

13:04 There is a Godel theorem that applies to a formal representation for automating science – that means that the formal representation can’t do everything – therefore what’s the scope of a formal system that can automate science? What will the formal representation and automated science implementation look like?

14:20 Going beyond formal representations to automate science (John Searle objects to AI on the basis of formal representations not being universal problem solvers)

15:45 Abductive inference (inference to the best explanation) – & Popper’s pessimism about a logic of discovery has no foundation – where does it come from? Calling it logic (if logic means deduction) is misleading perhaps – abduction is not deductive, but it can be formalised.

17:10 Some classified systems fall out of neural networks or clustering programs – Google’s concept of a cat is not deductive (IFAIK)

19:29 Map & territory – Turing Test – ‘if you can’t tell the difference between the model and the real system – then in practice there is no difference’ – the behavioural test is probably a pretty good one for intelligence

22:03 Discussion on IBM Watson on Jeopardy – a lot of natural language processing but not natural language generation

24:09 Bayesianism – in mathematics and in humans reasoning probabilistically – it introduced the concept of not seeing everything in black and white. People get statistical problems wrong often when they are asked to answer intuitively. Is the technology likely to have a broad impact?

26:26 Human thinking, subjective statistical reasoning – and the mismatch between the public communicative act often sounding like Boolean logic – a mismatch between our internal representation and the tools we have for externally representing likelihoods
29:08 Low hanging fruit in human communication probabilistic reasoning – Bayesian nets and argument maps (Bayesian nets strengths between premises and conclusions)

29:41 Human inquiry, wondering and asking questions – how do we automate asking questions (as distinct from making statements)? Scientific abduction is connected to asking questions – there is no reason why asking questions can’t be automated – there is contrasted explanations and conceptual space theory where you can characterise a question – causal explanation using causal Bayesian networks (and when proposing an explanation it must be supported some explanatory context)

32:29 Automating Philosophy – if you can automate science you can automate philosophy –

34:02 Stanford Computational Metaphysics project (colleagues with Greg Restall) – Stanford Computational Metaphysics project – formalization of representations of relationships between concepts – going back to Leibniz – complex notions can be boiled down to simpler primitive notions and grinding out these primitive notions computationally – they are making genuine discoveries
Weak Reading: can some philosophy be automated – yes
Strong Reading of q: can All of philosophy be automated? – there seem to be some things that count as philosophy that don’t look like they will be automated in the next 10 years

35:41 If what we’re is interested in is to represent and automate the production of reasoning formally (not only to evaluate), as long as the domain is such that we are making claims and we are interested in the inferential connections between the claims, then a lot of the properties of reasoning are subject matter agnostic.

36:46 (Rohan McLeod) Regarding Creationism is it better to think of it as a poor hypothesis or non-science? – not an exclusive disjunct, can start as a poor hypothesis and later become not-science or science – it depends on the stage at the time – science rules things out of contention – and at some point creationism had not been ruled out

38:16 (Rohan McLeod) Is economics a science or does it have the potential to be (or is it intrinsically not possible for it to be a science) and why?
Are there value judgements in science? And if there are how do you falsify a hypothesis that conveys a value judgement? physicists make value judgements on hypothesis “h1 is good, h2 is bad” – economics may have reducible normative components but physics doesn’t (electrons aren’t the kinds of things that economies are) – Michael ??? paper on value judgements – “there is no such thing as a factual judgement that does not involve value” – while there are normative components to economics, it is studied from at least one remove – problem is economists try to make normative judgements like “a good economy/market/corporation will do X”

42:22 Problems with economics – incredibly complex, it’s hard to model, without a model exists a vacuum that gets filled with ideology – (are ideologies normative?)

42:56 One of the problems with economics is it gets treated like a natural system (in physics or chemistry) which hides all the values which are getting smuggled in – commitments and values which are operative and contribute to the configuration of the system – a contention is whether economics should be a science (Kevin: Yes, Stephen: No) – perhaps economics could be called a nascent science (in the process of being born)

44:28 (James Fodor) Well known scientists have thought that their theories were implicit in nature before they found them – what’s the role of intuition in automating science & philosophy? – need intuitions to drive things forward – intuition in the abduction area – to drive inspiration for generating hypothesis – though a lot of what get’s called intuition is really the unconscious processing of a trained mind (an experienced driver doesn’t have to process how to drive a car) – Louis Pasteur’s prepared mind – trained prior probabilities

46:55 The Singularity – disagreement? John Wilkins suspects it’s not physically possible – Where does Moore’s Law (or its equivalents in other hardware paradigms) peter out? The software problem could be solved near or far. Kevin agrees with I.J. Good – recursively improving abilities without (obvious) end (within thermodynamic limits). Kevin Korb explains the intelligence explosion.

