Skip to content

Week #9 - Convolutional Neural Networks

In today's lecture, we'll dive into Convolutional Neural Networks (CNNs) and their foundational role in computer vision. We'll explore how these specialized architectures leverage spatial relationships in visual data, their core building blocks, and how they've revolutionized image processing tasks from classification to segmentation.

Learning objectives:

  • Understand the fundamental principles of computer vision and how CNNs process visual information
  • Master the key components of CNNs including convolutional layers, filters, pooling, and feature maps
  • Explore how convolution operations detect hierarchical features from edges to complex patterns
  • Learn common CNN architectures (LeNet, AlexNet, VGG, ResNet) and their historical significance
  • Implement basic CNN operations and visualize learned features at different network depths
  • Understand techniques for transfer learning and fine-tuning pre-trained CNN models
  • Apply CNNs to core computer vision tasks: image classification, object detection, and segmentation
  • Master practical considerations including data augmentation, batch normalization, and GPU acceleration
  • Explore modern architectural innovations like skip connections, inception modules, and attention mechanisms
  • Laboratory
  • TBA

Resources - TBA