Course overview
First, you’ll learn the relevance of CNN in the field of computer vision, and you’ll implement both basic and complex CNN for multi-class classification tasks in TensorFlow. You’ll then advance to understanding how a CNN model learns different features across its layers and attempts to improve the model’s performance.
You’ll learn different regularization techniques to tackle overfitting when building deep learning models in TensorFlow.
Next, you’ll see the importance of complicated models like ResNet for computer vision tasks, and you’ll implement a ResNet-based, pre-trained model on advanced CNN architecture.
Finally, you’ll learn how to use previously trained models for other similar tasks on a different dataset than the original model was trained on.
Best of all, you’ll learn by doing — you’ll practice and get feedback directly in the browser. At the end of the course, you’ll apply your new skills to a project to create a computer vision model that can detect if a patient has pneumonia using an X-ray scan.
Key skills
- Explaining the basics of convolutional neural networks (CNNs)
- Building and train a CNN for image classification tasks
- Implementing regularization techniques
- Fine-tuning a CNN model using transfer learning
Course outline
Convolutional Neural Networks for Deep Learning [6 lessons]
Introduction to CNNs 2h
Lesson Objectives- Describe the basics of digital images
- Describe the basic components of convolutional neural networks (CNNs)
- Explain the workings of convolutional neural networks (CNNs)
- Summarize the applications and advantages of using CNNs
- Build and train a basic CNN for multi-class classification in Keras
CNN Architecture 2h
Lesson Objectives- Build and train a CNN model based on the AlexNet architecture
- Explain the importance of initializing weights in a CNN
- Interpret the model's performance
- Improve a model’s performance using hyperparameter optimization
- Identify what different layers of a CNN learn
- Visualize outputs of different layers of a trained CNN model
Regularization in Deep Learning 2h
Lesson Objectives- Implement early stopping as a regularization technique
- Implement dropout as a regularization technique
- Implement batch normalization as a regularization technique
- Augment images using different approaches
Advanced CNN Architecture 2h
Lesson Objectives- Describe the basic components of Residual Neural Networks (ResNets)
- Explain the workings of ResNets
- Implement the ResNet18 architecture using the TensorFlow's Functional API
- Train and evaluate the ResNet18 model for a classification task
Transfer Learning 2h
Lesson Objectives- Explain transfer learning and its advantages
- Load a pre-trained model in Keras
- Freeze and unfreeze layers of a model
- Build and train a classifier using features from a pre-trained model
- Fine-tune a pre-trained model
Guided Project: Detect Pneumonia Using X-Ray Images with CNNs and Transfer Learning 2h
Lesson Objectives- Load and explore the dataset
- Build and train a simple CNN-based classifier
- Improve the CNN-based classifier's performance
- Build and train a classifier using transfer learning
- Improve the transfer learning-based classifier's performance
- Evaluate the models on the test set
Projects in this course
Detect Pneumonia Using X-Ray Images with CNNs and Transfer Learning
For this project, you’ll assume the role of a Deep Learning Engineer tasked with developing models to help hospitals diagnose pneumonia in children using chest X-ray images.
The Dataquest guarantee
Dataquest has helped thousands of people start new careers in data. If you put in the work and follow our path, you’ll master data skills and grow your career.
We believe so strongly in our paths that we offer a full satisfaction guarantee. If you complete a career path on Dataquest and aren’t satisfied with your outcome, we’ll give you a refund.
Master skills faster with Dataquest
Go from zero to job-ready
Learn exactly what you need to achieve your goal. Don’t waste time on unrelated lessons.
Build your project portfolio
Build confidence with our in-depth projects, and show off your data skills.
Challenge yourself with exercises
Work with real data from day one with interactive lessons and hands-on exercises.
Showcase your path certification
Share the evidence of your hard work with your network and potential employers.
Grow your career with
Dataquest.
98%
of learners recommend
Dataquest for career advancement
4.85
Dataquest rating
SwitchUp Best Bootcamps
$30k
Average salary boost
for learners who complete a path
Join 1M+ data learners on
Dataquest.
1
Create a free account
2
Choose a learning path
3
Complete exercises and projects
4