Image
Spatial raster data used in classification, detection, segmentation, and multimodal systems.
Lessons
Formal explanations, examples, simulations, and checkpoints.
Images are data contracts
Image preprocessing is model code; version and test it from raw bytes to final tensor.
Image MLConvolution under the microscope
Convolution is a repeated local dot product whose shape and spatial behavior follow directly from kernel, padding, stride, and dilation.
Image MLReceptive fields, normalization, and residuals
Depth works when context grows deliberately and identity paths keep shapes and gradients connected.
Image MLTransfer learning for classification, detection, and segmentation
Transfer the representation in measured stages, while letting the required output and leakage-safe split define the task.
Image MLVision in the wild: thresholds, latency, and drift
Production vision is a thresholded, timed, monitored decision system—not an accuracy number attached to a model file.
Courses & assignments
Dependency-authoritative learning units.
Casebook
Reported facts and course reconstructions.