Study 10-15 hrs/week and complete in 3 months.
Over the course of this program, you’ll become an expert in the main components of Natural Language Processing, including speech recognition, sentiment analysis, and machine translation. You’ll learn to code probabilistic and deep learning models, train them on real data, and build a career-ready portfolio as an NLP expert!
Natural Language Processing is at the center of the AI revolution, as it provides a tool for humans to communicate with computers effectively. The industry is hungry for highly-skilled specialists, and you’ll begin making an impact right away.
Master Natural Language Processing techniques with the goal of applying those techniques immediately to real-world challenges and opportunities. This is efficient learning for the innovative and career-minded professional AI engineer.
You’ll learn how to build and code natural language processing and speech recognition models in Python. You’ll complete three major natural language processing projects, and build a strong portfolio in the process.
The most effective way to learn is by having your code and solutions analyzed by AI experts who will give you powerful feedback in order to improve your understanding.
See fewer details
This program requires experience with Python, statistics, machine learning, and deep learning. See detailed requirements.
Learn text processing fundamentals, including stemming and lemmatization. Explore machine learning methods in sentiment analysis. Build a speech tagging model.Part of Speech Tagging
Learn advanced techniques like word embeddings, deep learning attention, and more. Build a machine translation model using recurrent neural network architectures.Machine Translation
Learn voice user interface techniques that turn speech into text and vice versa. Build a speech recognition model using deep neural networks.Speech Recognizer
Luis was formerly a Machine Learning Engineer at Google. He holds a PhD in Mathematics from the University of Michigan, and a Postdoctoral Fellowship at the University of Quebec at Montreal.
Jay has a degree in computer science, loves visualizing machine learning concepts, and is the Investment Principal at STV, a $500 million venture capital fund focused on high-technology startups.
Arpan is a computer scientist with a PhD from North Carolina State University. He teaches at Georgia Tech (within the Masters in Computer Science program), and is a coauthor of the book Practical Graph Mining with R.
Dana is an electrical engineer with a Masters in Computer Science from Georgia Tech. Her work experience includes software development for embedded systems in the Automotive Group at Motorola, where she was awarded a patent for an onboard operating system.
TL;DR: Enroll in this Program! I enjoyed completing the Udacity Natural Language Processing Nanodegree Program. There are three required projects. Project difficulty ranges from easy to somewhat challenging, depending on your prior experience. Hands-on projects are the most valuable aspect of this Program. When you start the first module, you might wonder why the Program is so expensive. After all, you can find free course materials that covers most of these topics elsewhere on the Web. For me this Program is worth it, and I came up with three reasons that justify the high cost. First, the projects really help you learn the concepts. One caveat is that you should allocate more time than the estimated completion time for all projects. For example, the Automatic Speech Recognition project has a 5 hour estimated completion time. Well, training all the required models takes at least 8 hours on AWS g3.4xlarge EC2 instance, NOT including implementation, testing, and debugging time. Second, the build-in Jupyter workspaces are nice; if you choose, you can submit project within the Udacity workspaces. In addition, the Machine Translation project actually offers the feature to switch between CPU and GPU workspaces. GPU cloud instances can be expensive, and Udacity allocated a generous number of hours for the Machine Translation project. NOTE: The Automatic Speech Recognition project DOESN"T offer any Jupyter workspaces. However, knowing how to setup AWS GPU workspaces from scratch is a valuable skill. I recommend that you budget between 30 to 50 USD to provision your own AWS GPU instances. Finally, the Code Reviews are helpful. The reviewers always pinpoint deficiencies in the submissions. In all cases when I needed to resubmit, it was because I didn't read the instructions carefully. Some reviewers offer more suggestions and recommend more optional improvements than others, so I guess luck has something to do with how much you benefit from Code Reviews. As with all learning, how much you get back is proportional to how much time and effort you invest. I also recommend taking advantage of the optional Extracurricular Modules to maximize value you gain from this Program.
Greeeeeeeeat! This course covers important topics in NLP. As a layperson, I cannot be sure that it covers all topics; but all NLP applications I saw can be explained by its teaching content. The teaching following the state of the art.
I finally understand neural nets and the fundamentals of NLP. I have tried many resources and even though some of the classes here were simply notebooks but the fact that they have gathered those resources in this order and provided readings and other resources has a great impact on the learning curve.
So far looks great!
Besides helping on the most important algorithms in NLP, the program manages to make you curious on solving even harder problems. The last project is pretty interesting. I'd suggest this Nanodegree for anyone that is starting to work with NLP or that wants to refresh their memories on the subject. Sometimes the program loses a bit of Udacity's style, and turn into something more academic (lessons + theory), unlike what is done in the Self Driving Car Nanodegree, or the Deep Learning Nanodegree, for instance. But it's bearable, and you can go faster on those parts.
Learn the essentials of natural language processing, including part-of-speech tagging, sentiment analysis, machine translation, and speech recognition.
To succeed in this Nanodegree program, we recommend you first take any course in Deep Learning equivalent to our Deep Learning Nanodegree program. You also need to be able to communicate fluently and professionally in written and spoken English.
Additionally, you should have the following knowledge:
Intermediate Python programming knowledge, including:
Basic shell scripting:
Basic statistical knowledge, including:
Intermediate differential calculus and linear algebra, including:
The Natural Language Processing Nanodegree program is composed of one (1) Term of three (3) months. A Term has fixed start and end dates.
To graduate, students must successfully complete four (4) projects, each of which affords you the opportunity to apply and demonstrate new skills that you learn in the lessons. Each project will be reviewed by the Udacity reviewer network. Feedback will be provided and if you do not pass the project, you will be asked to resubmit the project until it passes.
The full program consists of one 3-month long term at a cost of USD 799, for a total program cost of USD 799.
Payment is due before the term begins.