We hope you enjoyed this last chapter of Python Machine Learning and our exciting tour of machine learning and deep learning. Through the journey of this book, we've covered the essential topics that this field has to offer, and you should now be well equipped to put those techniques into action to solve real-world problems.

We started our journey with a brief overview of the different types of learning tasks: supervised learning, reinforcement learning, and unsupervised learning. We then discussed several different learning algorithms that you can use for classification, starting with simple single-layer neural networks in Chapter 2, Training Simple Machine Learning Algorithms for Classification.

We continued to discuss advanced classification algorithms in Chapter 3, A Tour of Machine Learning Classifiers Using scikit-learn, and we learned about the most important aspects of a machine learning pipeline in Chapter 4, Building Good Training Sets – Data Preprocessing and Chapter 5, Compressing Data via Dimensionality Reduction.

Remember that even the most advanced algorithm is limited by the information in the training data that it gets to learn from. So in Chapter 6, Learning Best Practices for Model Evaluation and Hyperparameter Tuning, we learned about the best practices to build and evaluate predictive models, which is another important aspect in machine learning applications.

If one single learning algorithm does not achieve the performance we desire, it can be sometimes helpful to create an ensemble of experts to make a prediction. We explored this in Chapter 7, Combining Different Models for Ensemble Learning.

Then in Chapter 8, Applying Machine Learning to Sentiment Analysis, we applied machine learning to analyze one of the most popular and interesting forms of data in the modern age that's dominated by social media platforms on the internet—text documents.

Next, we reminded ourselves that machine learning techniques are not limited to offline data analysis, and in Chapter 9, Embedding a Machine Learning Model into a Web Application, we saw how to embed a machine learning model into a web application to share it with the outside world.

For the most part, our focus was on algorithms for classification, which is probably the most popular application of machine learning. However, this is not where our journey ended! In Chapter 10, Predicting Continuous Target Variables with Regression Analysis, we explored several algorithms for regression analysis to predict continuous valued output values.

Another exciting subfield of machine learning is clustering analysis, which can help us find hidden structures in the data, even if our training data does not come with the right answers to learn from. We worked with this in Chapter 11, Working with Unlabeled Data – Clustering Analysis.

We then shifted our attention to one of one of the most exciting algorithms in the whole machine learning field—artificial neural networks. We started by implementing a multilayer perceptron from scratch with NumPy in Chapter 12, Implementing a Multilayer Artificial Neural Network from Scratch.

The power of TensorFlow became obvious in Chapter 13, Parallelizing Neural Network Training with TensorFlow, where we used TensorFlow to facilitate the process of building neural network models and make use of GPUs to make the training of multilayer neural networks more efficient.

We delved deeper into the mechanics of TensorFlow in Chapter 14, Going Deeper – The Mechanics of TensorFlow, and discussed the different aspects and mechanics of TensorFlow, including variables and operators in a TensorFlow computation graph, variable scopes, launching graphs, and different ways of executing nodes.

In Chapter 15, Classifying Images with Deep Convolutional Neural Networks, we dived into convolutional neural networks, which are widely used in computer vision at the moment, due to their great performance in image classification tasks.

Finally, here in Chapter 16, Modeling Sequential Data Using Recurrent Neural Networks, we learned about sequence modeling using RNNs. While a comprehensive study of deep learning is well beyond the scope of this book, we hope that we've kindled your interest enough to follow the most recent advancements in this field of deep learning.

If you're considering a career in machine learning, or you just want to keep up to date with the current advancements in this field, I can recommend to you the works of the following leading experts in the machine learning field:

Just to name a few!

And of course, don't hesitate to join the scikit-learn, TensorFlow, and Keras mailing lists to participate in interesting discussions around these libraries and machine learning in general. Lastly, you can find out what we, the authors, are up at http://sebastianraschka.com and http://vahidmirjalili.com. You're always welcome to contact us if you have any questions about this book, or need some general tips about machine learning.