Intro to Python for Computer Science and Data Science: Learning to Program with AI, Big Data and The Cloud

16.9 Recurrent Neural Networks for Sequences; Sentiment Analysis with the IMDb Dataset

In the MNIST CNN network, we focused on stacked layers that were applied sequentially. Non-sequential models are possible, as you’ll see here with recurrent neural networks. In this section, we use Keras’s bundled IMDb (the Internet Movie Database) movie reviews dataset⁷² to perform binary classification, predicting whether a given review’s sentiment is positive or negative.

72. Maas, Andrew L. and Daly, Raymond E. and Pham, Peter T. and Huang, Dan and Ng, Andrew Y. and Potts, Christopher, "Learning Word Vectors for Sentiment Analysis," Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, June ...