Deep Learning with Python and PyTorch from edX

Please Note: Learners who successfully complete this IBM course can earn a skill badge — a detailed, verifiable and digital credential that profiles the knowledge and skills you’ve acquired in this course. Enroll to learn more, complete the course and claim your badge!

NOTE: In order to be successful in completing this course, please ensure you are familiar with PyTorch Basics and have practical knowledge to apply it to Machine Learning. If you do not have this pre-requiste knowledge, it is highly recommended you complete the PyTorch Basics for Machine Learning course prior to starting this course.

This course is the second part of a two-part course on how to develop Deep Learning models using Pytorch.

In the first course, you learned the basics of PyTorch; in this course, you will learn how to build deep neural networks in PyTorch. Also, you will learn how to train these models using state of the art methods. You will first review multiclass classification, learning how to build and train a multiclass linear classifier in PyTorch. This will be followed by an in-depth introduction on how to construct Feed-forward neural networks in PyTorch, learning how to train these models, how to adjust hyperparameters such as activation functions and the number of neurons.

You will then learn how to build and train deep neural networks—learning how to apply methods such as dropout, initialization, different types of optimizers and batch normalization. We will then focus on Convolutional Neural Networks, training your model on a GPU and Transfer Learning (pre-trained models). You will finally learn about dimensionality reduction and autoencoders. Including principal component analysis, data whitening, shallow autoencoders, deep autoencoders, transfer learning with autoencoders, and autoencoder applications.

Finally, you will test your skills in a final project.

What's inside

Learning objectives

Apply knowledge of deep neural networks and related machine learning methods
Build and train deep neural networks using pytorch

Build deep learning pipelines

Apply knowledge of deep neural networks and related machine learning methods
Build and train deep neural networks using pytorch
Build deep learning pipelines

Syllabus

Module 1 - Classification

Softmax Regression

Softmax in PyTorch Regression

Training Softmax in PyTorch Regression

Module 2 - Neural Networks

Introduction to Networks

Network Shape Depth vs Width

Back Propagation

Activation functions

Module 3 - Deep Networks

Dropout

Initialization

Batch normalization

Other optimization methods

Module 4 - Computer Vision Networks

Convolution

Max Polling

Convolutional Networks

Pre-trained Networks

Module 5 - Computer Vision Networks

Max Pooling

Training your model with a GPU

Module 6 Dimensionality reduction and autoencoders

Principle component analysis

Linear autoencoders

Autoencoders

Transfer learning

Deep Autoencoders

Module 7 -Independent Project

Good to know

Know what's good

, what to watch for

, and possible dealbreakers

Requires a student to be familiar with PyTorch Basics, which may cause difficulties to beginners

Provides a in-depth introduction to constructing feedforward neural networks in PyTorch, which is valuable for machine learning practitioners

Examines key concepts such as dropout, initialization, batch normalization, and optimizers, which are essential for building robust models

Covers advanced techniques such as Convolutional Neural Networks, transfer learning, and autoencoders, which are in high demand in industry

Teaches practical skills like training models on GPUs, which is crucial for optimizing performance

Includes a final project to test students' understanding and reinforce learning

Activities

Be better prepared before your course. Deepen your understanding during and after it. Supplement your coursework and achieve mastery of the topics covered in Deep Learning with Python and PyTorch with these activities:

Read 'Deep Learning' by Ian Goodfellow, Yoshua Bengio and Aaron Courville

Show steps

This comprehensive book provides a deep dive into the foundational concepts of deep learning.

View Deep Learning on Amazon

Show steps

Read selected chapters covering topics of interest
Summarize key concepts and algorithms
Apply concepts to practical projects, (optional)

Solve LeetCode Problems on Neural Network Implementation

Show steps

Solving LeetCode problems helps develop proficiency in implementing and debugging neural networks.

Show steps

Select problems related to neural network implementation
Develop solutions using your preferred programming language
Test and debug your solutions

Train Neural Networks using Backpropagation

Show steps

Practice the use of backpropagation for training neural nets. This is critical to an intuitive understanding of the behavior of neural networks and can greatly help identify problems in NN designs.

