1 / 26

Artificial Neural Networks - Basics

Business School Institute of Business Informatics. Artificial Neural Networks - Basics. Uwe Lämmel. www.wi.hs-wismar.de/~laemmel U.laemmel@wi.hs-wismar.de. Neural Networks. Idea Artificial Neuron & Network Supervised Learning Unsupervised Learning Data Mining – other Techniques. Idea

jiro
Download Presentation

Artificial Neural Networks - Basics

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. Business SchoolInstitute of Business Informatics ArtificialNeural Networks - Basics Uwe Lämmel www.wi.hs-wismar.de/~laemmel U.laemmel@wi.hs-wismar.de

  2. Neural Networks • Idea • Artificial Neuron & Network • Supervised Learning • Unsupervised Learning • Data Mining – other Techniques

  3. Idea An artificial Neuron Neural Network Example Learning Application Artificial Neuron & Network

  4. Idea • A human being learns by example “learning by doing” • seeing(Perception), Walking, Speaking,… • Can a machine do the same? • A human being uses his brain. A brain consists of millions of single cells.A cell is connected with ten thousands of other cell. • Is it possible to simulate a similar structure on a computer?

  5. Idea Artificial Neural Network • Information processing similar to processes in a mammal brain • heavy parallel systems, • able to learn • great number of simple cells ? Is it useful to copy nature ? • wheel, aeroplane, ...

  6. Idea An artificial neural network functions in a similar way a natural neural network does. • we need: • software neurons • software connections between neurons • software learning algorithms

  7. Dendrits cell and nucleus Axon (Neurit) Synapsis A biological Neuron • Dendrits: (Input) Getting other activations • Axon: (Output ) forward the activation (from 1mm up to 1m long) • Synapse: transfer of activation: • to other cells, e.g. Dendrits of other neurons • a cell has about 1.000 to 10.000 connections to other cells • Cell Nucleus: (processing) evaluation of activation

  8. w1i w2i ... wji Dendrits cell and nucleus Axon oi (Neurit) Synapsis Natural vs. Artificial Neuron

  9. Abstraction • Dendrits: weighted (real number) connections • Axon: output: real number • Synapse: --- (identity: output is directly forwarded) • Cell nucleus: unit contains simple functions input = (many) real numbers processing = activation function output = real number (~activation)

  10. w1i w2i ... wji oi An artificial Neuron net : input from the network w : weight of a connection act : activation fact : activation function  :bias/threshold fout : output function (mostly ID) o : output

  11. Exercise: AND/OR -LTU • Built a „network“ that works like an AND-function • Built an OR-network • Try to built an XOR-network LTU – Linear Threshold Unit

  12. a1=__ a2=__ w1=__ w2=__ net = o1w1+o2 w2 a = 1, if net > = 0, otherwise o = a o=__ A simple switch • Neuron = AND-function • Find parameters: • Input neurons 1,2 :a1,a2 input pattern, • weights of edges: w1, w2 • bias  • Now evaluate output o !

  13. Mathematics in a Cell • Propagation function (neuron input)neti(t) =  ojwj = w1i  o1 + w2i  o2 + ... • Activationai(t) – Activation at time t • Activation functionfact :ai(t+1) = fact(ai(t), neti(t), i) i – bias • Output functionfout :oi = fout(ai)

  14. Activation

  15. Bias function 1,0 0,5 0,0 -4,0 -2,0 0,0 2,0 4,0 -0,5 Identity -1,0 4,0 2,0 0,0 -4,0 -2,5 -1,0 0,5 2,0 3,5 -2,0 -4,0 Activation Functions activation functionsaresigmoid functions

  16. y = tanh(c·x) c=3 1,0 c=2 c=1 0,5 y = 1/(1+exp(-c·x)) -0,6 0,6 1,0 -1,0 c=10 1,0 -0,5 c=3 c=1 -1,0 0,5 1,0 0,0 -1,0 Activation Functions activation functionsaresigmoid functions Logistic function:

  17. Structure of a network • layers • input layer – input neurons • output layer – output neurons • hidden layer – hidden neurons • An n-layer network has: • n layer of connections which can be trained 

  18. Definition: A Neural Network … • … is characterized by • connections of many (a lot of) simple units (neurons) and • units exchanging signals via these connections • … is a • coherent, directed graph which has • weighted edges and • each node (neuron, unit ) contains a value (activation).

  19. XOR-network input output • weights are set by hand • fact = 1, net >  = 0, otherwise •  = 1.0

  20. XOR-Example • standard propagation function:neti(t) =  oj(t)wji • activation function = bias function • ai = 1, if neti(t)> i e.g. =0.5 0, otherwise • output function = Identity: oj = aj • use EXCEL and built the XOR-example network!

  21. Network evaluation network error learning examples changingnetwork parameters Learning

  22. Learning - can be done by: • Modification of the weight of a connection • most frequently used • Deleting connections • can be done by (1): w=0  w0 • Modification of the bias of a neuron • Can be done by (1) using an extra neuron • changing functions (activation, propagation, output function) • Building new cells (GNG) • Building new connections • Deleting cells

  23. Learning • supervised learning • We know the results for certain input pattern:teaching input  teaching output • Network error is used to adapt weights • Fast, but not natural • reinforced learning • We know whether output is right or wrong • Information is used to adapt weights • Slower than supervised; natural • unsupervised learning • Network has to learn by itself; • Slow , natural

  24. Applications • Pattern recognition (text, numbers, faces) • Checking the quality of a surface • Control of autonomous vehicles • Monitoring of credit card accounts • Data Mining

  25. Applications • Speech recognition • Control of artificial limbs • classification of galaxies • Product orders (Supermarket) • Forecast of energy consumption • Stock value forecast

  26. Application - Summary • Classification • Clustering • Forecast • Pattern recognition • Learning by examples, generalization • Recognition of not known structures

More Related