摘要 |
The present invention extends to methods, systems, and computer program p roducts for recognizing input gestures. A neural network is trained using ex ample inputs and backpropagation to recognize specified input patterns. Inpu t gesture data is representative of movements in contact on a multi-touch in put display surface relative to one or more axes over time. Example inputs u sed for training the neural network to recognize a specified input pattern c an be created from sampling input gesture data for example input gestures kn own to represent the specified input pattern. Trained neural networks can su bsequently be used to recognize input gestures that are similar to known inp ut gestures as the specified input pattern corresponding to the known input gestures.
|