Applied Deep Learning with TensorFlow 2: Learn to Implement Advanced Deep Learning Techniques with Python

© Umberto Michelucci 2022

U. MichelucciApplied Deep Learning with TensorFlow 2https://doi.org/10.1007/978-1-4842-8020-1_7

7. Convolutional Neural Networks

Umberto Michelucci¹  

(1)

Dübendorf, Switzerland

 

In the previous chapters, we looked at fully connected networks and all the problems you encounter while training them. The network architecture we used, one where each neuron in a layer is connected to all the neurons in the previous and next layers, is not good at many fundamental tasks like image recognition, speech recognition, time series prediction, and many more. Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) are the most advanced architectures used today. This chapter looks at convolution and pooling, the basic building ...