【DAILY READING】Neural networks and physical systems with emergent collective computational abilities

Conclusion By Myself

Aha, totally not understandable for me. This paper was published at 1982, and it was said as the original paper of RNN. So of this, I read it. But the knowledge it introduced and the way of its description are so strange for me, and I can not see any sign about RNN in it. Instead, I think it is may about the ensemble learning? I don’t know. Well, let’s forget it. But there is not no any gain for me, I read this paper without dictionary almost, and also without any break through I read. It will give me so many confidence on my following readings.

Abstract

Computational properties of use to biological organisms or to the construction of computers can emerge as collective properties of systems having a large number of simple equivalent components (or neurons). The physical meaning of content-addressable memory is described by an appropriate phase space flow of the state of a system. A model of such a system is given, based on aspects of neurobiology but readily adapted to integrated circuits. The collective properties of this model produce a content-addressable memory which correctly yields an entire memory from any subpart of sufficient size. The algorithm for the time evolution of the state of the system is based on asynchronous parallel processing. Additional emergent collective properties include some capacity for generalization, familiarity recognition, categorization, error correction, and time sequence retention. The collective properties are only weakly sensitive to details of the modeling or the failure of individual devices.

Key Points By AI

• Computational properties of use to biological organisms or to the construction of computers can emerge as collective properties of system - having a large number of simple equivalent components
• In physical systems made from a large number of simple elements, interactions among large numbers of elements yield collective phenomena such as the stable magnetic orientations and domains in a magnetic system or the vortex patterns in fluid flow
• The neural of the emergent collective properties is insensitive to the details inserted in the model
• Some capacity for generalization is present, and time ordering of memories can be encoded. These properties follow from the nature of the flow in phase space produced by the processing algorithm, which does not appear to be strongly dependent on precise details of the modeling

File

Neural networks and physical systems with emergent collective computational abilities.