| ™ |
Tom Veatch
Flames of inspiration often leave smoke signals behind.From mine, these.
| Cognitive Simplification | The requirements of survival and reproduction impose logical structure onto evolved systems. Therefore the study of logical systems, cognitive science, is an essential layer in the study of biological systems. |
| Cognitive Science within Biology | as an epistemological layer imposed by evolution |
| Human Evolution | Logic constrains biology, biology constrains us, and yet we think and speak and feel. How did we get here, then, and what parts came in what order? This was a lot of fun to write. Includes Tautology, and Cognitive Biology, and Conceptual Archeology. |
| Foundations of Future AI | Towards a New Cognitive Science |
| N+V Humor Theory | Veatch's 1998 "A Theory of Humor" |
| The Logic of Irrational Emotion | Emotion in general, considered evolutionarily and logically. Mathematical notation for the emotional process. Review of N+V Humor Theory using it. Veatch asserts that the process of identifying yourself with an emotionally significant circumstance or role has a binding function whereby the emotional system is bound or required to implement the specific emotion that the system associates with that circumstance or role. That is, identification binds emotion. From this, much follows. Bound, a person harmonizes with others in shared understanding, moral assessment, and feeling, around a shared activity. Bound, a person is not free to experience the moment, the now, the timeless flow, but is instead aware of their status and moral self-assessment. Unbound, wherein identification does not occur, emotional flow states, high performance, spiritual goodness, etc., occur with attention paid to the evolving situation rather than to thinking about how it reflects upon you and tells a story about you. Unbound, the person has access to the unconditioned or irrational emotions of bliss, serenity, transcendence, etc. Veatch's Razor, distinguishing these, is given. |
| Math as Language | Underlying intuition reads out as discrete expression. |
| Robot Emotion | On the design of emotional systems for humans and robots. Motivational frames and their relative priorities. Metrics to guide reinforcement learning. |
| Borges | On the Crease of Logic |
| Logic from Space | A solution to the Crease of Logic. |
| Emotional Merger | Emotional change involves the reassessment of circumstances; a process that must come to include new details within the focus of attention, as well as to exclude now-irrelevant aspects of what had previously been focussed. I clarify and define emotional merger and specification as fundamental cognitive/emotional processes in this theoretical essay, which seems to have as great a significance in the cognitive architecture of emotion as humor theory. |
| Synthetic Perception | Examples include image merger, color qualia, rhythm, object coherence, and stereoscopic movement as object learning. |
| Gesture Learning | How to learn effective physical movement. A research program for reinforcement learning by embodied systems, like people. |
| A More General Theory of the Syllogism | Abstracting logic. Aristotle's
list of syllogisms missed half of them; there's nothing to them
(H!); and we can do better
without. Still it is pretty fun and cool, considering this was the intellectual pinnacle of humanity for 2000 years, and plus I'd say this is not a bad introduction to "term logic", and might be suggested reading for students of computer science, philosophy, classics, and/or math. |
| Evolutionary/Functional/Logical Decomposition | of the elements of Language |
| Neural Networks + Fuzzy Logic + Space | A careful, accessible introduction to neural networks
assuming only high school algebra and a little geometry and
differentiation. NNs are defined mathematically, along with how to
run them, how to train them (by the usual gradient descent), how
to train them better (so I suppose: using 'Newton-Raphson', which
really ought to kill!). I also discuss how to understand the
training algorithm's implicit reasoning about the adjustments it
decides to make; I share an interpretation that backpropagation is
like an Anti-Dunning-Kruger learning system (and therefore morally
superior to most men?). Then I give a whole Fuzzy Logic
re-interpretation of NNs, along with suggestions on how to enhance
their logical reasoning capabilities. I tried the wikipedia page,
and got so frustrated I wrote my own introduction. So yes, I
suggest reading this if you want to really understand neural
networks, and if your other resources have made it seem
inscrutable. It's a few pages of actual math, yes, but all the
steps are laid out: no leaps! It's not short, but you don't have to be
a math major to follow along. I encourage your
study here if you are interested in really knowing how neural
nets work. Also this adds Fuzzy Logic to neural networks, including how to train them. Finally this goes into Space Representing Neural Networks so robots can represent space, or humans' representation of space can be understood better. Three months of work is in here. |
| RSS for updates |
|