Correlation matrix memories : improving performance for capacity and generalisation
نویسنده
چکیده
The human brain is an extremely powerful pattern recogniser, as well as being capable of displaying amazing feats of memory. It is clear that human memory is associative; we recall information by associating items together so that one may be used to recall another. This model of memory, where items are associated as pairs rather than stored at a particular location, can be used to implement computer memories which display powerful properties such as robustness to noise, a high storage capacity and the ability to generalise. One example of such a memory is the Binary Correlation Matrix Memory (CMM), which in addition to the previously listed properties is capable of operating extremely quickly in both learning and recall, as well as being well suited for hardware implementation. These memories have been used as elements of larger pattern recognition architectures, solving problems such as object recognition, text recognition and rule chaining, with the memories being used to store rules. Clearly, the performance of the memories is a large factor in the performance of such architectures. This thesis presents a discussion of the issues involved with optimising the performance of CMMs in the context of larger architectures. Two architectures are examined in some detail, which motivates a desire to improve the storage capacity and generalisation capability of the memories. The issues surrounding the optimisation of storage capacity of CMMs are discussed, and a method for improving the capacity is presented. Additionally, while CMMs are able to generalise, this capability is often ignored. A method for producing codes suitable for storage in a CMM is presented, which provides the ability to react to previously unseen inputs. This potentially adds a powerful new capability to existing architectures.
منابع مشابه
Association between prospective, retrospective memories and job performance of nurses in the city of Ahvaz, Iran, in 2016
Background: Nurses continuously carry out several activities and need to develop certain cognitive mechanisms to be able to concentrate on their tasks. These activities and tasks affect and deal with the health and safety of people and their job performance. This study aims to investigate the association between prospective and retrospective memories and job performance of nurses in Imam Hospit...
متن کاملInformation storage capacity of incompletely connected associative memories
In this paper, the memory capacity of incompletely connected associative memories is investigated. First, the capacity is derived for memories with fixed parameters. Optimization of the parameters yields a maximum capacity between 0.53 and 0.69 for hetero-association and half of it for autoassociation improving previously reported results. The maximum capacity grows with increasing connectivity...
متن کاملHigh capacity recurrent associative memories
Various algorithms for constructing weight matrices for Hopfield-type associative memories are reviewed, including ones with much higher capacity than the basic model. These alternative algorithms either iteratively approximate the projection weight matrix or use simple perceptron learning. An experimental investigation of the performance of networks trained by these algorithms is presented, in...
متن کاملChemical Structure Matching using Correlation Matrix Memories
This paper describes the application of the Relaxation By Elimination (RBE) method to matching the 3D structure of molecules in chemical databases within the frame work of binary correlation matrix memories. The paper illustrates that, when combined with distributed representations, the method maps well onto these networks, allowing high performance implementation in parallel systems. It outlin...
متن کاملExamining significant factors in micro and small enterprises performance: case study in Amhara region, Ethiopia
Furniture manufacturing micro and small enterprises are confronted with several factors that affect their performance. Some enterprises fail to sustain, some others remain for long period of time without transforming, and most are producing similar and non-standard products. The main aim of this manuscript is on improving the performance and contribution of MSEs by analyzing impact of significa...
متن کامل