NLP and Deep Learning
In this course you will learn about deep neural networks, and how to use them in processing text with Python (Natural Language Processing or NLP).
Overview
In this course you will learn about deep neural networks (deep learning), and how to leverage them in processing, understanding and mining for insights from text. We start with an introduction to neural networks and deep learning. We then dive into essentials of representation learning like word and document embeddings and then move onto more complex methodologies including convolutional neural networks and sequence models and deep transfer learning approaches including universal embeddings and transformers. Popular applications are also covered with hands-on tutorials and exercises including text classification, information extraction, recommenders, search, summarization, translation and more.
- Intermediate
- 4 Weeks
- Expert Instructor
- Tuiton-Back Guarantee
- 100% Online
- TA Support
Learning Outcomes
In this course you will learn:
- How to specify and run artificial neural networks and deep networks
- How deep networks represent words as binary vectors
- How to use recurrent neural networks for sequential learning (sequence-to-sequence modeling)
- How to use attention models to improve predictive performance
Who Should Take This Course
Data scientists and aspiring data scientists.
Our Instructors
Mr. Dipanjan Sarkar
He holds a master of technology degree from IIIT Bangalore, with specializations in data science and software engineering and completed his post graduate diploma in machine learning and artificial intelligence from Columbia University in the City of New York.
Dipanjan has been an analytics practitioner and consultant for several years now, specializing in machine learning, natural language processing, computer vision and deep learning. Having a passion for data science and education, he also acts as an AI Advisor, Subject Matter Expert and Instructor at various organizations like Springboard, Propulsion Academy and Statistics.com (The Institute for Statistics Education) where he helps people build their skills on areas in data science and artificial intelligence. Dipanjan also beta-tests new courses on data science for popular MOOC platform, Coursera, before they are released. He is a published author, having authored several books on R, Python, Machine Learning, Natural Language Processing, and Deep Learning which includes Text Analytics with Python 2nd ed.
Course Syllabus
Week 1
Introduction to Deep Learning and Representation Learning
- Introduction to deep neural networks and deep learning
- Applications of Deep Learning for NLP
- Essential components of deep learning
- Types of models (especially for NLP)
- Layers, activation and loss functions
- Gradient descent and Backpropagation
- Representation Learning for Text Data
- Understanding Embeddings
- Types of Embeddings
- CBOW (Continuous Bag of Words) and SkipGram
- Word Embedding Models – Word2Vec, GloVe, FastText
- Obtaining document embeddings
Week 2
Context Sensitive Learning: Convnets and Sequential Models
- Convolutional Neural NetworksConvnets for NLP
- Convolutional Neural Networks
- 1D-CNNs for Text Classification
- Sequential Models for NLP
- Recurrent Neural Networks
- Long Short Term Memory Networks (LSTMs)
- Gated Recurrent Units (GRUs)
- Bi-directional LSTMs (Bi-LSTMs)
- Contextual Embeddings using BiLSTMs – ELMO
- Sequence-to-Sequence Models for NLP
- Encoder-Decoder Models
- Applications of Encoder-Decoder Models
Week 3
Deep Transfer Learning for NLP
- Transfer Learning
- Need and importance
- Methodologies
- Pre-trained word embeddings
- Word2vec, GloVe, FastText
- Universal Embeddings
- Neural net language model (NNLM)
- Universal Sentence Encoder
- Transformers and Multi-task Learning
- Brief and types of transformers
- Advantages of pre-trained transformers
- Applications
Week 4
Attention, Transformers and Applications
- Limitations of Sequential and Sequence-to-sequence models
- Attention in sequential Models
- Understanding Transformer Models
- Encoders and Decoders
- Self Attention and Multi-headed Attention
- Contextual and Pooled Embeddings
- BERT
- Transformers Variants
- Bidirectional Encoder Representations from Transformers (BERT) variants – Roberta, Albert, XLNet etc.
- Efficient Transformers with knowledge distillation – DistilBERT
- Generative Transformers – generative pre-training (GPT) family
Class Dates
2024
Instructors: Mr. Dipanjan Sarkar
Instructors: Mr. Dipanjan Sarkar
Instructors: Mr. Dipanjan Sarkar
2025
Instructors: Mr. Dipanjan Sarkar
Instructors: Mr. Dipanjan Sarkar
Instructors: Mr. Dipanjan Sarkar
Prerequisites
You should be sufficiently familiar with Python to follow and use code examples (see suggested course below). You should also be familiar with the neural net material covered in the predictive analytics course, below.
Introduction to NLP and Text Mining
- Skill: Intermediate
- Credit Options: ACE, CAP, CEU
Private: Predictive Analytics 2 with Python – Neural Nets and Regression
- Skill: Intermediate
- Credit Options: ACE, CAP, CEU
The Statistics.com courses have helped me a lot, pushing me to the limit and making me learn much more than I expected I could. The knowledge I gained I could immediately leverage in my job … then eventually led to landing a job in my dream company – Amazon.
