In this chapter, we have seen how to use and build real-life applications using CNNs, which are a type of feedforward artificial neural network in which the connectivity pattern between neurons is inspired by the organization of the animal visual cortex. Our image classifier application using CNN can classify real-life images with an acceptable level of accuracy, although we did not achieve higher accuracy. However, readers are encouraged to tune hyperparameters in the code and also try the same approach with another dataset.

Nevertheless, and importantly since the internal data representation of a convolutional neural network does not take into account important spatial hierarchies between simple and complex objects, CNN has some serious drawbacks and limitation for certain instances. Therefore, I would suggest you take a look at the recent activities around capsule networks on GitHub at https://github.com/topics/capsule-network. Hopefully, you can get something useful out from there

This is, more-or-less, the end of our little journey in developing ML projects using Scala and different open source frameworks. Throughout the chapters, I tried to provide you with several examples of how to use these wonderful technologies efficiently for developing ML projects. During the writing of this book, I had to keep many constraints in my mind, for example, the page count, API availability, and my expertise. But I tried to make the book more-or-less simple, and I also tried to avoid details on the theory, as you can read about that in many books, blogs, and websites on Apache Spark, DL4j, and H2O itself.

I will also keep the code of this book updated on my GitHub repo at: https://github.com/PacktPublishing/Scala-Machine-Learning-Projects. Feel free to open a new issue or any pull request for improving this book and stay tuned.

Finally, I did not write this book to earn money but a major portion of the royalties will be spent for the child education in the rural areas of my home district in Bangladesh. I would like to say thanks and express my sincere gratitude for buying and enjoying this book!