Internet of Things for Architects

CNN examples

Four layer CNN. Here, an image is convolved to extract large features based on primitives, then using a max pool to scale the image down and feed as input to the feature filters. The fully connected layer ends the CNN path and outputs the best guess.

An example of primitive features that compose the layers are courtesy of TensorFlow (http://playground.tensorflow.org). The TensorFlow example of a system with six features on input layer 1, followed by 33 hidden layers of four neurons, followed by two neurons and ending with two more is shown in the following diagram. In this model, the features attempt to classify the color groupings ...