AAAI 2013 Fall Symposium Proposal

Title – Self, Intelligent Reflection & Implementing Safe Autopoiesis

Description – In I Am a Strange Loop, Douglas Hofstadter argues that the key to understanding selves is the “strange loop”, a complex feedback loop inhabiting our brains and, arguably, constituting our minds. Artificial Intelligence (AI) and Artificial General Intelligence (AGI) generally have a focus of solving problems or achieving goals.  Instead, this implementation-oriented symposium will focus on this loop and guided self-(re)creation – particularly as a method of achieving human-level intelligence through iterative improvement (“seed AI”).  Ideally, the ultimate end product is a successful AGI with extensive self-knowledge and a motivational system promoting cooperation with and contribution to community via improvement of self and tools.

The AAAI communities that are expected to find this appealing are sub-groups of the Artificial General Intelligence (AGI) community, the Biologically Inspired Cognitive Architectures (BICA) community, and the Machine Consciousness (MC) community.  Non-AAAI communities that are expected to find this appealing are the NeuroBioEthics  community and the Ethical/Moral Machines sub-group of the Philosophy & Technology community.

This symposium is proposed as an implementation-orientation exploration of self, to include:

  • integrative architectures that are explicitly goal driven
    • “self” as operating system
    • “self” as society (of mind – Marvin Minsky)
    • “self” as economy (of idiots – Eric Baum)
    • “self” as authorship (Dennett, Wegner)
  • “safe” motivational systems
    • goal hierarchies
    • “safe” goal content
    • evaluation schemes
  • reflection
    • self-examination
    • self-modeling & self-knowledge
    • goal-based self-evaluation for self-improvement
  • emotions
    • as knowledge/rules of thumb/”actionable qualia”
    • as helpful & unhelpful biases (and how to intelligently improve)
    • as evaluation & enforcement mechanisms
  • integrating different knowledge and action representation schemes
    • coordination & translation between various schemes
    • analyzing trade-offs & knowing when to switch between schemes
  • self-improvement
    • via automated tool/method incorporation and evaluation
    • via learning (knowledge incorporation)
      • (re-)building schemes and models
    • discovery (refactoring, modularization, encapsulation and scale-invariance)
      • Meta-Optimizing Semantic Evolutionary Search (MOSES)
      • Frequent & Interesting Sub-HyperGRAph Mining (FISHGRAM)

While solutions need to be grounded and extensible, the symposium would prefer approaches starting with some initial structure rather than a tabula rasa with the lowest level bootstrapping approaches or first causes explanations (except where they are fully extended to initial structures and/or used to justify such structures).  Also, while autopoiesis and “functional consciousness” are obviously key topics, we would prefer that phenomenal consciousness arguments be considered off-topic.

Responses

  1. How to represent some of these using Kurweil’s PRTM Pattern Recognition Theory of Mind architecture?
    What can we harvest here from the signals into/out of our body, e.g. From LifeLogs?

  2. hello, I got your web address from a friend of yours, I am a social psychology PhD student, just saw your symposium call – could I please be included in the symposium? I am doing grounded theory research on cognition-physics interconnectedness, mapping cognition from the core drive to interaction and culture, working with a psychodynamic model I have developed while working with clients and doing my doctoral thesis.
    Right now I am working on contacting fellow academics to do a computational, visualization, modeling project after the mathematical basics have been published,
    http://worldsciencepublisher.org/journals/index.php/ALSA/article/view/956/745
    and I am really interested in the topic of the symposium, as the construct of the self have emerged in the model and is the part of a seven-step modeling structure (please see more on intelligentphysics.com or mindchocolate.com)
    I have a paper on psychotecture if interested http://mindchocolate.co.uk/controls-of-the-cognitive-drive-c-algorithms-psychotecture
    os

  3. We all want to believe there is something magical in our brains (strange loop, quantum computing, blackholes, qualia…) and we are so afraid there isn’t. Most who serach for machine consciousness are afraid to find it.

    • There is nothing “magical” about a single loop other than the fact that is non-linear. Branch it twice before it feeds back into itself and it is a complex and unsolvable as the three-body gravitational problem (still without being “magical” except in terms of its perceived respects). The “magic” in our brains is all in the perception and it *can’t* be removed because it is literally impossible for something to simulate itself (or anything else of equivalent Kolomogorov complexity) particularly when it contains black boxes that are not accessible to it and particularly when it is constantly changing and growing more complex with every passing instant. Creating the “magic” is not impossible (we should be able to do it in the reasonably near future) — it is the fact that, once created, absolutely guaranteed CONTROL/SAFETY is an insurmountable problem (i.e. literal impossibility).


Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s

%d bloggers like this: