Part 3/11:

• Convolutional Neural Networks (CNNs): The most prevalent architecture, extensively used for image classification and segmentation tasks. CNNs process images through layers of filters that detect features like edges, textures, or specific patterns relevant to medical conditions.

• Capsule Networks (Set Caps): A newer, less common architecture emphasized during the session. Caps are designed to better understand spatial hierarchies and relationships within image data, offering a promising alternative to CNNs. The presenter shared insights from personal research at IIT Hyderabad, noting that capsule networks perform comparably to CNNs but are more capable in certain complex segmentation tasks.