Bidirectional Associative Memory

Bidirectional associative memory (BAM) proposed by Kosko is a recurrent heteroassociative memory consisting of two layers (Figure 2). It is considered an extension of a Hopfield network, and performs recurrent autoassociations as well as heteroassociations on the stored memories.

The network is trained by interactions of two layers. The input x of x layer is processed and transferred the output of Y layer:

Y layer

X layer x1 x2 Figure 2 Diagram of a BAM.

n where a(.) is a threshold function and Wis a weight vector. Vector y of Y layer feeds to the X layer and produces output x:

and x then feeds into the input of Y layer in turn and producesy" using eqn [3]. The learning process continues until further updates of x and y stop.

A BAM can further be generalized to enable multiple associations (xk, yl,z, ...), k = 1, 2...,p., This is called multidirectional associative memory.

Trash To Cash

Trash To Cash

This book will surely change your life due to the fact that after reading this book and following through with the steps that are laid out for you in a clear and concise form you will be earning as much as several thousand extra dollars a month,  as you can see by the cover of the book we will be discussing how you can make cash for what is considered trash by many people, these are items that have value to many people that can be sold and help people who need these items most.

Get My Free Ebook


Post a comment