Deep Learning with Python and PyTorch Free Online Course
International Business Machines Corporation is pleased to announce a Free Online Course on Deep Learning with Python and PyTorch. The course will teach you how to develop Deep Learning models using Pytorch while providing the necessary deep-learning background.
In the course, you will learn how to use Python and its popular libraries such as NumPy and Pandas, as well as the PyTorch Deep Learning library. You’ll then apply them to build Neural Networks and Deep Learning models.
Course At a Glance
Length: 6 weeks
Effort: 2-4 hours pw
Subject: Analysis of data and statistics
Institution: International Business Machines Corporation
Languages: English
Price: Free
Certificate Available: Yes, Add a Verified Certificate for $99
Session: At your own pace
Providers’ Details
IBM is a cognitive solution and cloud platform company headquartered in Armonk, NY. It is the largest technology and consulting employer in the world, serving clients in more than 170 countries. With 25 consecutive years of patent leadership, IBM Research is the world’s largest corporate research organization with more than 3,000 researchers in 12 labs located across six continents.
About This Course
They’ll start off with PyTorch’s tensors and its Automatic Differentiation package. Then they’ll cover different Deep Learning models in each section, beginning with fundamentals such as Linear Regression and logistic/softmax regression.
They’ll then move on to Feedforward deep neural networks, the role of different activation functions, normalization and dropout layers.
In the final part of the course, they’ll focus on Convolutional Neural Networks and Transfer Learning (pre-trained models). Several other Deep Learning methods will also be covered.
Course Syllabus
Module 1 – Introduction to Pytorch
- What’s Deep Learning and why Pytorch
- 1-D Tensors and useful Pytoch Functions
- 2-D Tensors and useful functions
- Derivatives and Graphs in Pytorch
- Data Loader
Module 2 – Linear Regression
- Prediction 1D regression
- Training 1D regression
- Stochastic gradient descent, mini-batch gradient descent
- Train, test, split and early stopping
- By torch way
- Multiple Linear Regression
Module 3 – Classification
- Logistic Regression
- Training Logistic Regressions Part 1
- Training Logistic Regressions Part 2
- Softmax Regression
Module 4 – Neural Networks
- Introduction to Networks
- Network Shape Depth vs Width
- Back Propagation
- Activation functions
Module 5 – Deep Networks
- Dropout
- Initialization
- Batch normalization
- Other optimization methods
Module 6 – Computer Vision Networks
- Convolution
- Max Polling
- Convolutional Networks
- Pre-trained Networks
Learning Outcomes
- Explain and apply knowledge of Deep Neural Networks and related machine learning methods;
- Know how to use Python, and Python libraries such as Numpy and Pandas along with the PyTorch library for Deep Learning applications;
- Build Deep Neural Networks using PyTorch.
Instructors
Joseph Santarcangelo is currently working as a Data Scientist at IBM. Joseph has a Ph.D. in Electrical Engineering. His research focused on using machine learning, signal processing, and computer vision to determine how videos impact human cognition.
How To Join This Course
- Go to the course website link
- Create an edX account to SignUp
- Choose “Register Now” to get started.
- EdX offers honor code certificates of achievement, verified certificates of achievement, and XSeries certificates of achievement. Currently, verified certificates are only available in some courses.
- Once the applicant signs up for a course and activates their account, click on the Log In button on the org homepage and type in their email address and edX password. This will take them to the dashboard, with access to each of their active courses. (Before a course begins, it will be listed on their dashboard but will not yet have a “view course” option.)