Advanced CNNs, Transfer Learning, and Recurrent Networks
Keep adding new skills with 10,000+ programs for $239 (usually $399). Save now.
Advanced CNNs, Transfer Learning, and Recurrent Networks
This course is part of Deep Learning with Real-World Projects Specialization
Included with
Ask Coursera
Recommended experience
Recommended experience
What you'll learn
Apply transfer learning techniques to enhance model performance.
Utilize RNNs and LSTMs for sequence prediction tasks.
Develop practical solutions for industry-specific problems.
Master the integration of advanced neural networks in real-world applications.
Skills you'll gain
Tools you'll learn
Details to know
See how employees at top companies are mastering in-demand skills
Build your subject-matter expertise
- 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
There are 8 modules in this course
Updated in May 2025.
This course now features Coursera Coach! A smarter way to learn with interactive, real-time conversations that help you test your knowledge, challenge assumptions, and deepen your understanding as you progress through the course. Embark on a journey through the intricate workings of advanced Convolutional Neural Networks (CNNs), Transfer Learning, and Recurrent Neural Networks (RNNs). This course begins with a thorough exploration of CNNs, delving into sophisticated architectures like VGG16 and practical applications through multi-part case studies. Each segment is designed to build your foundational knowledge and practical skills incrementally. Transitioning into Transfer Learning, the course explores pivotal models such as AlexNet, GoogleNet, and ResNet. You will engage with numerous hands-on sessions, applying transfer learning techniques to real-world datasets. These sessions are meticulously crafted to ensure a robust understanding of how pre-trained models can accelerate your projects and improve outcomes. The course culminates with an in-depth study of Recurrent Neural Networks, including Long Short-Term Memory (LSTM) networks and Gated Recurrent Units (GRUs). By working through comprehensive case studies, you'll gain practical experience in applying RNNs to sequential data tasks such as part-of-speech tagging and text generation. Each module is designed to provide a seamless learning experience, combining theoretical insights with practical implementation. This course is tailored for data scientists, machine learning engineers, and AI enthusiasts with a solid understanding of basic neural networks and Python programming. Prerequisites include prior experience with deep learning frameworks such as TensorFlow or Keras, and familiarity with fundamental machine learning concepts.
In this module, we will delve into the basics of CNNs, examining the VGG16 architecture, and engage in a comprehensive case study spread across multiple practical sessions. These hands-on exercises will reinforce the theoretical concepts covered.
What's included
7 videos2 readings
7 videos•Total 49 minutes
- Introduction•3 minutes
- VGG16 (Visual Geometry Group)•16 minutes
- Practical on CNN: Case Study – Part 1•4 minutes
- Practical on CNN: Case Study – Part 2•8 minutes
- Practical on CNN: Case Study – Part 3•10 minutes
- Practical on CNN: Case Study – Part 4•5 minutes
- Practical on CNN: Case Study – Part 5•3 minutes
2 readings•Total 20 minutes
- Introduction to the Course 'Advanced CNNs, Transfer Learning, and Recurrent Networks'•10 minutes
- Full Specialization Resources•10 minutes
In this module, we will explore various pre-trained models, their architectures, and the principles of transfer learning. Through a series of detailed sessions, we will apply these concepts in practical settings, culminating in case studies and analytical discussions.
What's included
16 videos
16 videos•Total 97 minutes
- Introduction•9 minutes
- AlexNet•12 minutes
- GoogleNet•4 minutes
- ResNet - Part 1•8 minutes
- ResNet - Part 2•7 minutes
- Transfer Learning - Part 1•4 minutes
- Transfer Learning - Part 2•4 minutes
- Transfer Learning - Part 3•4 minutes
- Transfer Learning - Part 4•3 minutes
- Transfer Learning - Part 5•4 minutes
- Transfer Learning - Part 6•3 minutes
- Case Study - Part 1•14 minutes
- Case Study - Part 2•6 minutes
- Case Study - Part 3•3 minutes
- Analysis - Part 1•9 minutes
- Analysis - Part 2•2 minutes
In this module, we will apply CNN techniques to real-world natural images, specifically focusing on flower images. Through an extensive case study spread over multiple sessions, we will learn to implement, evaluate, and refine models in a practical, industry-relevant context.
What's included
15 videos1 assignment
15 videos•Total 103 minutes
- Introduction•7 minutes
- Working with Flower Images: Case Study - Part 1•4 minutes
- Working with Flower Images: Case Study - Part 2•9 minutes
- Working with Flower Images: Case Study - Part 3•6 minutes
- Working with Flower Images: Case Study - Part 4•6 minutes
- Working with Flower Images: Case Study - Part 5•7 minutes
- Working with Flower Images: Case Study - Part 6•6 minutes
- Working with Flower Images: Case Study - Part 7•3 minutes
- Working with Flower Images: Case Study - Part 8•14 minutes
- Working with Flower Images: Case Study - Part 9•6 minutes
- Working with Flower Images: Case Study - Part 10•5 minutes
- Working with Flower Images: Case Study - Part 11•7 minutes
- Working with Flower Images: Case Study - Part 12•13 minutes
- Working with Flower Images: Case Study - Part 13•2 minutes
- Working with Flower Images: Case Study - Part 14•8 minutes
1 assignment•Total 15 minutes
- CNN-Industry Live Project: Playing with Real-World Natural Images - Assessment•15 minutes
In this module, we will tackle the challenge of identifying medical abnormalities using CNNs. Focusing on X-Ray images, we will conduct a detailed case study over several sessions, learning to interpret medical data and develop effective diagnostic models.
