1 / 12

Neural Networks

Neural Networks. An Introduction. A Neuron. Computer Representation. Output= a(n) = a(pw+b). A Single Neuron with Multiple Inputs. Single Layer Neural Network with Multiple Neurons. Multiple Layer Neural Network. Activation Functions. Hard Limit a = 0 n < 0 a = 1 n >= 0

Download Presentation

Neural Networks

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Neural Networks An Introduction

  2. A Neuron An Introduction to Neural Networks

  3. Computer Representation Output= a(n) = a(pw+b) An Introduction to Neural Networks

  4. A Single Neuron with Multiple Inputs An Introduction to Neural Networks

  5. Single Layer Neural Network with Multiple Neurons An Introduction to Neural Networks

  6. Multiple Layer Neural Network An Introduction to Neural Networks

  7. Activation Functions • Hard Limit • a = 0 n < 0 • a = 1 n >= 0 • Symmetrical Hard Limit • a = -1 n < 0 • a = +1 n >= 0 • Saturating Linear • a = 0 n < 0 • a = n 0 <= n <= 1 • a = 1 n > 1 An Introduction to Neural Networks

  8. Activation Functions • Linear • a = n • Symmetric Saturating Linear • a = -1 n < -1 • a = n -1 <= n <= 1 • a = 1 n > 1 • Log-Sigmoid • a = 1 1+ e-n An Introduction to Neural Networks

  9. Activation Functions • Hyperbolic Tangent Sigmoid • a = en - e-n en + e-n • Positive Linear • a = 0 n < 0 • a = n n >= 0 • Competitive • a = 1 neuron with max n • a = 0 all other neurons An Introduction to Neural Networks

  10. The History of Development of Neural Networks • The Beginning of Neural Networks (1940's) • McCulloch Pitts Neuron • Hebb Learning • The First Golden Age of Neural Networks (1950's and 1960's) • Perceptrons • Adaline • The Quiet Years: 1970's • Kohonen • Anderson • Grossberg • Carpenter • Renewed Enthusiasm: 1980's • Backpropagation • Hopfield nets • Neocognitron • Boltzman machine • Hardware Implementation An Introduction to Neural Networks

  11. Developing a Neural Network System Choose a neural network architecture Train the neural network using a training set Apply the neural network to identify patterns. This involves implementing the application algorithm An Introduction to Neural Networks

  12. Choosing a Neural Network Architecture • Identify the number of inputs • Number of network inputs = number of problem inputs. • Identify the number of outputs • Number of neurons in output layer = number of problem outputs. • The output layer transfer function is partly determined by problem specification of the outputs. An Introduction to Neural Networks

More Related