50:31 Stephen Ames discusses his view of the singularity – but disagrees with uploading on the grounds of needing to commit to philosophical naturalism

51:52 Greg Restall mistrusts IT corporations to get uploading right – Kevin expresses concerns about using star-trek transporters – the lack of physical continuity. Greg discusses theories of intelligence – planes fly as do birds, but planes are not birds – they are differing

54:07 John Wilkins – way too much emphasis is put on propositional knowledge and communication in describing intelligence – each human has roughly the same amount of processing power – too much rests on academic pretense and conceit.

54:57 The Harvard Rule – under conditions of consistent lighting, feeding etc – the organism will do as it damn well pleases. But biology will defeat simple models.. Also Hulls rule – no matter what the law in biology is there is an exception (inc Hull’s law) – so simulated biology may be difficult. We won’t simulate an entire organism – we can’t simulate a cell. Kevin objects

58:30 Greg R. says simulations and models do give us useful information – even if we isolate certain properties in simulation that are not isolated in the real world – John Wilkins suggests that there will be a point where it works until it doesn’t

1:00:08 One of the biggest differences between humans and mice is 40 million years of evolution in both directions – the problem is in evo biol is your inductive projectability – we’ve observed it in these cases, therefore we expect it in this – it fades out relatively rapidly in direct disproportion to the degree of relatedness

1:01:35 Colin Kline – PSYCHE – and other AI programs making discoveries – David Chalmers have proposed the Hard Problem of Consciousness – pZombies – but we are all pZombies, so we will develop systems that are conscious because there is to such thing as consciousness. Kevin is with Dennet – info processing functioning is what consciousness supervenes upon
Greg – concept formation in systems like PSYCHE – but this milestone might be very early in the development of what we think of as agency – if the machine is worried about being turned off or complains about getting board, then we are onto something

Science vs Pseudoscience – Kevin Korb

Science vs PseuodoscienceScience has a certain common core, especially a reliance on empirical methods of assessing hypotheses. Pseudosciences have little in common but their negation: they are not science.
They reject meaningful empirical assessment in some way or another. Popper proposed a clear demarcation criterion for Science v Rubbish: Falsifiability. However, his criterion has not stood the test of time. There are no definitive arguments against any pseudoscience, any more than against extreme skepticism in general, but there are clear indicators of phoniness.

Demarcation

Science v Non-science – What’s the point? Possible goals for distinguishing btw them: Rhetorical, Political, Social Methodological: aiming at identifying methodolgical virtues and vices; improving practice How to proceed? Traditional: propose and test necessary and sufficient conditions for being science Less ambitious: collect prominent characteristics that support a “family resemblance”

What is Science?

Science is something like the organized (social, intersubjective) attempt to acquire knowledge about the world through interacting with the world. In the Western tradition, this began with the pre-Socratic philosophers and is especially associated with Aristotle.

science-pseudoscienceNature of Science Science contrasts to: Learning: individuals learn about the world. Their brains are wired for that. Mathematics/deduction: a handmaid to science, but powerless to teach us about the world on its own. Dogma, ideology, faith: These may be crucial to driving even scientific projects forward (as are good meals, sleep, etc.), but as they are by definition not tested by evidence, they are not themselves science.

A Potted History of the Philosophy of Science

Wissenschaftsphilosophie – The Vienna Circle Early 20th Century Scientific Major Success Stories: Charles Darwin (evolutionary biology) Gottlob Frege (formal logic) Albert Einstein (physics) The sciences were showing themselves as the most successful human project ever undertaken. In Vienna a group of great philosophers asked themselves: Why? How did this happen? With the Vienna Circle philosophy of science became a discipline, attempting to answer these questions.

