Nn devs
Download as PPT, PDF0 likes455 views
This document introduces neural networks and neuro-DEVS. It defines artificial neural networks and provides examples of single neuron and multi-layer network structures. It describes different types of neural networks including perceptrons, multi-layer perceptrons, backpropagation networks, Hopfield networks, and Kohonen feature maps. It discusses areas where neural networks can be useful and their limitations. It outlines the advantages of using neural networks and describes three main applications. It provides an overview of the neuro-atomic model and its use in DEVS simulations, giving an example of a solar energetic system model that uses a neural network as a sub-component.
![Multi Layered Perceptron I/O are bounded in [0,1] for the activation to perform Pass 1: Forward Pass - Present inputs and let the activations flow until they reach the output layer. Pass 2: Backward Pass - Error estimates are computed for each output unit by comparing the actual output (Pass 1) with the target output. Then, these error estimates are used to adjust the weights in the hidden layer and the errors from the hidden layer are used to adjust the input layer.](https://image.slidesharecdn.com/nn-devs-110219121124-phpapp02/85/Nn-devs-18-320.jpg)
Nn devs
- 1. Introduction to Neural Network and Neuro-DEVS Yan Wang August 29 th 2002
- 2. Neural Network Definition of Artificial Neural Network Two Examples with some fundamental concepts Types of Neural Nets What they can do and where they fail
- 3. What is an Artificial Neural Network? (ANN) A neural network is a computational method inspired by studies of the brain and nervous systems in biological organisms. A Computing system made of a number of simple, highly interconnected processing elements, which process information by their dynamic state response to external input. given by R.Hecht-Nielsen (1989)
- 4. Example 1-Single Neuron Structure of a neuron in a neural net
- 5. Example 2-Three Layers Neural Net Neural net with three neuron layers
- 6. They can be distinguished by: their type (feedforward or feedback) their structure the learning algorithm they use Types of Neural Nets
- 7. Perceptron Multi-Layer-Perceptron Backpropagation Net Hopfield Net Kohonen Feature Map A Selection of Neural Nets
- 8. Perceptron Perceptron structure
- 9. Multi-Layer-Perceptron Multi-Layer-Perceptron structure
- 10. Backpropagation Net Backpropagation Net structure
- 11. Hopfield Net Hopfield Net structure
- 12. Kohonen Feature Map Kehonen Feature Map structure
- 13. · pattern association · pattern classification · regularity detection · image processing · speech analysis · optimization problems · robot steering · processing of inaccurate or incomplete inputs · quality assurance · stock market forecasting · simulation · ... The areas where neural nets may be useful
- 14. the operational problem encountered when attempting to simulate the parallelism of neural networks instability to explain any results that they obtain Limits to Neural Networks
- 15. The Advantage Using Neural Network Three Main Applications Neuro-Atomic Model and its description in DEVS An Example - Solar Energetic System Neuro-DEVS
- 16. Handle partial lack of system understanding Create adaptive models (models that can learn) The Advantage Using Neural Network
- 17. Concurrent simulation, where results of an ANN model are compared with results of a less realistic but validated common model to avoid a non expected behavior of the Neural-Net. ANN as sub-components of a global model, to model subsystems that would be hard to model commonly because of a lack of understanding. Adaptive models, "models that can learn", according to an error feedback such model would be able to adapt runtime to situations that hasn't been taken into account. Three Main Applications
- 18. Multi Layered Perceptron I/O are bounded in [0,1] for the activation to perform Pass 1: Forward Pass - Present inputs and let the activations flow until they reach the output layer. Pass 2: Backward Pass - Error estimates are computed for each output unit by comparing the actual output (Pass 1) with the target output. Then, these error estimates are used to adjust the weights in the hidden layer and the errors from the hidden layer are used to adjust the input layer.
- 19. Neuro-Atomic Model ANN designed by expert for specific purpose Trained ANNs stored in libraries ANN Object loaded while simulator is created
- 20. Neuro-Atomic Model (NAM) Description NAM=<X,Y,S,NN,ta,init,dint,dext, λ ,learn,act,prop> where: X = {R } is the set of input external event Y = {R } is the set of output external event S is the state set, where S = {(s,phase,error) s is the status {activated, learn, propagate} phase {active, passive} error {0,1} is the squared root error between the actual output and the desired output } NN is the link to the neural net object (ANN) ta: is the time advance function
- 21. init: X -> S is the initialization function d int: S -> S is the internal transition function d ext: X -> S is the external transition function λ : S -> Y is the output function learn: Xerro r -> NN is the ANN’s learning function act: X -> NN is the ANN’s input activation function prop: N N -> Y is the ANN’s propagation function Proposed in the paper” NEURO-DEVS, AN HYBRID ETHODOLOGY TO DESCRIBE COMPLEX SYSTEMS” by Jean-Baptiste Filippi. Neuro-Atomic Model (NAM) Description
- 22. Example - Solar Energetic System Solar panel, sun shinness and consumption are well known Battery shows better results with NN, use of NN as sub-component