Intro to Deep Learning Theory and Practice Featuring Keras
Published by O'Reilly Media, Inc.
Why, when, and how deep learning works to solve problems
Deep learning is a much-hyped technology. While we often hear about its flashiest applications, such as in self-driving cars, most companies are more interested in determining how they can use deep neural models to improve business processes such as quality control, market segmentation and pricing, and forecasting. To do so, companies need to enable their existing engineers and data scientists to use deep learning without creating a separate PhD-level R&D lab (as Google and Facebook have done), demystifying deep learning and making it immediately practical for business use.
Expert Adam Breindel offers an introduction to how deep learning models work, where they come from, and why they have become so popular now. In just three three-hour sessions, you’ll get a solid feel for selecting, building, tuning, and training models (as well as the critical mathematical concepts behind deep learning)—all without doing any extensive work in linear algebra and vector calculus. Join Adam to learn about deep feed-forward networks, convolutional networks, and recurrent network variants like LSTM, generative networks, reinforcement learning, and real-world operational issues.
What you’ll learn and how you can apply it
By the end of this live, online course, you’ll understand:
- Where deep learning came from, why it’s so popular right now, and where it may go in the future
- How to make sense of published deep learning models (e.g., in papers or online code)
- How the specific mechanics and choices in a deep network operate to produce results
And you’ll be able to:
- Evaluate the suitability of deep learning for a specific problem and dataset
- Design, tune, and train several common network architectures
- Create and modify networks implemented with the Keras Python framework
- Choose deep learning data science pipelines for your company’s needs that make sense in the real world
This live event is for you because...
- You’re a software engineer with a data analytics or algorithmic background who wants to implement deep learning in products and services at your company.
- You’re a data scientist with a traditional machine-learning or predictive analytics background, and you need to brush up on the latest deep learning approaches so you can integrate them into your pipelines.
- You’re a product manager, technical director, or VP who wants to get a nuts-and-bolts intuitive feel for where deep learning can help your company’s product strategy (and where it cannot).
Prerequisites
- A basic understanding of calculus (one variable), probability, statistics, traditional machine learning, and predictive analytics
- A working knowledge of Python
- Familiarity with multivariable or vector calculus and analysis, probability theory, and information theory (useful but not required)
Recommended preparation:
Materials and setup instructions
- Please sign up for a free Databricks Community Edition account, you can create an anonymous account at tinyurl.com/databricks-ce
- Confirm your email address and ensure you can log in prior to class
Schedule
The time frames are only estimates and may vary according to how the class is progressing.
Day 1
Introduction to deep learning (30 minutes)
Hello, TensorFlow (30 minutes)
Artificial neural networks (90 minutes)
Multilayer (deep) networks (30 minutes)
Day 2
Training deep networks (30 minutes)
Convolutional networks (105 minutes)
Recurrent networks (45 minutes)
Day 3
Generative networks (85 minutes)
Reinforcement learning (60 minutes)
Operations, real-world considerations, and Q&A (45 minutes)
Your Instructor
Adam Breindel
Adam Breindel consults and teaches courses on Apache Spark, data engineering, machine learning, AI, and deep learning. He supports instructional initiatives as a senior instructor at Databricks, has taught classes on Apache Spark and deep learning for O'Reilly, and runs a business helping large firms and startups implement data and ML architectures. Adam’s first full-time job in tech was neural net–based fraud detection, deployed at North America's largest banks back; since then, he's worked with numerous startups, where he’s enjoyed getting to build things like mobile check-in for two of America's five biggest airlines years before the iPhone came out. He’s also worked in entertainment, insurance, and retail banking; on web, embedded, and server apps; and on clustering architectures, APIs, and streaming analytics.