Crossroads The ACM Magazine for Students

Sign In

Association for Computing Machinery

Articles Tagged: Modeling methodologies

Articles & Features

Storage capacity comparison of neural network models for memory recall

The physiology of how the human brain recalls memories is not well understood. Neural networks have been used in an attempt to model this process.

Two types of networks have been used in several models of temporal sequence memory for simple sequences of randomly generated and also of structured patterns: auto- and hetero-associative networks. Previous work has shown that a model with coupled auto- and hetero-associative continuous attractor networks can robustly recall learned simple sequences. In this paper, we compare Hebbian learning and pseudo-inverse learning in a model for recalling temporal sequences in terms of their storage capacities. The pseudo-inverse learning method is shown to have a much higher storage capacity, making the new network model 700% more efficient by reducing calculations.

By Kate Patterson, December 2007

PDF | HTML | In the Digital Library

Modeling protein dependency networks using CoCoA

In an interdisciplinary effort to model protein dependency networks, biologists measure signals from certain proteins within cells over a given interval of time. Using this time series data, the goal is to deduce protein dependency relationships. The mathematical challenges is to statistically measure correlations between given proteins over time in order to conjecture probable relationships. Biologists can then consider these relationships with more scrutiny, in order to confirm their conjectures. One algorithm for finding such relationships makes use of interpolation of the data to produce next-state functions for each protein and the Deegan-Packel Index of Power voting method to measure the strength of correlations between pairs of proteins. The algorithm was previously implemented, but limitations associated with the original language required the algorithm to be re-implemented in a more computationally efficient language. Because of the algebraic focus of the Computational Commutative Algebra language, or CoCoA, the algorithm was re-implemented in this language, and results have been produced much more efficiently. In this paper I discuss the algorithm, the CoCoA language, the implementation of the algorithm in CoCoA, and the quality of the results.

By Grey Ballard, September 2006

PDF | HTML | In the Digital Library