What's included
7 videos
7 videos•Total 30 minutes
- Introduction•3 minutes
- Working with X-Ray images: Case Study - Part 1•2 minutes
- Working with X-Ray images: Case Study - Part 2•3 minutes
- Working with X-Ray images: Case Study - Part 3•5 minutes
- Working with X-Ray images: Case Study - Part 4•4 minutes
- Working with X-Ray images: Case Study - Part 5•7 minutes
- Working with X-Ray images: Case Study - Part 6•5 minutes
In this module, we will introduce Recurrent Neural Networks, covering their basic concepts, architecture, and types. We will delve into training methods and address common challenges like the vanishing gradient problem through a series of detailed sessions.
What's included
12 videos
12 videos•Total 100 minutes
- Introduction to RNN•8 minutes
- RNN - Part 1•5 minutes
- RNN - Part 2•4 minutes
- RNN Formula•17 minutes
- Architecture•11 minutes
- Batch data•5 minutes
- Simplified Notations•14 minutes
- Types of RNN - Part 1•4 minutes
- Types of RNN - Part 2•7 minutes
- Training RNN•6 minutes
- One-to-Many•8 minutes
- Vanishing Gradient•11 minutes
In this module, we will focus on Long Short-Term Memory (LSTM) networks, covering their architecture and functionality. We will compare LSTM with other RNN variants like GRU and implement these networks in practical scenarios through a series of detailed sessions.
What's included
10 videos1 assignment
10 videos•Total 57 minutes
- Introduction•3 minutes
- Online Offline Mode•6 minutes
- Bidirectional RNN•9 minutes
- LSTM - Part 1•5 minutes
- LSTM - Part 2•3 minutes
- LSTM - Part 3•2 minutes
- LSTM - Part 4•8 minutes
- LSTM - Part 5•6 minutes
- LSTM Equation•3 minutes
- Gated Recurrent Network (GRU)•12 minutes
1 assignment•Total 15 minutes
- Recurrent Neural Networks: LSTM - Assessment•15 minutes
In this module, we will apply RNN techniques to develop a Part-Of-Speech tagger for natural language processing tasks. Through an extended case study spread across multiple sessions, we will develop, evaluate, and refine the performance of the Part-Of-Speech tagger.
What's included
9 videos
9 videos•Total 62 minutes
- Part-Of-Speech Tagger Case-Study (Part-1)•8 minutes
- Part-Of-Speech Tagger Case- Study (Part-2)•8 minutes
- Part-Of-Speech Tagger Case- Study (Part-3)•5 minutes
- Part-Of-Speech Tagger Case- Study (Part-4)•10 minutes
- Part-Of-Speech Tagger Case- Study (Part-5)•10 minutes
- Part-Of-Speech Tagger Case- Study (Part-6)•7 minutes
- Part-Of-Speech Tagger Case- Study (Part-7)•5 minutes
- Part-Of-Speech Tagger Case- Study (Part-8)•7 minutes
- Part-Of-Speech Tagger Case- Study (Part-9)•2 minutes
In this module, we will delve into the practical application of RNNs for text generation by exploring a comprehensive code generator case study divided into four parts. Each part builds on the previous one, enhancing our understanding and skills in using RNNs for generating coherent text.
What's included
4 videos1 reading2 assignments
4 videos•Total 28 minutes
- Text Generation: Code Generator Case- Study (Part-1)•14 minutes
- Text Generation: Code Generator Case- Study (Part-2)•7 minutes
- Text Generation: Code Generator Case- Study (Part-3)•3 minutes
- Text Generation: Code Generator Case- Study (Part-4)•4 minutes
1 reading•Total 10 minutes
- Conclusion to the Course 'Advanced CNNs, Transfer Learning, and Recurrent Networks'•10 minutes
2 assignments•Total 75 minutes
- Text Generation Using RNN - Assessment•15 minutes
- Full Course Assessment•60 minutes
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
Explore more from Machine Learning
- Status: Free Trial
Course
- Status: Free Trial
- Status: Free Trial
- Status: Free Trial
Specialization
Why people choose Coursera for their career
Frequently asked questions
Yes, you can preview the first video and view the syllabus before you enroll. You must purchase the course to access content not included in the preview.
If you decide to enroll in the course before the session start date, you will have access to all of the lecture videos and readings for the course. You’ll be able to submit assignments once the session starts.
Once you enroll and your session begins, you will have access to all videos and other resources, including reading items and the course discussion forum. You’ll be able to view and submit practice assessments, and complete required graded assignments to earn a grade and a Course Certificate.
More questions
Financial aid available,