Convolutional Neural Networks (CNNs / ConvNets)

Table of Contents:Architecture OverviewConvNet LayersConvolutional LayerPooling LayerNormalization LayerFully-Connected LayerConverting Fully-Connected Layers to Convolutional LayersConvNet ArchitecturesLayer PatternsLayer Sizing PatternsCase Studies (LeNet / AlexNet / ZFNet / GoogLeNet / VGGNet)Computational ConsiderationsAdditional ReferencesConvolutional Neural Networks (CNNs / ConvNets) Convolutional Neural Networks are very similar to ordinary Neural Networks from the previouschapter: they are made up of neurons that have learnable weights and biases. Each neuronreceives some inputs, performs a dot product and optionally follows it with a non-linearity. Thewhole network still expresses a single differentiable score function: from the raw image pixels onone end to class scores at the other.

Clearly, this full connec tivity is wasteful and the huge number of parameters would quickly lead t o overtting. 3D volumes of neurons. Convolutional Neural Networks take advantage of the fact that the input consists o f images and they constrai n the architecture in a more sensible way. In par ticular, unlike a regular Neural Network, the ...

Loading..

Tags:

  Network, Neural network, Neural, Wasteful

Information

Related search queries