Code: USD75OFF

This is the code repository for Enhancing Deep Learning with Bayesian Inference, published by Packt.

Create more powerful, robust deep learning systems with Bayesian deep learning in Python

Deep learning is revolutionizing our lives, impacting content recommendations and playing a key role in mission- and safety-critical applications. Yet, typical deep learning methods lack awareness about uncertainty. Bayesian deep learning offers solutions based on approximate Bayesian inference, enhancing the robustness of deep learning systems by indicating how confident they are in their predictions. This book will guide you in incorporating model predictions within your applications with care.

This book covers the following exciting features:

• Discern the advantages and disadvantages of Bayesian inference and deep learning
• Become well-versed with the fundamentals of Bayesian Neural Networks
• Understand the differences between key BNN implementations and approximations
• Recognize the merits of probabilistic DNNs in production contexts
• Master the implementation of a variety of BDL methods in Python code
• Apply BDL methods to real-world problems
• Evaluate BDL methods and choose the most suitable approach for a given task
• Develop proficiency in dealing with unexpected data in deep learning applications

If you feel this book is for you, get your copy today!

All of the code is organized into folders.

The code will look like the following:

{const set = function(...items) {
    this.arr = [...items];
    this.add = {function}(item) {
        if( this._arr.includes(item) ) {
            return false; (SC-Source)}

Following is what you need for this book: This book provides a comprehensive introduction to Bayesian deep learning methods for machine learning researchers and practitioners. It discusses the importance of uncertainty in machine learning, covers numerous methods for uncertainty-aware deep networks, and provides detailed code examples in Python to assist you throughout your exploration.

With the following software and hardware list you can run all code files present in the book (Chapters 1-9).

You are expected to have some prior knowledge of machine learning and deep learning, as well as some familiarity with concepts around Bayesian inference. Some practical knowledge of working with Python and a machine learning framework such as TensorFlow or PyTorch would also be valuable but is not necessary. Python 3.8 or above is recommended, as all code has been tested with Python 3.8. Chapter 1 provides detailed instructions on setting up your environment for the book’s code examples.

We also provide a PDF file that has color images of the screenshots/diagrams used in this book. Click here to download it.

• Causal Inference and Discovery in Python [Packt] [Amazon]

• Hands-On Simulation Modeling with Python [Packt] [Amazon]

Dr. Matt Benatan is a principal research scientist at Sonos, where he leads research into intelligent personalization systems. He has also been awarded a Simon Industrial Fellowship at the University of Manchester, where he collaborates on a variety of AI research projects. Matt obtained his Ph.D. in audio-visual speech processing from the University of Leeds, after which he pursued a career in industry, conducting machine learning research across a range of domains including signal processing, materials discovery, and fraud detection. Matt previously co-authored Wiley’s Deep Learning for Physical Scientists, and his key research interests currently include user-facing AI, optimization, and uncertainty estimation. Matt is deeply grateful to his wife, Rebecca, for her love, patience, and support, and to his parents, Dan and Debby, for their tireless enthusiasm, guidance, and encouragement.

Jochem Gietema studied philosophy and law in Amsterdam but transitioned to machine learning after his studies. He currently works as an applied scientist at Onfido in London, where he has developed and deployed several patented solutions to production in the field of computer vision and anomaly detection. He is passionate about uncertainty estimation, interactive data visualizations, and solving real-world problems with machine learning.

Dr. Marian Schneider is an applied scientist in machine learning and computer vision. He received his Ph.D. in computational visual neuroscience from the University of Maastricht. He has since transitioned from academia to industry, where he has developed and applied machine learning solutions to a wide range of products, from brain image segmentation to uncertainty estimation, to smarter image capturing on mobile phone devices. Marian is grateful to his partner, Undine, who was very supportive of the book writing process and enabled many writing and working sessions on this book, especially during weekends.