Neuron-adaptive higher order neural-network models for automated financial data modeling.

Neuron-adaptive higher order neural-network models for automated financial data modeling. Research Abstract Details 

Research Abstract Table of Contents

Jump to the:

Neuron-adaptive higher order neural-network models for automated financial data modeling. Abstract Text:

Ming Zhang,Shuxiang Xu,J Fulcher,

Real-world financial data is often nonlinear, comprises high-frequency multipolynomial components, and is discontinuous (piecewise continuous). Not surprisingly, it is hard to model such data. Classical neural networks are unable to automatically determine the optimum model and appropriate order for financial data approximation. We address this problem by developing neuron-adaptive higher order neural-network (NAHONN) models. After introducing one-dimensional (1-D), two-dimensional (2-D), and n-dimensional NAHONN models, we present an appropriate learning algorithm. Network convergence and the universal approximation capability of NAHONNs are also established. NAHONN Group models (NAHONGs) are also introduced. Both NAHONNs and NAHONGs are shown to be "open box" and as such are more acceptable to financial experts than classical (closed box) neural networks. These models are further shown to be capable of automatically finding not only the optimum model, but also the appropriate order for specific financial data.

Neuron-adaptive higher order neural-network models for automated financial data modeling. Publishing Authors By Initials

M Zhang,S Xu,J Fulcher,

For similar abstracts research abstracts see: abstracts research

PUBMED ID PMID:

MEDLINE DATE:

Neuron-adaptive higher order neural-network models for automated financial data modeling. Journal Published:

PUBLICATION TYPE: Journal Article

Journal: IEEE transactions on neural networks / a publicati

VOLUME: 13

Page Numbers: 188-204

Journal Abbreviation:

ISSN: 1045-9227

DAY: 4

MONTH: 02

YEAR: 2002

Neuron-adaptive higher order neural-network models for automated financial data modeling. Information

Number of References:

LANGUAGE: eng

NlmUniqueID: 101211035

Neuron-adaptive higher order neural-network models for automated financial data modeling. Keywords Mesh Terms:

KEYWORDS:

MESH TERMS:

Chemical & Substance for Abstract: Neuron-adaptive higher order neural-network models for automated financial data modeling. Information

Substance Name:

Registry Number:

Grant and Affiliation Information for Neuron-adaptive higher order neural-network models for automated financial data modeling.

AFFILIATION: Dept. of Phys., Comput. Sci. and Eng., Newport Univ., Newport News, VA.

Country: United States

AGENCY:

GRANT:

ACRONYM:

MEDLINETA: IEEE Trans Neural Netw

REFSOURCE:

DATABASENAME:

ACCESSION NUMBER:

Number Hits: 0

Neuron-adaptive higher order neural-network models for automated financial data modeling Related Publications

• B-cell maturation defects in common variable immunodeficiency and association with clinical features.
• Carboplatin desensitization.
• Cognition, continence and transfer status at the time of discharge from an acute hospital setting and their associations with an unfavourable discharge outcome after stroke.
• Cranioplasty; a technic with tantalum.
• Drug-induced thyroiditis and papillary carcinoma in a minocycline-pigmented black thyroid gland.
• Face recognition using artificial neural network group-based adaptive tolerance (GAT) trees.
• Improved apparatus for skeletal traction of the cervical spine.
• Leiomyosarcoma of the urinary bladder.
• Neuron-adaptive higher order neural-network models for automated financial data modeling.
• The motherhood choice: A decision aid for women with multiple sclerosis.
• The motherhood choice: Themes arising in the decision-making process for women with multiple sclerosis.
• The use of smart tokens to permit the secure, remote access of electronic health records.
• Visual outcomes and graft survival following corneal transplants: the need for an Irish National Corneal Transplant Registry.