-
Book Overview & Buying
-
Table Of Contents
Hands-On Artificial Intelligence for IoT - Second Edition
By :
The models we have explored so far learned using supervised learning. In this section, we will learn about autoencoders. They are feedforward, non-recurrent neural networks, and they learn through unsupervised learning. They find applications in image reconstruction, clustering, machine translation, and much more. They were initially proposed in the 1980s by Geoffrey E. Hinton and the PDP group (http://www.cs.toronto.edu/~fritz/absps/clp.pdf).
The autoencoder basically consists of two cascaded neural networks – the first network acts as an encoder; it takes the input, x, and encodes it using a transformation, h, to an encoded signal, y, as shown in the following equation:

The second neural network uses the encoded signal, y, as its input and performs another transformation, f, to get a reconstructed signal, r, as follows:

The loss function is the MSE with error, e, defined as the difference between the original input, x, and the reconstructed...