In this chapter,we saw how to develop a demo project for predicting stock prices for five categories: OPEN, CLOSE, LOW, HIGH, and VOLUME. However, our approach cannot generate an actual signal. Still, it gives some idea of how to use LSTM. I know there are some serious drawbacks of this approach. Nevertheless, we did not use enough data, which potentially limits the performance of such a model.
In the next chapter, we will see how to apply deep learning approaches to a video dataset. We will describe how to process and extract features from a large collection of video clips. Then we will make the overall pipeline scalable and faster by distributing the training on multiple devices (CPUs and GPUs), and run them in parallel.
We will see a complete example of how to develop a deep learning application that accurately classifies a large collection of a video dataset, such...
