What will I get if I subscribe to this Certificate?

When you enroll in the course, you get access to all of the courses in the Certificate, and you earn a certificate when you complete the work. Your electronic Certificate will be added to your Accomplishments page - from there, you can print your Certificate or add it to your LinkedIn profile.

Introduction to Deep Learning & Neural Networks with Keras

Introduction to Deep Learning & Neural Networks with Keras

This course is part of multiple programs.

Instructor: Alex Aklson

115,979 already enrolled

Included with

5 modules

Gain insight into a topic and learn the fundamentals.

Intermediate level

Some related experience required

1 week to complete

at 10 hours a week

Flexible schedule

Learn at your own pace

5 modules

Gain insight into a topic and learn the fundamentals.

Intermediate level

Some related experience required

1 week to complete

at 10 hours a week

Flexible schedule

Learn at your own pace

What you'll learn

Describe the foundational concepts of deep learning, neurons, and artificial neural networks to solve real-world problems
Explain the core concepts and components of neural networks and the challenges of training deep networks
Build deep learning models for regression and classification using the Keras library, interpreting model performance metrics effectively.
Design advanced architectures, such as CNNs, RNNs, and transformers, for solving specific problems like image classification and language modeling

Skills you'll gain

Category: Natural Language Processing
Category: Applied Machine Learning
Category: Artificial Neural Networks
Category: Machine Learning
Category: Deep Learning
Category: Image Analysis
Category: Model Training
Category: Regression Analysis
Category: Recurrent Neural Networks (RNNs)
Category: Convolutional Neural Networks
Category: Machine Learning Methods
Category: Model Optimization
Category: Network Architecture
Category: Transfer Learning

Tools you'll learn

Category: Keras (Neural Network Library)
Category: Autoencoders

Details to know

Shareable certificate

Add to your LinkedIn profile

Assessments

8 assignments

Taught in English

Build your subject-matter expertise

This course is available as part of

When you enroll in this course, you'll also be asked to select a specific program.

Learn new concepts from industry experts
Gain a foundational understanding of a subject or tool
Develop job-relevant skills with hands-on projects
Earn a shareable career certificate from IBM

There are 5 modules in this course

This course introduces deep learning and neural networks with the Keras library. In this course, you’ll be equipped with foundational knowledge and practical skills to build and evaluate deep learning models.

You’ll begin this course by gaining foundational knowledge of neural networks, including forward and backpropagation, gradient descent, and activation functions. You will explore the challenges of deep network training, such as the vanishing gradient problem, and learn how to overcome them using techniques like careful activation function selection. The hands-on labs in this course allow you to build regression and classification models, dive into advanced architectures, such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), transformers, and autoencoders, and utilize pretrained models for enhanced performance. The course culminates in a final project where you’ll apply what you’ve learned to create a model that classifies images and generates captions. By the end of the course, you’ll be able to design, implement, and evaluate a variety of deep learning models and be prepared to take your next steps in the field of machine learning.

In this module, you will explore the foundational concepts of deep learning and neural networks using Keras. This module introduces you to the significance and applications of deep learning. You’ll delve into the structure and function of neurons and neural networks. Further, you’ll explore artificial neural networks, detailing their architecture and operation. Finally, you’ll evaluate the forward propagation process, understanding how data moves through a network to produce outputs. Additionally, you’ll gain a comprehensive understanding of how deep learning models are constructed and function.

What's included

4 videos2 readings2 assignments1 app item1 plugin

4 videosTotal 17 minutes

Course Introduction3 minutes
Introduction to Deep Learning4 minutes
Neurons and Neural Networks4 minutes
Artificial Neural Networks6 minutes

2 readingsTotal 8 minutes

Course Overview5 minutes
Module Summary: Introduction to Neural Networks and Deep Learning 3 minutes

2 assignmentsTotal 31 minutes

Practice Quiz: Introduction to Neural Networks and Deep Learning 10 minutes
Module 1 Graded Quiz: Introduction to Neural Networks and Deep Learning21 minutes

1 app itemTotal 30 minutes

Artificial Neural Networks - Forward Propagation30 minutes

1 pluginTotal 2 minutes

Helpful Tips for Course Completion2 minutes

In this module, you’ll delve into the core mechanisms of neural networks. You'll explain how models optimize gradient descent algorithms and explore backpropagation. Further, you’ll demonstrate how to address challenges using the vanishing gradient problem. Finally, this module introduces you to the activation functions as solutions. Through hands-on exercises, you’ll observe how different activation functions impact learning, equipping you with the knowledge to design and train effective deep learning models.

What's included

4 videos1 reading2 assignments2 app items

4 videosTotal 22 minutes

Gradient Descent5 minutes
Backpropagation9 minutes
Vanishing Gradient2 minutes
Activation Functions6 minutes

1 readingTotal 3 minutes

Module 2 Summary: Basics of Deep Learning3 minutes

2 assignmentsTotal 40 minutes

Practice Quiz: Basics of Deep Learning10 minutes
Module 2 Graded Quiz: Basics of Deep Learning30 minutes

2 app itemsTotal 50 minutes

Lab: Backpropagation30 minutes
Lab: Vanishing Gradient and Activation Functions20 minutes

In this module, you will explore the applications of deep learning using the Keras library. You’ll also gain insights into the role of Keras and other deep learning libraries in model development. This module guides you through building and training regression and classification models using Keras. The hands-on labs in this module provide real-world datasets to implement and evaluate deep learning models for various predictive tasks.

