Summary

In this chapter, we learned about sequential modeling and sequential memory by examining some real-life cases with Google Assistant. Then, we learned how sequential modeling is related to RNNs, as well as how RNNs are different from traditional feedforward networks. We learned about the vanishing gradient problem in detail and how using an LSTM is better than a simple RNN to overcome the vanishing gradient problem. We applied what we learned to time series problems by predicting stock trends.

In this workshop, we learned the basics of machine learning and Python, while also gaining an in-depth understanding of applying Keras to develop efficient deep learning solutions. We explored the difference between machine and deep learning. We began the workshop by building a logistic regression model, first with scikit-learn, and then with Keras.

Then, we explored Keras and its different models further by creating prediction models for various real-world scenarios, such as classifying...