Survey
* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project
Download presentation on artificial neural networks
Document related concepts
Neural modeling fields wikipedia , lookup
Philosophy of artificial intelligence wikipedia , lookup
Gene expression programming wikipedia , lookup
Pattern recognition wikipedia , lookup
Existential risk from artificial general intelligence wikipedia , lookup
Machine learning wikipedia , lookup
Hierarchical temporal memory wikipedia , lookup
Ethics of artificial intelligence wikipedia , lookup
History of artificial intelligence wikipedia , lookup
Transcript
An informal description of artificial neural networks John MacCormick Decision tree for “Should I take an umbrella?” Schematic representation of a biological neuron Neural network for “Should I take an umbrella?” Objective: detect sunglasses Source for sunglasses data and code: Tom Mitchell, Machine Learning, McGraw-Hill (1998). We use an artificial neural network with a single hidden layer Our artificial neurons compute a weighted sum followed by a non-linear threshold (actually a sigmoid) The weights of the inputs to each neuron are tuned to produce good results on the training set This experiment produced an 85% success rate for determining the presence of sunglasses
