Long-term Cognitive Networks for pattern classification
Project description
This package introduces the Long-Term Cognitive Network (LTCN) model for structured pattern classification problems. This recurrent neural network incorporates a quasi-nonlinear reasoning rule that allows controlling the amount of non-linearity in the reasoning mechanism. Furthermore, this neural classifier uses a recurrence-aware decision model that evades the issues posed by the unique fixed point while introducing a deterministic learning algorithm to compute the tunable parameters. The experiments in the original paper show that this classifier obtains competitive results when compared to state-of-the-art white and black-box models.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.