← 📊 Evaluation & ML FoundationsNEXT IN EVALUATION & ML FOUNDATIONSTransfer Learning→
Core
CV Architectures: ResNets, ViT, Detection
Modern computer vision rests on three pillars: residual connections that let CNNs go hundreds of layers deep without degrading, Vision Transformers that patchify an image and run self-attention instead of convolutions, and detection heads (one-stage vs two-stage) scored by mAP after non-maximum suppression. Applied AI interviews probe this to check you can pick an architecture, fine-tune a pretrained backbone, and reason about latency vs accuracy rather than train from scratch.
a free account unlocks the core curriculum tier · no card
RELATED CONCEPTS
PRACTICE THIS IN REAL QUESTIONS
Machine Learning & Data ScienceHow would you build an object detection system that detects and localizes objects in images?→System Design for AI in ProductionDesign an object detection service (detect and localize objects in images at scale).→Machine Learning & Data ScienceExplain MLE vs MAP and apply Bayes' theorem to a medical-test (base-rate) problem.→Machine Learning & Data ScienceHow do CNNs work? Explain convolution, pooling, and the receptive field.→Machine Learning & Data ScienceHow does a Vision Transformer (ViT) work, and when does it beat a CNN?→Machine Learning & Data ScienceWhat is transfer learning, and how do you decide whether to freeze, fine-tune, or use feature extraction?→
COMPANIES THAT ASSUME THIS