Search Results: 'neural network algorithm'

Search

×
×
×
×
19 results for "neural network algorithm"
Basic Algorithms By Malcolm McLean
eBook (PDF): $2.96
Download immediately.
A massive compendium of computer programming algorithms. Everything is explained from the ground up; from basic stacks, queues and lists, floating point arithmetic and maths functions, through to... More > hash tables, red black trees, compression, complex numbers, the GIF and JPEG file formats, 3D graphics, and up to advanced topics such as Hidden Markov models, neural networks, and fuzzy logic.< Less
Basic Algorithms By Malcolm McLean
Paperback: $32.07
Ships in 3-5 business days
A massive compendium of computer programming algorithms. Everything is explained from the ground up; from basic stacks, queues and lists, floating point arithmetic and maths functions, through to... More > hash tables, red black trees, compression, complex numbers, the GIF and JPEG file formats, 3D graphics, and up to advanced topics such as Hidden Markov models, neural networks, and fuzzy logic.< Less
Basic Algorithms By Malcolm McLean
eBook (ePub): $9.25
Download immediately.
A massive compendium of computer programming algorithms. Everything is explained from the ground up; from basic stacks, queues and lists, floating point arithmetic and maths functions, through to... More > hash tables, red black trees, compression, complex numbers, the GIF and JPEG file formats, 3D graphics, and up to advanced topics such as Hidden Markov models, neural networks, and fuzzy logic.< Less
KB Neural Data Mining: with Python sources By Roberto Bello
eBook (PDF): $0.00
Download immediately.
The aim of this work is to present and describe in detail the algorithms to extract the knowledge hidden inside data using Python language, which allows us to read and easily understand the nature... More > and the characteristics of the rules of the computing utilized, as opposed to what happens in commercial applications, which are available only in the form of running codes, which remain impossible to modify. The algorithms of computing contained within the work, are minutely described, documented and available in the Python source format, and serve to extract the hidden knowledge within the data whether they are textual or numerical kinds. There are also various examples of usage, underlining the characteristics, method of execution and providing comments on the obtained results.< Less
Online Learning of a Neural Fuel Control System for Gaseous Fueled SI Engines By Travis Wiens
eBook (PDF): $0.00
Download immediately.
This PhD dissertation presents a new type of fuel control algorithm for gaseous fuelled vehicles. Gaseous fuels such as hydrogen and natural gas have been shown to be less polluting than liquid... More > fuels, both at the tailpipe and on a total cycle. Unfortunately, it can be expensive to convert vehicles to gaseous fuels. One of major development costs for a new vehicle is the development and calibration of the fuel controller. The research presented here includes a fuel controller which does not require an expensive calibration phase. The controller is based upon a two-part model, using online training of a neural network to model the engine’s steady state characteristics. An experimental test was performed, in which the controller was installed on a truck fuelled by natural gas. The tailpipe emissions of the truck with the new controller showed better results than the OEM controller on both carbon monoxide and nitrogen oxides, and required no calibration and very little information about the engine.< Less
Online Learning of a Neural Fuel Control System for Gaseous Fueled SI Engines By Travis Wiens
Hardcover: $18.83
Ships in 6-8 business days.
This PhD dissertation presents a new type of fuel control algorithm for gaseous fuelled vehicles. Gaseous fuels such as hydrogen and natural gas have been shown to be less polluting than liquid... More > fuels, both at the tailpipe and on a total cycle. Unfortunately, it can be expensive to convert vehicles to gaseous fuels. One of major development costs for a new vehicle is the development and calibration of the fuel controller. The research presented here includes a fuel controller which does not require an expensive calibration phase. The controller is based upon a two-part model, using online training of a neural network to model the engine’s steady state characteristics. An experimental test was performed, in which the controller was installed on a truck fuelled by natural gas. The tailpipe emissions of the truck with the new controller showed better results than the OEM controller on both carbon monoxide and nitrogen oxides, and required no calibration and very little information about the engine.< Less
Probabilistic Models of Phase Variables for Visual Representation and Neural Dynamics By Charles Cadieu
Paperback: $29.50
Ships in 3-5 business days
My work seeks to contribute to three broad goals: predicting the computational representations found in the brain, developing algorithms that help us infer the computations that the brain performs,... More > and producing better statistical models of natural signals. My thesis is broken down into three major chapters that reflect these three goals. Within each chapter I develop novel probabilistic models of phase variables and apply these models to the invariant representation of visual motion, to the inference of connectivity in networks of coupled neural oscillators, and to the development of statistical models of edge structure in images.< Less
Probabilistic Models of Phase Variables for Visual Representation and Neural Dynamics By Charles Cadieu
eBook (PDF): $0.00
Download immediately.
My work seeks to contribute to three broad goals: predicting the computational representations found in the brain, developing algorithms that help us infer the computations that the brain performs,... More > and producing better statistical models of natural signals. My thesis is broken down into three major chapters that reflect these three goals. Within each chapter I develop novel probabilistic models of phase variables and apply these models to the invariant representation of visual motion, to the inference of connectivity in networks of coupled neural oscillators, and to the development of statistical models of edge structure in images.< Less
Modelling of Deterministic, Fuzzy and Probablistic Dynamical Systems: M.S. Thesis By Rohitash Chandra
eBook (PDF): $0.00
Download immediately.
Recurrent neural networks and hidden Markov models have been the popular tools for sequence recognition problems such as automatic speech recognition. This work investigates the combination of... More > recurrent neural networks and hidden Markov models into the hybrid architecture. This combination is feasible due to the similarity of the architectural dynamics of the two systems. Initial experiments were done by training recurrent neural networks to behave like finite-state automata using genetic algorithms in order to demonstrate that their structure is sufficiently rich to represent dynamical systems. The results show that hybrid recurrent neural networks can learn and represent dynamical systems such as finite automaton. Finally, the proposed hybrid architecture is applied to automatic speech phoneme recognition. The results show that hybrid recurrent neural networks perform with some conditions and degree of success when applied to difficult real-world problems.< Less
Modelling of Deterministic, Fuzzy and Probablistic Dynamical Systems: M.S. Thesis By Rohitash Chandra
Paperback: $20.00
Ships in 3-5 business days
Recurrent neural networks and hidden Markov models have been the popular tools for sequence recognition problems such as automatic speech recognition. This work investigates the combination of... More > recurrent neural networks and hidden Markov models into the hybrid architecture. This combination is feasible due to the similarity of the architectural dynamics of the two systems. Initial experiments were done by training recurrent neural networks to behave like finite-state automata using genetic algorithms in order to demonstrate that their structure is sufficiently rich to represent dynamical systems. The results show that hybrid recurrent neural networks can learn and represent dynamical systems such as finite automaton. Finally, the proposed hybrid architecture is applied to automatic speech phoneme recognition. The results show that hybrid recurrent neural networks perform with some conditions and degree of success when applied to difficult real-world problems.< Less