Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Artificial neural networks are used to model systems that receive inputs and produce outputs. The relationships between the inputs and outputs and the representation parameters are critical issues in the design of related engineering systems, and sensitivity analysis concerns methods for analyzing these relationships. Perturbations of neural networks are caused by machine imprecision, and they can be simulated by embedding disturbances in the original inputs or connection weights, allowing us to study the characteristics of a function under small perturbations of its parameters. This is the first book to present a systematic description of sensitivity analysis methods for artificial neural networks. It covers sensitivity analysis of multilayer perceptron neural networks and radial basis function neural networks, two widely used models in the machine learning field. The authors examine the applications of such analysis in tasks such as feature selection, sample reduction, and network optimization. The book will be useful for engineers applying neural network sensitivity analysis to solve practical problems, and for researchers interested in foundational problems in neural networks.

Neural networks (Computer science). --- Sensitivity theory (Mathematics). --- Neural networks (Computer science) --- Sensitivity theory (Mathematics) --- Mechanical Engineering --- Engineering & Applied Sciences --- Computer Science --- Mechanical Engineering - General --- Information Technology --- Artificial Intelligence --- Neural circuitry. --- Circuitry, Neural --- Circuits, Neural --- Nerve net --- Nerve network --- Neural circuits --- Neurocircuitry --- Neuronal circuitry --- Artificial neural networks --- Nets, Neural (Computer science) --- Networks, Neural (Computer science) --- Neural nets (Computer science) --- Computer science. --- Artificial intelligence. --- Computer simulation. --- Pattern recognition. --- Statistical physics. --- Dynamical systems. --- Engineering design. --- Control engineering. --- Robotics. --- Mechatronics. --- Computer Science. --- Artificial Intelligence (incl. Robotics). --- Control, Robotics, Mechatronics. --- Statistical Physics, Dynamical Systems and Complexity. --- Pattern Recognition. --- Simulation and Modeling. --- Engineering Design. --- Mechanical engineering --- Microelectronics --- Microelectromechanical systems --- Automation --- Machine theory --- Control engineering --- Control equipment --- Control theory --- Engineering instruments --- Programmable controllers --- Design, Engineering --- Engineering --- Industrial design --- Strains and stresses --- Dynamical systems --- Kinetics --- Mathematics --- Mechanics, Analytic --- Force and energy --- Mechanics --- Physics --- Statics --- Mathematical statistics --- Design perception --- Pattern recognition --- Form perception --- Perception --- Figure-ground perception --- Computer modeling --- Computer models --- Modeling, Computer --- Models, Computer --- Simulation, Computer --- Electromechanical analogies --- Mathematical models --- Simulation methods --- Model-integrated computing --- AI (Artificial intelligence) --- Artificial thinking --- Electronic brains --- Intellectronics --- Intelligence, Artificial --- Intelligent machines --- Machine intelligence --- Thinking, Artificial --- Bionics --- Cognitive science --- Digital computer simulation --- Electronic data processing --- Logic machines --- Self-organizing systems --- Fifth generation computers --- Neural computers --- Informatics --- Science --- Design --- Statistical methods --- Electrophysiology --- Nervous system --- Neural networks (Neurobiology) --- Reflexes --- Artificial intelligence --- Natural computation --- Soft computing --- Optical pattern recognition. --- Artificial Intelligence. --- Complex Systems. --- Optical data processing --- Pattern perception --- Perceptrons --- Visual discrimination --- Automation. --- System theory. --- Pattern recognition systems. --- Control, Robotics, Automation. --- Automated Pattern Recognition. --- Computer Modelling. --- Pattern classification systems --- Pattern recognition computers --- Computer vision --- Systems, Theory of --- Systems science --- Automatic factories --- Automatic production --- Computer control --- Engineering cybernetics --- Factories --- Industrial engineering --- Mechanization --- Assembly-line methods --- Automatic control --- Automatic machinery --- CAD/CAM systems --- Robotics --- Philosophy

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Case-based reasoning. --- Soft computing.

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Artificial neural networks are used to model systems that receive inputs and produce outputs. The relationships between the inputs and outputs and the representation parameters are critical issues in the design of related engineering systems, and sensitivity analysis concerns methods for analyzing these relationships. Perturbations of neural networks are caused by machine imprecision, and they can be simulated by embedding disturbances in the original inputs or connection weights, allowing us to study the characteristics of a function under small perturbations of its parameters. This is the first book to present a systematic description of sensitivity analysis methods for artificial neural networks. It covers sensitivity analysis of multilayer perceptron neural networks and radial basis function neural networks, two widely used models in the machine learning field. The authors examine the applications of such analysis in tasks such as feature selection, sample reduction, and network optimization. The book will be useful for engineers applying neural network sensitivity analysis to solve practical problems, and for researchers interested in foundational problems in neural networks.

Discrete mathematics --- Mathematical statistics --- Mathematics --- Classical mechanics. Field theory --- Statistical physics --- Materials sciences --- Electrical engineering --- Applied physical engineering --- Engineering sciences. Technology --- Production management --- Artificial intelligence. Robotics. Simulation. Graphics --- patroonherkenning --- factoranalyse --- mechatronica --- superclaus proces --- grafentheorie --- DFMA (design for manufacture and assembly) --- industriële robots --- vormgeving --- automatisering --- statistiek --- mineralen (chemie) --- simulaties --- mijnbouw --- KI (kunstmatige intelligentie) --- fysica --- robots --- dynamica --- automatische regeltechniek

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Artificial neural networks are used to model systems that receive inputs and produce outputs. The relationships between the inputs and outputs and the representation parameters are critical issues in the design of related engineering systems, and sensitivity analysis concerns methods for analyzing these relationships. Perturbations of neural networks are caused by machine imprecision, and they can be simulated by embedding disturbances in the original inputs or connection weights, allowing us to study the characteristics of a function under small perturbations of its parameters. This is the first book to present a systematic description of sensitivity analysis methods for artificial neural networks. It covers sensitivity analysis of multilayer perceptron neural networks and radial basis function neural networks, two widely used models in the machine learning field. The authors examine the applications of such analysis in tasks such as feature selection, sample reduction, and network optimization. The book will be useful for engineers applying neural network sensitivity analysis to solve practical problems, and for researchers interested in foundational problems in neural networks.

Discrete mathematics --- Mathematical statistics --- Mathematics --- Classical mechanics. Field theory --- Statistical physics --- Materials sciences --- Electrical engineering --- Applied physical engineering --- Engineering sciences. Technology --- Production management --- Artificial intelligence. Robotics. Simulation. Graphics --- patroonherkenning --- factoranalyse --- mechatronica --- superclaus proces --- grafentheorie --- DFMA (design for manufacture and assembly) --- industriële robots --- vormgeving --- automatisering --- statistiek --- mineralen (chemie) --- simulaties --- mijnbouw --- KI (kunstmatige intelligentie) --- fysica --- robots --- dynamica --- automatische regeltechniek