Training: Convolutional Neural Networks (CNNs)
Level
IntermediateDuration
16h / 2 daysDate
Individually arrangedPrice
Individually arrangedTraining: Convolutional Neural Networks (CNNs)
An intensive, hands-on training focused on Convolutional Neural Networks (CNNs). Over this two-day course, participants will gain both solid theoretical knowledge and—most importantly—practical skills in designing, implementing, and training CNNs. The course blends theory with practice, emphasizing 80% workshops and 20% lectures.
What will you learn?
- How to design and implement advanced CNN architectures
- Techniques for optimization and fine-tuning of convolutional models
- Practical use of transfer learning in computer vision tasks
- How to deploy and optimize CNN models in real-world projects
Required technical skills
- Basic knowledge of Python
- At least minimal experience with machine learning libraries (e.g., scikit-learn, TensorFlow, or PyTorch)
- Basic knowledge of neural networks and machine learning
- Ability to work in a Jupyter Notebook environment
Who is this training for?
This training is designed for developers, data scientists, machine learning engineers, and researchers who want to deepen their knowledge of CNNs and acquire practical skills in implementing and optimizing them.
Training Program
-
Day 1
- Introduction to neural networks and convolutional networks
- Basics of neural network architecture
- CNN architecture overview
- Comparison of CNNs vs. traditional neural networks
- Convolutional and pooling layers
- Implementing convolutional layers in PyTorch
- Designing and optimizing pooling layers
-
Workshop: Building a simple CNN
- Creating a CNN model from scratch
- Analyzing the impact of different architectures on performance
-
Transfer learning techniques in CNNs
- Using pretrained models
- Fine-tuning models on custom datasets
-
Day 2
- Advanced CNN architectures
- Implementing ResNet and Inception
- Comparative performance analysis of different architectures
-
CNN optimization and regularization
- Regularization techniques: dropout, batch normalization
- Hyperparameter optimization strategies
-
Workshop: Solving complex computer vision problems
- Implementing an image classification model
- Building an object detection system
-
Deploying CNN models in practice
- Performance optimization
- Integrating CNNs into real-time applications
