RAMnets
≈ 2 min read
Names in other languages
No names in other languages are held for this entry yet.
Article bodies are English and are not machine-translated. A name in another language is not a translation of the article.
RAMnets is one of the oldest practical neurally inspired classification algorithms. The RAMnets is also known as a type of "n-tuple recognition method" or "weightless neural network".
RAMnets is one of the oldest practical neurally inspired classification algorithms. The RAMnets is also known as a type of "n-tuple recognition method" or "weightless neural network".
Algorithm
Consider (let us say N) sets of n distinct bit locations are selected randomly. These are the n-tuples. The restriction of a pattern to an n-tuple can be regarded as an n-bit number which, together with the identity of the n-tuple, constitutes a `feature' of the pattern. The standard n-tuple recognizer operates simply as follows: A pattern is classified as belonging to the class for which it has the most features in common with at least one training pattern of that class.
This is the \Theta = 0 case of a more general rule whereby the class assigned to unclassified pattern u is \begin{align} \underset{c}argmax(\sum_{i=1}^N\Theta(\sum_{v\in D_{c}}\delta(\alpha_{i}(u),\alpha_{i}(v))))\end{align} where D c is the set of training patterns in class c, \Theta(x) = x for 0\leq x\leq \theta , \Theta(x)=\theta for x\geq\theta , \delta_{i,j} is the Kronecker delta( \delta_{i,j} =1 if i=j and 0 otherwise.)and (\alpha_{i}(u)) is the i th feature of the pattern u: \sum_{j=0}^{n-1}u_\eta i(j)2^{j} Here u k is the k th bit of u and u_\eta i (j) is the j th bit location of the i th n-tuple.
With C classes to distinguish, the system can be implemented as a network of NC nodes, each of which is a random access memory (RAM); hence the term RAMnet. The memory content m_{ci\alpha} at address \alpha of the i th node allocated to class c is set to m_{ci\alpha} = \Theta(\sum_{v\in D_{c}}\delta(\alpha,\alpha_{i}(v))) In the usual \theta = 1 case, the 1-bit content of m_{ci\alpha} is set if any pattern of D c has feature \alpha and unset otherwise.
Recognition is accomplished by summing the contents of the nodes of each class at the addresses given by the features of the unclassified pattern. That is, pattern u is assigned to class \begin{align} \underset{c}argmax(\sum_{i=1}^N m_{ci\alpha}(u)) \end{align}
Further reading
An introductory tutorial to classifiers (introducing the basic terms, with numeric example)
Text derived from https://en.wikipedia.org/w/index.php?oldid=1345666064 under CC BY-SA 4.0; modifications have been made.