Abstract
Recent artificial higher order neural network research has focused on simple models, but such models have not been very successful in describing complex systems (such as face recognition). This chapter presents the artificial higher order neural network group-based adaptive tolerance (HONNGAT) tree model for translation-invariant face recognition. Moreover, face perception classification, detection of front faces with glasses and/or beards models of using HONNGAT trees are presented. The artificial higher order neural network group-based adaptive tolerance tree model is an open box model and can be used to describe complex systems.
TopArtificial Higher Order Neural Network Sets
A set (Waerden, 1970) is defined as a collection of elements which possess the same properties. The symbola ∈ A (12 – 1)means: A is a set, and a is an element of set A.
The artificial higher order neural network set is a set in which every element is an HONN. The symbolhonn ∈HONNS (where: honn = f:Rn →Rm) (12 - 2)means: HONNS is an HONN set, and honn, which is one kind of artificial higher order neural network, is an element of set HONNS. The domain of the artificial higher order neural network honn inputs is the n-dimensional real number Rn. Likewise, the honn outputs belong to the m-dimensional real number Rm. The neural network function f is a mapping from the inputs of honn to its outputs.
Key Terms in this Chapter
GAT: Group-based adaptive tolerance tree.
THONNG: Artificial trigonometric higher order neural network group.
HONN*: Product HONN sets.
UCSHONN: Artificial ultra-high frequency trigonometric higher order neural network.
PHONN: Artificial polynomial higher order neural network.
HONN: Artificial higher order neural network.
SPHONN: Artificial sigmoid polynomial higher order neural network.
SSINCHONN: Artificial sine and SINC higher order neural network.
HONNG: Artificial higher order neural network group.
HONN+: Additive HONN sets.
PHONNG: Artificial polynomial higher order neural network group.
HONNGAT: Artificial higher order neural network group-based adaptive tolerance tree.
SINCHONN: Artificial SINC higher order neural network.
SPHONNG: Artificial sigmoid polynomial higher order neural network group.
HONNS: Artificial higher order neural network set.
THONN: Artificial trigonometric higher order neural network.
HONNGS: Artificial higher order neural network grnrtslised set.