Sparse distributed memory: Difference between revisions

Revision as of 22:26, 27 February 2023

Revision as of 22:29, 27 February 2023

Line 64:

===As neural network===

The SDM may be regarded either as a [[content-addressable memory|content-addressable]] extension of a classical [[random-access memory]] (RAM) or as a special type of three layer [[feedforward neural network]]. The main SDM alterations to the RAM are:<ref name="Grebenıcek">Grebenıcek, František. Neural Nets as Associative Memories. Diss. Brno University of Technology, 2001. URL: http://www.vutium.vutbr.cz/tituly/pdf/ukazka/80-214-1914-8.pdf</ref>

*The SDM calculates [[Hamming distance]]s between the reference address and each ___location address. For each distance which is less or equal to the given radius the corresponding ___location is selected.

Line 277:

* [[Autoassociative memory]]

* [[Cerebellar model articulation controller]]

* [[Types of artificial neural networks#Dynamic memory networks|Dynamic memory networks]]

* [[Content-addressable memory]]

* [[Types of artificial neural networks#Dynamic memory networks]]

* [[Feedforward neural network]]

* [[Hierarchical temporal memory]]

* [[Holographic associative memory]]