The Vienna Circle & Logical Positivism : The beginning was the appointment of Ernst Mach as Professor of the Philosophy of the Inductive Sciences at the University of Vienna, 1895. Thereafter, Mortiz Schlick founded the Vienna Circle (and Logical Positivism) in 1922. Through the helpful activities of Adolf Hitler, the leading philosophers of science introduced the Vienna Circles ideas throughout the English speaking world.
Vienna Circle Ernst Mach Moritz Schlick Rudolf Carnap Hans Reichenbach Karl Popper Paul Feyerabend Noretta Koertge Positivismus Falsifikationismus Anarchismus
The Vienna Circle Basic Principles: Philosophy as logical analysis The logical foundation of science lies in observation & experiment e.g., Rudolf Carnap’s 1928 title: The Logical Construction of the World!! Key: Verifiability Criterion of Meaning What cannot be proven empirically, is meaningless. E.g., metaphysics, religion, superstition. {h, b e1, . . . en; e1, . . . en} verifies h
Karl Popper Objects Many scientific hypotheses are universal: E.g., light always bends near large masses. But {h, b e1, . . . e∞; e1, . . . e∞} is not even a possible state of affairs Aside from that, metaphysics is an ineliminable part of science; all science has fundamental presuppositions.
Karl Popper Falsificationism Key: Demarcation criterion for science What cannot be falsified empirically, is unscientific. E.g., Marxism, religion, psychoanalysis. {h, b e, ¬e} falsifies h Theses: We can make scientific (or social) progress alternating between Bold Conjectures and Refutations. The ideal test (severe test) is guaranteed to falsify one of two (or more) alternative conjectures. Progress: refuting more and more theories; not accumulating more and more knowledge.
Imre Lakatos Sophisticated Falsificationism {h, b e, ¬e} falsifies (h&b) Hypotheses stand or fall in networks, networked to each other and to theories of measurement, etc. = research programmes If a research programme makes novel predictions that come up true, it is progressive If a programme lies in a sea of anomalies and is dominated by ad hoc saving maneuvers, it is degenerating Unfortunately, there’s no definite point at which a degenerating research programme rationally needs to be abandoned.
Thomas Kuhn Scientific Revolutions In The Structure of Scientific Revolutions (1962) he introduced the idea that science moves (not: progresses) from “normal science” through a sea of anomalies to “revolutionary science” to a new “normal science” – from “paradigm” to “paradigm”. According to Kuhn, the process is not rational, but explained in terms of psychology, social processes and power relationships.
Paul Feyerabend Epistemic Anarchy In 1958 Feyerabend went to Berkeley, where he turned against Popper, promoting “Epistemological Anarchism” instead (Against Method, 1974). He embraced the inability to reject research programmes, promoting methodological pluralism instead. Denunciations of witchcraft, pseudosciences, etc. are mere expressions of prejudice.
Ludwig Wittgenstein Open Concepts Natural language concepts have an “open structure”, based on family resemblance, not definition.
Ludwig Wittgenstein Open Concepts One of Wittgenstein’s examples: Define “game”, in terms of the necessary and sufficient conditions. Now let’s play a game involving changing those conditions. . . Socrates’ game of taking some sophist’s definition for “love”, “knowledge”, “good” and poking holes in it could be played forever. Hence, Socrates’ phony humility in claiming that he knew nothing. The reality is that our understanding and use of language doesn’t depend on definitions.
1“Science” is an Open Concept Instead of assembling inadequate necessary and sufficient conditions, let’s collect examples of science and non-science and see what the former share in family resemblances. Leave problematic cases for later. Physics Mathematics Epidemiology Medicine Paleontology Religion Climatology Mining Evolution Theory Creationism Economics Politics Political Science Fox News
“Science” is an Open Concept I’d like to suggest the key family resemblances are: Empiricism: insistance on an empirical base versus ideological dominance Abstraction (generalization) and mathematization (when possible) versus anecdotal evidence Social processes encouraging objectivity, intersubjectivity, peer review, Popperian critical rationality versus authoritarianism
Some Pseudoscientific Arguments AGW/ecology/genetic regulatory/etc models are highly abstract, lose track of detailed reality and so are not scientific. George Box: “All models are wrong, but some are useful.” Any computer model will misrepresent continuity, but does it matter? The question is whether the property of the model of interest (mapping to reality) is preserved under model dynamics, not whether irrelevant details are carried along. The demand for “proof” in science is a good indicator of dishonesty.
Some Pseudoscientific Arguments Similarly: the model predicts overall process ok, but omits some really tiny details and therefore is wrong. Here’s an example I gave a data mining class; 120 years of data on business profits. Looks like three different trends concatenated. Let’s just regress just the points from 80-120.
Some Pseudoscientific Arguments Not bad. But some ornery shareholder says, let’s just try years 109-120 instead.
Some Pseudoscientific Arguments As we can all see profits are hardly moving; let’s turf out the board!!
Some Pseudoscientific Arguments NB: profit = global surface temperature; competitiveness = solar energy.
Some References on Scientific Method F Bacon (1620) Novum Organum Scientiarum. JS Mill (1843) System of Logic. M Gardner (1957) Fads and Fallacies in the Name of Science. Dover. T Kuhn (1962) The Structure of Scientific Revolutions. K Popper (1963) Conjectures and Refutations. R Carnap (1966) An Introduction to the Philosophy of Science. C Hitchcock (2004) Contemporary Debates in Philosophy of Science.

Slides can be found here:

 

Kevin KorbMy research is in: machine learning, artificial intelligence, philosophy of science, scientific method, Bayesian inference and reasoning, Bayesian networks, artificial life, computer simulation, epistemology, evaluation theory.

See http://www.csse.monash.edu.au/~korb/ The page is out of date, but accurate as far as it goes.

http://theconversation.com/is-passing-a-turing-test-a-true-measure-of-artificial-intelligence-27801

Email kbkorb [at] gmail {dot} com twitter: @kbkorb
http://theconversation.com/profiles/kevin-korb-115721