Browse courses on Backpropagation

Show steps

Set up a simple neural network with one hidden layer and write forward and backpropagation functions
Generate a dataset and train the network on it
Analyze the results and identify ways to improve accuracy

Two other activities

Expand to see all activities and additional details

Show all five activities

Build a Convolutional Neural Network for Image Classification

Show steps

Build a CNN from scratch to understand how CNN layers extract features and classify images.

Browse courses on Convolution

Show steps

Gather and prepare an image dataset
Design and implement a CNN architecture
Train the CNN and evaluate its performance

Develop a Tutorial on Dimensionality Reduction using PCA

Show steps

Create a personal tutorial or guide on PCA to solidify your understanding of it and help others.

Browse courses on Dimensionality Reduction

Show steps

Review the concepts of dimensionality reduction and PCA
Implement a PCA algorithm in your preferred programming language
Create visual demonstrations to illustrate how PCA works

Career center

Learners who complete Deep Learning with Python and PyTorch will develop knowledge and skills that may be useful to these careers:

Data Scientist

Data Scientists design and implement analytical solutions to complex business problems. They use their knowledge of mathematics, statistics, and computer science to extract insights from data, which can then be used to make informed decisions. This course can help you develop the skills needed to be a successful Data Scientist. You will learn how to build and train deep neural networks using PyTorch, which is a powerful tool for data analysis. Additionally, you will gain experience with deep learning pipelines, which are used to automate the process of building and training deep neural networks.

See salaries and explore the career path for Data Scientist

Machine Learning Engineer

Machine Learning Engineers design, develop, and maintain machine learning systems. They use their knowledge of mathematics, statistics, and computer science to build models that can learn from data and make predictions. This course can help you develop the skills needed to be a successful Machine Learning Engineer. You will learn how to build and train deep neural networks using PyTorch, which is a powerful tool for machine learning. Additionally, you will gain experience with deep learning pipelines, which are used to automate the process of building and training deep neural networks.

See salaries and explore the career path for Machine Learning Engineer

Deep Learning Engineer

Deep Learning Engineers design, develop, and maintain deep learning systems. They use their knowledge of mathematics, statistics, and computer science to build models that can learn from data and make predictions. This course can help you develop the skills needed to be a successful Deep Learning Engineer. You will learn how to build and train deep neural networks using PyTorch, which is a powerful tool for deep learning. Additionally, you will gain experience with deep learning pipelines, which are used to automate the process of building and training deep neural networks.

See salaries and explore the career path for Deep Learning Engineer

Software Engineer

Software Engineers design, develop, and maintain software systems. They use their knowledge of computer science to build systems that meet the needs of users. This course can help you develop the skills needed to be a successful Software Engineer. You will learn how to build and train deep neural networks using PyTorch, which is a powerful tool for building software systems. Additionally, you will gain experience with deep learning pipelines, which are used to automate the process of building and training deep neural networks.

See salaries and explore the career path for Software Engineer

Data Analyst

Data Analysts collect, clean, and analyze data to extract insights that can be used to make informed decisions. They use their knowledge of mathematics, statistics, and computer science to make sense of data. This course can help you develop the skills needed to be a successful Data Analyst. You will learn how to build and train deep neural networks using PyTorch, which is a powerful tool for data analysis. Additionally, you will gain experience with deep learning pipelines, which are used to automate the process of building and training deep neural networks.

See salaries and explore the career path for Data Analyst

Computer Vision Engineer

Computer Vision Engineers design, develop, and maintain computer vision systems. They use their knowledge of computer science and mathematics to build systems that can see and understand the world around them. This course can help you develop the skills needed to be a successful Computer Vision Engineer. You will learn how to build and train deep neural networks using PyTorch, which is a powerful tool for computer vision. Additionally, you will gain experience with deep learning pipelines, which are used to automate the process of building and training deep neural networks.

