Deep Learning

Deep Learning

This course will introduce you to the essential techniques of text mining as the extension of data mining's standard predictive methods to unstructured text.

This course will introduce you to the essential techniques of text mining as the extension of data mining's standard predictive methods to unstructured text.

549
Alert me to upcoming courses
Menu

Overview

This course is designed for data scientists, statisticians, software engineers and technical managers interested in learning about state-of-the-art deep learning techniques and concepts, and the range of applications in which they can be used. A surge in deployed applications based on deep learning methods indicates its potential to more fully realize the promise of Artificial Intelligence. You will study basic concepts underlying the representations and methods of deep learning, and discuss applications where deep learning is most effective.

Learning Outcomes

At the end of this course you will have an appreciation of what kind of problems are most suited for deep learning, along with current research trends. Topics covered include: neural networks and optimization; convolutional networks and image processing; recurrent architectures and language processing; and advanced topics. Students will learn to install and use Tensorflow to run a linear classifier and neural net.

  • Install and run Tensorflow
  • Build on the available Tensorflow code to run a linear classifier and neural net
  • Explain the characteristics and parameters of a convolutional network
  • Use Tensorflow to configure a convolutional network to recognize handwritten digits
  • Explain the role played by networks based on Long Short Term Memory
  • Explain the considerations involved in implementing both supervised and unsupervised methods in a deep network

Who Should Take This Course

Data scientists, statisticians, software engineers, technical managers interested in learning about what is deep learning, the state-of-the-art techniques/concepts and the range of applications in which they can be used.

Instructors

Nayak_Pragyansmita_56469_Apr 18 2019

Dr. Pragyansmita Nayak

Pragyansmita Nayak is Senior Data Scientist (Federal Data Intelligence) at Hitachi Vantara Federal, a wholly owned subsidiary of Hitachi Vantara. She has over 20 years of experience in software applications and data science-related research and development.  
See Instructor Bio

Course Syllabus

Week 1

Neural Networks and Optimization

  • Overview
  • Machine Learning Basics
  • Deep Feedforward Networks
  • Basic Optimization Algorithms

Week 2

Convolutional Networks and Image Processing

  • Convolutional Networks
  • Practical Methodology
  • Image Applications

Week 3

Recurrent Architectures and Language Processing

  • Recurrent Networks
  • Long Short Term Memory
  • Language Applications

Week 4

Advanced Topics, Research Trends

  • Autoencoders
  • Representation Learning
  • Deep Generative Models

Class Dates

2019

Nov 8, 2019 to Dec 6, 2019

2020

Nov 6, 2020 to Dec 4, 2020

2021

No classes scheduled at this time.

Send me reminder for next class

Prerequisites

There are no prerequisites for this course.

You should have some familiarity with linear algebra, probability and information theory. You should also be able to run open-source tools and install them on your personal computer. You should be sufficiently familiar with Python to write programs to read/generate data and process it in appropriate data structures using relevant packages.

What Our Students Say​

Dave was a fantastic instructor. Lots of personalized feedback. The course was challenging but  extremely rewarding. It's made me think about a range of new areas of statistical analysis, which I've found very stimulating

Jim Pearse
Director, Health Policy Analysis

The two instructors are to be congratulated in putting together a jewel of a short course, one of my very favorite among the many I have taken at Statistics.com.  The discussion with such experts was particularly valuable and greatly enhanced the value of the course.  If there were an extension to this course, I would gladly take it.

Milan Hejtmanek
Seoul National University

Frequently Asked Questions

Can I transfer or withdraw from a course?

We have a flexible transfer and withdrawal policy that recognizes circumstances may arise to prevent you from taking a course as planned. You may transfer or withdraw from a course under certain conditions.

  • Students are entitled to a full refund if a course they are registered for is canceled.
  • You can transfer your tuition to another course at any time prior to the course start date or the drop date, however a transfer is not permitted after the drop date.
  • Withdrawals on or after the first day of class are entitled to a percentage refund of tuition.

Please see this page for more information.

