8. Neural NetworksΒΆ
Recently, Deep Neural Networks has revolutionalized wide areas of computer science. Today, applications like object recognition, face recognition, semantic segmentation, speech recognition, etc. achieve a significantly improved accuracy, since they are implemented as Deep Neural Networks. This is particularly true for NLP applications such as text classification, automatic translation, intent recognition, named entity recognition and so on.
In this chapter first the basics of conventional neural networks (Single- and Multi-Layer Perceptron) are introduced in Neural Networks Introduction. In Recurrent Neural Networks different types of recurrent neural networks (RNN) are described. The most important type of deep neural network, the so called Convolutional Neural Network (CNN), is subject of Convolutional Neural Networks.
Implementations of CNNs and LSTMs for document classification are shown in CNN, LSTM and Attention for IMDB Movie Review classification.