See salaries and explore the career path for Computer Vision Engineer

Natural Language Processing Engineer

Natural Language Processing Engineers design, develop, and maintain natural language processing systems. They use their knowledge of computer science and linguistics to build systems that can understand and generate human language. This course can help you develop the skills needed to be a successful Natural Language Processing Engineer. You will learn how to build and train deep neural networks using PyTorch, which is a powerful tool for natural language processing. Additionally, you will gain experience with deep learning pipelines, which are used to automate the process of building and training deep neural networks.

See salaries and explore the career path for Natural Language Processing Engineer

Research Scientist

Research Scientists conduct research in a variety of fields, including computer science, mathematics, and statistics. They use their knowledge to develop new theories and technologies. This course can help you develop the skills needed to be a successful Research Scientist. You will learn how to build and train deep neural networks using PyTorch, which is a powerful tool for research. Additionally, you will gain experience with deep learning pipelines, which are used to automate the process of building and training deep neural networks.

See salaries and explore the career path for Research Scientist

Artificial Intelligence Engineer

Artificial Intelligence Engineers design, develop, and maintain artificial intelligence systems. They use their knowledge of computer science and mathematics to build systems that can learn from data and make predictions. This course can help you develop the skills needed to be a successful Artificial Intelligence Engineer. You will learn how to build and train deep neural networks using PyTorch, which is a powerful tool for artificial intelligence. Additionally, you will gain experience with deep learning pipelines, which are used to automate the process of building and training deep neural networks.

See salaries and explore the career path for Artificial Intelligence Engineer

Systems Engineer

Systems Engineers design, develop, and maintain computer systems. They use their knowledge of computer science and engineering to build systems that meet the needs of users. This course can help you develop the skills needed to be a successful Systems Engineer. You will learn how to build and train deep neural networks using PyTorch, which is a powerful tool for building computer systems. Additionally, you will gain experience with deep learning pipelines, which are used to automate the process of building and training deep neural networks.

See salaries and explore the career path for Systems Engineer

Product Manager

Product Managers are responsible for the development and launch of new products. They use their knowledge of business and technology to create products that meet the needs of users. This course can help you develop the skills needed to be a successful Product Manager. You will learn how to use deep learning to develop new products, and you will gain experience with deep learning pipelines. Deep learning is a powerful tool for developing new products, and this course will give you the skills you need to be successful in this field.

See salaries and explore the career path for Product Manager

Quantitative Analyst

Quantitative Analysts use mathematics, statistics, and computer science to analyze financial data. They use their knowledge to develop trading strategies and make investment decisions. This course can help you develop the skills needed to be a successful Quantitative Analyst. You will learn how to build and train deep neural networks using PyTorch, which is a powerful tool for financial analysis. Additionally, you will gain experience with deep learning pipelines, which are used to automate the process of building and training deep neural networks.

See salaries and explore the career path for Quantitative Analyst

Actuary

Actuaries use mathematics, statistics, and computer science to assess risk. They use their knowledge to develop insurance policies and make recommendations to businesses. This course can help you develop the skills needed to be a successful Actuary. You will learn how to build and train deep neural networks using PyTorch, which is a powerful tool for risk assessment. Additionally, you will gain experience with deep learning pipelines, which are used to automate the process of building and training deep neural networks.

See salaries and explore the career path for Actuary

Biostatistician

Biostatisticians use mathematics, statistics, and computer science to analyze medical data. They use their knowledge to develop new treatments and make recommendations to healthcare providers. This course can help you develop the skills needed to be a successful Biostatistician. You will learn how to build and train deep neural networks using PyTorch, which is a powerful tool for medical data analysis. Additionally, you will gain experience with deep learning pipelines, which are used to automate the process of building and training deep neural networks.

See salaries and explore the career path for Biostatistician

Operations Research Analyst

Operations Research Analysts use mathematics, statistics, and computer science to solve problems in business and industry. They use their knowledge to develop new methods for improving efficiency and productivity. This course can help you develop the skills needed to be a successful Operations Research Analyst. You will learn how to build and train deep neural networks using PyTorch, which is a powerful tool for solving business problems. Additionally, you will gain experience with deep learning pipelines, which are used to automate the process of building and training deep neural networks.

See salaries and explore the career path for Operations Research Analyst