A Study on Associative Neural Memories

@article{Prasad2010ASO,
  title={A Study on Associative Neural Memories},
  author={Binod Prasad and P. E. S. N. Krishna Prasad and Sagar Yeruva and Pilla Sita Rama Murty},
  journal={International Journal of Advanced Computer Science and Applications},
  year={2010},
  volume={1}
}
Memory plays a major role in Artificial Neural Networks. Without memory, Neural Network can not be learned itself. One of the primary concepts of memory in neural networks is Associative neural memories. A survey has been made on associative neural memories such as Simple associative memories (SAM), Dynamic associative memories (DAM), Bidirectional Associative memories (BAM), Hopfield memories, Context Sensitive Auto-associative memories (CSAM) and so on. These memories can be applied in… 

Figures from this paper

On subspace projection autoassociative memories based on linear support vector regression

A novel class of SPAM models obtained by considering linear support vector regression (SVR) is presented, based on primal, dual, and bi-level formulations of the linear e-support vector regression.

Performance Evaluation of Password Authentication using Associative Neural Memory Models

This paper proposed performance analysis of password authentication schemes using Associative memories and CSAM using graphical Images shows that in comparison to existing layered and associative neural network techniques for graphical images as password, the CSAM method provides better accuracy and quicker response time to registration and password changes.

Holographic memory-based Bayesian optimization algorithm (HM-BOA) in dynamic environments

This paper presents a new evolutionary dynamic optimization algorithm, holographic memory-based Bayesian optimization algorithm (HM-BOA), whose objective is to address the weaknesses of sequential

Design of a Data Error Correction System Based on Associative Memory

A new method is suggested to guarantee 100% accuracy in correct one more bits of the erring messages and the obtained results proved that the proposed method can reach the goal with simple design for the system.

A PERFORMANCE STUDY

This work considers the disease asthma for diagnosis and chooses some machine learning algorithms such as Context sensitive auto-associative memory neural network model, Backpropogation model, C4.5 algorithm, Bayesian Network, Particle Swarm Optimization to design the expert system for diagnosis.

A Novel Approach for Password Authentication Using Bidirectional Associative Memory

Test results show that converting user password in to Probabilistic values and giving them as input for BAM improves the security of the system.

Password Authentication Using Context-Sensitive Associative Memory Neural Networks: A Novel Approach

This paper focuses on the verification table approach, which has significant drawbacks and storing passwords in password table is one of the drawbacks.

AN APPROACH TO DEVELOP EXPERT SYSTEMS IN MEDICAL DIAGNOSIS USING MACHINE LEARNING ALGORITHMS (A STHMA ) AND A PERFORMANCE STUDY

This work considers the disease asthma for diagnosis and chooses some machine learning algorithms such as Context sensitive auto-associative memory neural network model, Backpropogation model, C4.5 algorithm, Bayesian Network, Particle Swarm Optimization to design the expert system for diagnosis.

A Novel Approach for Authenticating Textual or Graphical Passwords Using Hopfield Neural Network

This study proposes the use of a Hopfield neural network technique for password authentication, in comparison to existing layered neural network techniques, which provides better accuracy and quicker response time to registration and password changes.

References

SHOWING 1-10 OF 43 REFERENCES

Context-sensitive associative memory: 'residual excitation' in neural networks as the mechanism of STM and mental set

  • V. Eliashberg
  • Psychology, Biology
    International 1989 Joint Conference on Neural Networks
  • 1989
A model illustrating the E-state concept can be represented naturally in neural models by introducing states of residual excitation (E-states) in the neural elements.

Context-dependent associations in linear distributed memories.

  • E. Mizraji
  • Biology, Computer Science
    Bulletin of mathematical biology
  • 1989

Fuzzy Decisions in Modular Neural Networks

Results of semantic evaluations in several self-referential systems including modal versions of the chaotic liar, antagonistic decisions and extended dilemmas are analyzed to shed some light on the modeling of cognitive decisions.

Hippocampal auto-associative memory

  • N. P. Fougier
  • Psychology, Computer Science
    IJCNN'01. International Joint Conference on Neural Networks. Proceedings (Cat. No.01CH37222)
  • 2001
This work presents a model of auto-associative memory based on 4 distinct structures (EC, DG, CA3 and CA1) where information is processed along a loop at three distinct levels and has been tested successfully on a real robot.

BI DIRECTIONAL ASSOCIATIVE MEMORY NEURAL NETWORK METHOD IN THE CHARACTER RECOGNITION

This work will analyze different neural network methods in pattern recognition, which deals with recognition of optically processed patterns rather then magnetically processed ones.

Associative Memories in Medical Diagnostic

The main result is that the proposed neural network allows not only to find a solution in some cases, but also to suggest to obtain more clinical data if the data available is insufficient to conclude.

Phrase detection and the associative memory neural network

  • R. C. Murphy
  • Computer Science
    Proceedings of the International Joint Conference on Neural Networks, 2003.
  • 2003
This paper describes the use of a novel associative memory neural network architecture to perform unsupervised phrase detection in a large, unstructured, English text corpus. To significantly

An Introduction To Neural Networks

An Introduction to Neural Networks falls into a new ecological niche for texts aimed at cognitive science and neuroscience students who need to understand brain function in terms of computational modeling, and at engineers who want to go beyond formal algorithms to applications and computing strategies.