What's included

3 videos1 reading2 assignments2 app items

3 videosTotal 15 minutes

Deep Learning Libraries4 minutes
Regression Models with Keras5 minutes
Classification Models with Keras6 minutes

1 readingTotal 2 minutes

Module 3 Summary: Keras and Deep Learning Libraries2 minutes

2 assignmentsTotal 40 minutes

Practice Quiz: Modeling with Keras10 minutes
Module 3 Graded Quiz: Keras and Deep Learning Libraries 30 minutes

2 app itemsTotal 75 minutes

Regression Models with Keras45 minutes
Classification with Keras30 minutes

In this module, you’ll delve into advanced deep learning architectures and techniques using the Keras library. You’ll distinguish between shallow and deep neural networks, understanding their respective complexities and applications. You’ll also explore convolutional neural networks (CNNs) for image processing tasks and gain guidance for implementing CNNs using Keras. You’ll explore recurrent neural networks (RNNs) for sequential data and transformer models that have revolutionized natural language processing (NLP). Additionally, you’ll explore autoencoders for unsupervised learning and pretrained models to enhance performance and reduce training time. The hands-on labs in this module provide you with a practical understanding of various deep learning models and transformers in Keras.

What's included

6 videos1 reading2 assignments2 app items

6 videosTotal 29 minutes

Shallow Versus Deep Neural Networks3 minutes
Convolutional Neural Networks8 minutes
Recurrent Neural Networks3 minutes
Transformers7 minutes
Autoencoders3 minutes
Using Pre-trained Models 5 minutes

1 readingTotal 3 minutes

Module 4 Summary: Deep Learning Models3 minutes

2 assignmentsTotal 40 minutes

Practice Quiz: Supervised and Unsupervised Neural Networks10 minutes
Module 4 Graded Quiz: Deep Learning Models30 minutes

2 app itemsTotal 90 minutes

Convolutional Neural Networks with Keras60 minutes
Lab: Transformers with Keras30 minutes

In this final module, you will apply and demonstrate the full range of skills you have gained throughout the course. In this module, you will consolidate your learning through a final project integrating core deep learning concepts such as image classification and caption generation using Keras. After completing the project, you will reflect on your journey through the course and understand the next steps for continued growth in deep learning.

What's included

1 video2 readings2 app items

Earn a career certificate

Add this credential to your LinkedIn profile, resume, or CV. Share it on social media and in your performance review.

Instructor

Alex Aklson

IBM

21 Courses1,455,853 learners

Offered by

IBM

Why people choose Coursera for their career

Felipe M.

Learner since 2018

"To be able to take courses at my own pace and rhythm has been an amazing experience. I can learn whenever it fits my schedule and mood."

Jennifer J.

Learner since 2020

"I directly applied the concepts and skills I learned from my courses to an exciting new project at work."

Larry W.

Learner since 2021

"When I need courses on topics that my university doesn't offer, Coursera is one of the best places to go."

Chaitanya A.

"Learning isn't just about being better at your job: it's so much more than that. Coursera allows me to learn without limits."

Frequently asked questions

This course bridges the gap between high-level code syntax and the mathematical realities of neural network optimization. You will unpack how data travels forward through layers via forward propagation to generate predictions, and how the network calculates error using a loss function. Crucially, you will explore the calculus behind backpropagation and gradient descent, learning how network weights and biases are iteratively adjusted based on the calculated gradients to minimize prediction error.

A key value proposition of this course is teaching you how to troubleshoot and design stable, deep architectures. As neural networks grow in depth, they often suffer from the vanishing gradient problem, where gradients become exponentially smaller during backpropagation, causing the early layers to stop learning. You will study how to mitigate this training bottleneck by implementing advanced mathematical activation functions (such as ReLU, LeakyReLU, and Softmax) and adjusting optimization hyperparameters directly within your Keras code.

You will transition from basic dense networks to specialized, modern artificial intelligence models designed for different data modalities:

Convolutional Neural Networks (CNNs): Tailored for computer vision, feature map extraction, and spatial image classification tasks.

Recurrent Neural Networks (RNNs): Structured to process sequential data, time-series predictions, and natural language.

Transformers: Explored as the foundational, attention-based architecture driving modern generative AI and sequence-to-sequence language modeling.

Autoencoders: Implemented for unsupervised learning, dimensionality reduction, and data denoising workflows.

To access the course materials, assignments and to earn a Certificate, you will need to purchase the Certificate experience when you enroll in a course. You can try a Free Trial instead, or apply for Financial Aid. The course may offer 'Full Course, No Certificate' instead. This option lets you see all course materials, submit required assessments, and get a final grade. This also means that you will not be able to purchase a Certificate experience.