Artificial Neural Networks When using ANN, we have to define:When using ANN, we have to define: –Artificial Neuron Model –ANN Architecture –Learning mode
Developing Intelligent Program Systems Machine Learning : Neural Nets Neural nets can be used to answer the following: – Pattern recognition: Does that image contain a face? – Classification problems: Is this cell defective? – Prediction: Given these symptoms, the patient has disease X – Forecasting: predicting behavior of stock market – Handwriting: is character recognized?
Artificial Neural Network Learning paradigms Supervised learning: –Teacher presents ANN input-output pairs, –ANN weights adjusted according to error Classification Control Function approximation Associative memory Unsupervised learning: –no teacher Clustering
Main Problems with ANN Contrary to Expert sytems, with ANN the Knowledge base is not transparent (black box)Contrary to Expert sytems, with ANN the Knowledge base is not transparent (black box) Learning sometimes difficult/slowLearning sometimes difficult/slow Limited storage capabilityLimited storage capability
When to use ANNs? Input is high-dimensional discrete or real-valued (e.g. raw sensor input).Input is high-dimensional discrete or real-valued (e.g. raw sensor input). Inputs can be highly correlated or independent.Inputs can be highly correlated or independent. Output is discrete or real valuedOutput is discrete or real valued Output is a vector of valuesOutput is a vector of values Possibly noisy data. Data may contain errorsPossibly noisy data. Data may contain errors Form of target function is unknownForm of target function is unknown Long training time are acceptableLong training time are acceptable Fast evaluation of target function is requiredFast evaluation of target function is required Human readability of learned target function is unimportantHuman readability of learned target function is unimportant ⇒ ANN is much like a black-box