Karolis Urbonas
This program has been a life and work game changer for me. Within 2 weeks of taking this class, I was able to produce far more than I ever had before.
Susan Kamp
The material covered in the Analytics for Data Science Certificate will be indispensable in my work. I can’t wait to take other courses. Great work!
Stephen McAllister
I learned more in the past 6 weeks than I did taking a full semester of statistics in college, and 10 weeks of statistics in graduate school. Seriously.
Amir Aminimanizani
This is the best online course I have ever taken. Very well prepared. Covers a lot of real-life problems. Good job, thank you very much!
Elena Rose
The more courses I take at Statistics.com, the more appreciation I have for the smart approach, quality of instructors, assistants, admin and program. Well done!
Leonardo Nagata
This course greatly benefited me because I am interested in working in AI. It has given me solid foundational knowledge…After completing this last course, I feel I have gained valuable skills that will enhance my employability in Data Science, opening up diverse career opportunities.
Richard Jackson
Frequently Asked Questions
-
What is your satisfaction guarantee and how does it work?
-
Can I transfer or withdraw from a course?
-
Who are the instructors at Statistics.com?
Visit our knowledge base and learn more.
Additional Information
Organization of Course
This course takes place online at The Institute for 4 weeks. During each course week, you participate at times of your own choosing – there are no set times when you must be online. Course participants will be given access to a private discussion board. In class discussions led by the instructor, you can post questions, seek clarification, and interact with your fellow students and the instructor.
At the beginning of each week, you receive the relevant material, in addition to answers to exercises from the previous session. During the week, you are expected to go over the course materials, work through exercises, and submit answers. Discussion among participants is encouraged. The instructor will provide answers and comments, and at the end of the week, you will receive individual feedback on your homework answers.
Time Requirements
This is a 4-week course requiring 10-15 hours per week of review and study, at times of your choosing.
Homework
Homework in this course consists of coding exercises using Python.
Course Text
The text used for the practical work in this course is Text Analytics with Python (Apress, 2019) by Dipanjan Sarkar, chosen for its wealth of hands on Python illustrations and code. The code for these illustrations is organized here:
https://github.com/dipanjanS/text-analytics-with-python/tree/master/New-Second-Edition
Note: this text is also used in the introductory course, Introduction to NLP and Text Mining
Software
The course uses Python.
Course Fee & Information
Enrollment
Courses may fill up at any time and registrations are processed in the order in which they are received. Your registration will be confirmed for the first available course date unless you specify otherwise.
Transfers and Withdrawals
We have flexible policies to transfer to another course or withdraw if necessary.
Group Rates
Contact us to get information on group rates.
Discounts
Academic affiliation? In most courses you are eligible for a discount at checkout.
New to Statistics.com? Click here for a special introductory discount code.
Invoice or Purchase Order
Add $50 service fee if you require a prior invoice, or if you need to submit a purchase order or voucher, pay by wire transfer or EFT, or refund and reprocess a prior payment.
Options for Credit and Recognition
This course is eligible for the following credit and recognition options:
No Credit
You may take this course without pursuing credit or a record of completion.
Mastery or Certificate Program Credit
If you are enrolled in mastery or certificate program that requires demonstration of proficiency in this subject, your course work may be assessed for a grade.
CEUs and Proof of Completion
If you require a “Record of Course Completion” along with professional development credit in the form of Continuing Education Units (CEU’s), upon successfully completing the course, CEU’s and a record of course completion will be issued by The Institute upon your request.
INFORMS-CAP
This course is recognized by the Institute for Operations Research and the Management Sciences (INFORMS) as helpful preparation for the Certified Analytics Professional (CAP®) exam and can help CAP® analysts accrue Professional Development Units to maintain their certification.
ACE CREDIT | College Credit
This course has been evaluated by the American Council on Education (ACE) and is recommended for the upper-division baccalaureate degree, 2 semester hours in computer science, computer information systems, or cyber security. Please note that the decision to accept specific credit recommendations is up to the academic institution accepting the credit.
Supplemental Information
Literacy, Accessibility, and Dyslexia
At Statistics.com, we aim to provide a learning environment suitable for everyone. To help you get the most out of your learning experience, we have researched and tested several assistance tools. For students with dyslexia, colorblindness, or reading difficulties, we recommend the following web browser add-ons and extensions:
Chrome
- Color Enhancer (for colorblindness)
- HelperBird (for colorblindness, dyslexia, and reading difficulties)
Firefox
- Mobile Dyslexic
- Color Vision Simulation (native accessibility feature)
- Other native accessibility features instructions
Safari
- Navidys (for colorblindness, dyslexia, and reading difficulties)
- HelperBird for Safari (for colorblindness, dyslexia, and reading difficulties)