Making Minds, Part 3

In the last part of this series I listed the main reasons I'd love to try and make a Mind. In this part I list some of the features I'd like a Mind to have.

What kind of features would I like a Mind to have?

How about:

• ability to remember things
• ability to model the environment, including itself
• a values system that assigns goodness/badness to various states
• the ability to be encoded digitally for copying/transmission purposes
• hardware independence so the "brain" can be upgraded
• high resolution self-introspection (so the mind can see exactly how it works)
• ability to communicate internal state (bored, happy, frustrated, etc.)
• ability to allocate internal resources effectively (focus of attention)
• ability to resolve constraints (pattern recognition)
• ability to edit itself
• rigorous deduction/inductive reasoning
• understanding of probabilities
• supports multiple data input streams and output streams (audio, video, etc.)
• plugin architecture to accomodate new I/O streams
• partitioning (ability to focus on several things at the same time)

I'm sure I'll think of more features over the next few weeks that I'll add to this list, but I think it's a good start.

The Human brain has some of these features but is unfortunately lacking in some key areas such as the ability to be copied, hardware independence, rigorous reasoning (in most cases), and understanding of probabilities. The book Kluge goes into plenty of detail about the various weaknesses of the Human brain, and I highly recommend it.

Comments

[jeremy]

love this series, keep it up!