↓ Skip to main content
  1. Artificial General Intelligence/

Requirements and Properties

Author
Tom Rochette
Table of Contents

Learned in this study
#

Things to explore
#

Overview
#

  • Computation/Processing
  • Memory
    • Storage
      • Compression
    • Retrieval

Things it should do
#

  • Improve algorithms
    • Receive an existing algorithm and be able to determine its purpose. With that in mind, optimize the algorithm so it is maximally efficient in both time and space
    • Learn which data structure is the most appropriate for a problem
      • Inspect code and be able to figure out if the current data structure is the best one for its current use
  • Improve data structures

Important properties
#

  • Signal filtering (ignore non-essential data to reduce the domain size)
  • Abstraction/simplification/class generation. Learn to group similar stimuli so that you do not have to learn about each of them individually.
  • It should be constructive: modifying or adding new features should not require that its database be flushed/reset.