Who are the instructors at the Institute?

The Institute has more than 60 instructors who are recruited based on their expertise in various areas in statistics. Our faculty members are:

  • Authors of well-regarded texts in their area;
  • Advisory board members;
  • Senior faculty; and
  • Educators who have made important contributions to the field of statistics or online education in statistics.

The majority of our instructors have more than five years of teaching experience online at the Institute.

Please visit our faculty page for more information on each instructor at The Institute for Statistics Education.

Please see our knowledge center for more information.

What type of courses does the Institute offer?

The Institute offers approximately 80 courses each year. Topics include basic survey courses for novices, a full sequence of introductory statistics courses, bridge courses to more advanced topics. Our courses cover a range of topics including biostatistics, research statistics, data mining, business analytics, survey statistics, and environmental statistics.

Please see our course search or knowledge center for more information.

Do your courses have for-credit options?

Our courses have several for-credit options:

  • Continuing education units (CEU)
  • College credit through The American Council on Education (ACE CREDIT)
  • Course credits that are transferable to the INFORMS Certified Analytics Professional (CAP®)

Please see our knowledge center for more information.

Is the Institute for Statistics Education certified?

The Institute for Statistics Education is certified to operate by the State Council of Higher Education for Virginia (SCHEV). For more information visit: http://www.schev.edu

Please see our knowledge center for more information.

Visit our knowledge base and learn more.

FAQs + Knowledge Base

Related Courses

Anomaly Detection

In this course you will learn how to examine data with the goal of detecting anomalies or abnormal instances.
Topic: Data Science, Machine Learning | Skill: Intermediate | Credit Options: ACE, CAP, CEU
Class Start Dates: Oct 16, 2020, Oct 15, 2021

Additional Course 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 short answer questions to test concepts, practice with using public-domain tools and some guided exercises that involve freely available data. There is also an end-of-course project.

Course Text

The required text is Deep Learning (MIT Press, 2016) by I. Goodfellow, Y. Bengio and A. Courville.

A freely available html version is available at http://www.deeplearningbook.org

It will be supplemented in the course by other technical papers, also available online.

Please order a copy of your course textbook prior to course start date.

Software

The assignments will use TensorFlow. Instructions for installing TensorFlow can be found here: https://www.tensorflow.org/install/

We recommend installing Python 3 (>= 3.4) and pip3, although TensorFlow can also be run using Python 2 (>= 2.7) and pip. It is possible to have both versions of Python on your computer and switch between them for different purposes. One advantage of Python 3 is that it uses Unicode natively, which is often convenient for language processing tasks.

If you are using a computer with a CUDA-enabled graphics card, try to install CUDA (>=8.0) and cuDNN (>=v6) and integrate them into TensorFlow. Otherwise, you will still be able to complete the assignments in CPU mode (but some of the models will be run on a smaller scale).

Some assignments will build on the tutorials and software available at https://www.tensorflow.org/get_started/

For convenience of download, it is highly recommended that you have github installed on your computer (git is easy to install and available for almost any operating system). https://git-scm.com/

Software Uses and Descriptions | Available Free Versions
To learn more about the software used in this course, or how to obtain free versions of software used in our courses, please read our knowledge base article “What software is used in courses?” 

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.

ACE CREDIT | College Credit
This course has been evaluated by the American Council on Education (ACE) and is recommended for the the upper division baccalaureate degree, 3 semester hours in data mining, statistics, or computer science. Please note that the decision to accept specific credit recommendations is up to the academic institution accepting the credit.

ACE Digital Badge
Courses evaluated by the American Council on Education (ACE) have a digital badge available for successful completion of the course.

Supplemental Information

There is no supplemental content for this course.

Miscellaneous

There is no additional information for this course.

Register for This Course​

Deep Learning
549
Get Notified

Have a Question About This Course?

Janet Dobbins

Sales and Business Development

Phone

(571) 281-8817

Send Us A Note

We like to hear from you.

Name*

Email*

Phone

Company

Message*

 

Send
Close Menu