Convolutional neural networks. Recurrent neural networks. Long short-term memory networks.
There's a lot to learn to get up to speed in deep learning. A new online offering from Deeplearning.ai and Coursera will show you how.
Across five courses, you'll get up to speed on the foundations of deep learning, understand how to build, optimize and deploy neural networks, and learn how to lead successful machine learning projects.
In addition to CNNs, RNNs and LSTMs, you'll learn about Adam, Dropout, BatchNorm and Xavier/He initialization, which are algorithms you'll get to practice in Python using the TensorFlow deep learning framework.
You'll master not only theory but see how it's applied through case studies from healthcare, autonomous driving, sign language reading, music generation and natural language processing. Plus, you'll get to build deep learning models for several of these applications, including a machine learning flight simulator.
Finding the Language for Deep Learning
DLI collaborated with Deeplearning.ai on the "sequence models" portion of term 5 of the Deep Learning Specialization. Deeplearning.ai is using some of the DLI's natural language processing fundamentals course curriculum.
To illustrate the techniques needed to translate languages, date translation is built into the course. Examples include translating dates from human-readable forms like 12th of November 2015 into machine-readable forms such as 2015-11-12.
Thanks to deep learning, the sequence algorithms used in this area have enabled exciting advancements in speech recognition, music synthesis, chatbots, machine translation, natural language understanding and many other applications.
Finishing the Deep Learning Specialization will help you master the topic, understand how to apply it creatively within your work and get on your way to building a career in AI.
"AI is the new electricity, and will change almost everything we do," said Andrew Ng, founder of Deeplearning.ai, co-founder of Coursera and who was research chief at Baidu. "Partnering with the NVIDIA Deep Learning Institute to develop materials for our course on sequence models allows us to make the latest advances in deep learning available to everyone."
The course is taught in Python so it's recommended that attendees have basic programming skills, such as understanding of for loops, if/else statements and data structures such as lists and dictionaries. A basic knowledge of machine learning is also recommended, so consider Ng's machine learning course on Coursera if you're just getting started.
And if you're totally new to deep learning but anxious to get going, check out this list of the best places to get a crash course in AI.