Module Question 7
- What distinguishes “deep learning” from traditional machine learning?
- What are convolutional layers and pooling layers in a CNN, and what is their primary function?
- Why are CNNs particularly well-suited for image processing tasks compared to standard neural networks?
- Name two major applications of CNNs in the real world
Answer:
- Deep learning uses neural networks with multiple layers to learn complex patterns from large amounts of data. Unlike traditional machine learning, which often requires humans to select and extract features manually, deep learning can automatically learn useful features from raw data.
- Convolutional layers use filters to detect features such as edges, shapes, and textures in images. Pooling layers reduce the size of feature maps while keeping important information. Together, they help CNNs process images efficiently.
- CNNs are well-suited for image processing because they can recognize spatial patterns and local features in images. They use fewer parameters than standard fully connected neural networks, making them more efficient at processing image data
- Two major applications of CNNs are:
Medical imaging: Detecting diseases from X-rays, MRI scans, and other medical images.
Autonomous vehicles: Recognizing pedestrians, traffic signs, and other vehicles to help cars navigate safely.