Convolutional Networks & Vision Basics
Conv arithmetic, ResNets, transfer learning, and what detection and segmentation actually measure
Understand and debug convolutional vision models: why convolution (locality, weight sharing, translation equivariance) and its parameter savings over fully connected layers, the exact output-size formula with padding, stride and dilation, receptive-field growth, 1x1 and depthwise-separable convolutions with their FLOP and parameter ratios, pooling vs strided convs and global average pooling, the LeNet to AlexNet to VGG to ResNet lineage with bottleneck blocks, EfficientNet and ConvNeXt, and the ViT bridge, CNN training details (BatchNorm placement, augmentation, normalization statistics, resolution), transfer learning (feature extraction, fine-tuning, discriminative learning rates, linear probes, domain gap), the task landscape with exact metrics (top-k, IoU, anchors vs anchor-free, NMS, COCO mAP, U-Net, mIoU and Dice, keypoints), Grad-CAM, efficiency, and a worked example with a verified 4-layer CNN shape and parameter count, a receptive-field calculation and mAP computed by hand from a tiny detection table.
Practice questions (6)
-
View →
Shapes, Parameters and Receptive Field of a ResNet-Style Stem
Intermediate · Free -
View →
Explain Residual Blocks and the Bottleneck's Parameter Savings
Intermediate · Free -
View →
Transfer-Learning Plan for 2,000 Chest X-Rays
Advanced -
View →
NMS in a Crowded Scene: Why a Person Disappears
Intermediate -
View →
Choosing a Segmentation Metric When the Tumour Is 1% of Pixels
Intermediate