Philosophy-Consc. - 2

Developing an A.I. robot?:


Program it to cry when it detects something very bad or very good.




Developing a conscious robot?:


Program it to want to cry when it detects something very bad or very good.

Sources and Resources

• Related Background
  • What is it like to be a bat?
    This classic discussion by Thomas Nagel is one of the best known "explanatory devices." It begins to move us away from Turing's flawed (but necessary, at the time) kludge for explaining what consciousness is.

  • The Chinese Room
    A clarifying paper on the Chinese Room Argument, written by John Searle.

  • [pdf] Facing Up to the Problem of Consciousness
    This is an introductory level explanation of consciousness and where we are in dealing with the hard problem of explaining it. It is authored by one of the premier thinkers in the field David Chalmers

  • Time In Three Parts, Temporality

  • "Through Other Eyes" — A short story from a collection of short stories called Nine Hundred Grandmothers by R. A. Lafferty, 1970
    This is a fictional treatment of the concept of first person knowledge (see below).

  
  
  



• Related Glossary Entries

  
  

  • First Person Knowledge

  • Phenomenal Consciousness

  • John Searle

  
  
  
  

Overview

“Certainly, one of the most relevant and obvious characteristics of a present moment is that it goes away, and that characteristic must be represented internally.”

Stated plainly[1], the principle behind multitemporal synapses is that we maintain the blunt “residue” of past lessons in long-term connections, while everything else is quickly forgotten, and learned over again, in the instant. In other words, we re-learn the detailed parts of our responses as we are confronted with each new current situation.[2] One of the primary benefits of applying this principle, in the form of multitemporal synapses, is a neural network construct that is completely free of the usual problems associated with catastrophic forgetting. When you eliminate catastrophic forgetting from your neural network structure, the practical result is the ability to develop networks that continuously learn from their surroundings, just like their natural counterparts.

A Major Problem With Neural Networks

One major challenge with conventional neural network models has been in how to maintain connections that store enough intricate in-the-moment response-details to deal with any contingency that the system may encounter. Conventionally, such details would overwhelm long-term lessons stored in permanent connections-weights. This characteristic of conventional neural network models is known as The Stability Plasticity Problem, and is the underlying cause of "catastrophic forgetting."

When an artificial neural network that has learned a training set of responses, then encounters a new response to be learned, the result is usually ‘catastrophic forgetting’ of all earlier learning. Training on the new detail alters connections that are maintained by the network in a holistic (global) fashion. Because of this, it is almost certain that such a change will radically alter the outputs that were desired for the original training set.