Introducing Convolutional Neural Networks

MLPs are powerful enough to do well on many different problems, but they’re not always the best choice. In the previous section, you saw how a basic MLP struggled to outperform random guessing when identifying images of cats and dogs. In this section, you’ll see how you can do much better than an MLP by introducing a new type of neural network: the convolutional neural network (CNN).

Convolutional neural networks are neural networks that replace traditional matrix multiplications in dense layers with convolution operations. If you have an engineering background, you’re likely familiar with the convolution operation. Although the convolution operation used in neural networks is similar to the definition ...

Get Machine Learning in Elixir now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.