Polynomial Theory of Complex Systems
1971/10/01 by A. G. Ivakhnenko · 37 citations
Computer Science · #Statistical and Computational Modeling #Neural Networks and Applications
paper · doi:10.1109/tsmc.1971.4308320
Abstract
A complex multidimensional decision hypersurface can be approximated by a set of polynomials in the input signals (properties) which contain information about the hypersurface of interest. The hypersurface is usually described by a number of experimental (vector) points and simple functions of their coordinates. The approach taken in this paper to approximating the decision hypersurface, and hence the input-output relationship of a complex system, is to fit a high-degree multinomial to the input properties using a multilayered perceptronlike network structure. Thresholds are employed at each layer in the network to identify those polynomials which best fit into the desired hypersurface. Only the best combinations of the input properties are allowed to pass to succeeding layers, where more complex combinations are formed. Each element in each layer in the network implements a nonlinear function of two inputs. The coefficients of each element are determined by a regression technique which enables each element to approximate the true outputs with minimum mean-square error. The experimental data base is divided into a training and testing set. The training set is used to obtain the element coefficients, and the testing set is used to determine the utility of a given element in the network and to control overfitting of the experimental data. This latter feature is termed "decision regularization.
Cited by
- On Learning to Think: Algorithmic Information Theory for Novel\n Combinations of Reinforcement Learning Controllers and Recurrent Neural World\n Models
- Deep Learning in Neural Networks: An Overview
- One Big Net For Everything
- Astronomia ex machina: a history, primer and outlook on neural networks in astronomy
- Surface roughness inspection by computer vision in turning operations
- Scalable Nonlinear Learning with Adaptive Polynomial Expansions
- Lets keep it simple, Using simple architectures to outperform deeper and\n more complex architectures
- SSFN -- Self Size-estimating Feed-forward Network with Low Complexity, Limited Need for Human Intervention, and Consistent Behaviour across Trials
- A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures
- AI-Powered Social Bots
- Progressive Learning for Systematic Design of Large Neural Networks
- Modelling income, wealth, and expenditure data by use of Econophysics
- Deep Learning in Alzheimer's Disease: Diagnostic Classification and Prognostic Prediction Using Neuroimaging Data. [europepmc]
- Multiparametric quantitative and texture 18 F-FDG PET/CT analysis for primary malignant tumour grade differentiation. [europepmc]
- An Approach towards Increasing Prediction Accuracy for the Recovery of Missing IoT Data Based on the GRNN-SGTM Ensemble. [europepmc]
- Artificial Intelligence Based Methods for Asphaltenes Adsorption by Nanocomposites: Application of Group Method of Data Handling, Least Squares Support Vector Machine, and Artificial Neural Networks. [europepmc]
- Deep learning for early detection of pathological changes in X-ray bone microstructures: case of osteoarthritis. [europepmc]
- On the Evaluation of Rhamnolipid Biosurfactant Adsorption Performance on Amberlite XAD-2 Using Machine Learning Techniques. [europepmc]
- Deep scoping: a breeding strategy to preserve, reintroduce and exploit genetic variation. [europepmc]
- Towards Interpretable Deep Learning: A Feature Selection Framework for Prognostics and Health Management Using Deep Neural Networks. [europepmc]
- Evolving interpretable plasticity for spiking networks. [europepmc]
- Deep learning in macroscopic diffuse optical imaging. [europepmc]
- Modeling of wave run-up by applying integrated models of group method of data handling. [europepmc]
- Modeling the solubility of light hydrocarbon gases and their mixture in brine with machine learning and equations of state. [europepmc]
- Linear leaky-integrate-and-fire neuron model based spiking neural networks and its mapping relationship to deep neural networks. [europepmc]
- Comprehensive Survey of Machine Learning Systems for COVID-19 Detection. [europepmc]
- Examining rheological behavior of CeO 2 -GO-SA/10W40 ternary hybrid nanofluid based on experiments and COMBI/ANN/RSM modeling. [europepmc]
- Air Kerma Calculation in Diagnostic Medical Imaging Devices Using Group Method of Data Handling Network. [europepmc]
- Astronomia ex machina: a history, primer and outlook on neural networks in astronomy. [europepmc]
- Universal closed-tube barcoding for monitoring the shark and ray trade in megadiverse conservation hotspots. [europepmc]
- Modeling construction and demolition waste quantities in Tanta City, Egypt: a synergistic approach of remote sensing, geographic information system, and hybrid fuzzy neural networks. [europepmc]
- Modeling of ionic liquids viscosity via advanced white-box machine learning. [europepmc]
- On the evaluation of surface tension of biodiesel. [europepmc]
- Integrating artificial neural networks, multi-objective metaheuristic optimization, and multi-criteria decision-making for improving MXene-based ionanofluids applicable in PV/T solar systems. [europepmc]
- White-box methodologies for achieving robust correlations in hydrogen storage with metal-organic frameworks. [europepmc]
- Control of medical digital twins with artificial neural networks. [europepmc]
- Generative artificial intelligence: a historical perspective. [europepmc]
Related