Stability Criteria for Unsupervised Temporal Association Networks

G. Wallis
2005 IEEE Transactions on Neural Networks  
A biologically realizable, unsupervised learning rule is described for the online extraction of object features, suitable for solving a range of object recognition tasks. Alterations to the basic learning rule are proposed which allow the rule to better suit the parameters of a given input space. One negative consequence of such modifications is the potential for learning instability. The criteria for such instability are modeled using digital filtering techniques and predicted regions of
more » ... ity and instability tested. The result is a family of learning rules which can be tailored to the specific environment, improving both convergence times and accuracy over the standard learning rule, while simultaneously insuring learning stability.
doi:10.1109/tnn.2004.841795 pmid:15787138 fatcat:blqvnz3suzcfdkumvr3qjgy7gi