🧠 Deep Learning Lectures §

My notes on the VHB course “Deep Learning 4 Beginners”, which is part of my extra classes as part of my B.A. in Media Informatics at the University of Regensburg.

Course description: Deep Learning (DL) has attracted much interest in a wide range of applications such as image recognition, speech recognition, and artificial intelligence, both from academia and industry. In this course, you will learn the core elements of neural networks and deep learning, such as convolutional layers, activation and loss functions, and regularization techniques.

🗓️ Plan §

📑 VL01 Introduction §

• ✍️ (DL) Notation
• What is 🧩 Pattern Recognition?
  • 🧩 Pattern
  • 🔵 Feature
• How does 🌅 Image Processing work?
  • 🏛️ Classical image processing pipeline
  • 🪝 Deep learning image processing pipeline
• What is a 🧠 Perceptron?

📑 VL02 Signal Processing - 1D §

• What is ⚙️ System Theory?
  • ⚙️ System (System Theory)
  • 📶 Signal
• What are ⧉ Complex numbers?
• What’s the ⛓️ Fourier Series good for?
• What does the ↪️ Fourier Transform do?
• How does 🙏 Convolution work?

📑 VL Signal Processing - 2D §

• What is an 🏙️ Image derivative?
• How does convolution work in 2D?
• What is 🌅 Image filtering?