The continued growth in data, coupled with the need to make increasingly complex decisions against that data, is creating massive hurdles that prevent organizations from deriving insights in a timely manner using traditional analytical approaches.
To find meaningful values and insights, deep learning evolved, which is a branch of machine learning algorithms based on learning multiple levels of abstraction. Neural networks, being at the core of deep learning, are used in predictive analytics, computer vision, natural language processing, time series forecasting, and performing a myriad of other complex tasks.
Until date, most DL books available are written in Python. However, this book is conceived for developers, data scientists, machine learning practitioners, and deep learning enthusiasts who want to build powerful, robust, and accurate predictive models with the power of Deeplearning4j (a JVM-based DL framework), combining other open source Java APIs.
Throughout the book, you will learn how to develop practical applications for AI systems using feedforward neural networks, convolutional neural networks, recurrent neural networks, autoencoders, and factorization machines. Additionally, you will learn how to attain your deep learning programming on GPU in a distributed way.
After finishing the book, you will be familiar with machine learning techniques, in particular, the use of Java for deep learning, and will be ready to apply your knowledge in research or commercial projects. In summary, this book is not meant to be read cover to cover. You can jump to a chapter that looks like something you are trying to accomplish or one that simply ignites your interest.
Happy reading!