A.: Building Grounding Abstractions for Artificial Intelligence Programming (2001)
Abstract:
Most Artificial Intelligence (AI) work can be characterized as either “high-level” (e.g., logical, symbolic) or “low-level ” (e.g., connectionist, behavior-based robotics). Each approach suffers from particular drawbacks. High-level AI uses abstractions that often have no relation to the way real, biological brains work. Low-level AI, on the other hand, tends to lack the powerful abstractions that are needed to express complex structures and relationships. I have tried to combine the best features of both approaches, by building a set of programming abstractions defined in terms of simple, biologically plausible components. At the “ground level”, I define a primitive, perceptron-like computational unit. I then show how more abstract computational units may be implemented in terms of the primitive units, and show the utility of the abstract units in sample networks. The new units make it possible to build networks using concepts such
Citations
| 86 | High-level Vision – Ullman - 1996 |
| 68 | Enabling Agents to work Together – Guha, Lenat - 1994 |
| 44 | Reactivation of hippocampal ensemble memories during sleep – Wilson, McNaughton - 1994 |
| 43 | Cambrian Intelligence – Brooks - 1999 |
| 38 | Memory in the Cerebral Cortex – Fuster - 1995 |
| 16 | A logical calculus of the ideas immanent in nervous activity – McCullough, Pitts - 1943 |
| 7 | Computation: Finite and infinite machines. Englewood Cliffs: Prentice--Hall – Minsky - 1967 |
| 3 | Expanded Edition – Perceptrons - 1988 |
| 1 | Evolving the Mind – Cairns-Smith - 1996 |
| 1 | et al. “What the Frog’s Eye Tells the Frog’s Brain – Lettvin - 1959 |
| 1 | a Theory of Memory – “K-lines - 1980 |
| 1 | vs. Analogical or Symbolic vs. Connectionist or Neat vs. Scruffy – “Logical - 1990 |
| 1 | Zatocoding and Developments – Mooers - 1956 |
| 1 | eds. “Four reviews of The Society of Mind and a response.” Artificial Intelligence 48 – Stefik, Smoliar - 1991 |
