← 📊 Evaluation & ML FoundationsNEXT IN EVALUATION & ML FOUNDATIONSAutoencoders and GANs→
Core
Transfer Learning
Transfer learning reuses a model pretrained on a large general corpus as the starting point for a new task, so you inherit learned features instead of training from scratch. The two modes are feature extraction (freeze the backbone, train only a new head) and fine-tuning (unfreeze some layers and keep training), and the choice turns on how much labeled data you have and how far the new domain has drifted. Applied AI interviews probe it because it is the default for vision and NLP when labels are scarce, and because candidates often fine-tune when they should freeze, or vice versa.
a free account unlocks the core curriculum tier · no card
RELATED CONCEPTS
PRACTICE THIS IN REAL QUESTIONS
Machine Learning & Data ScienceWhat is transfer learning, and how do you decide whether to freeze, fine-tune, or use feature extraction?→LLM & GenAI FundamentalsWhat is instruction tuning, and how does it differ from pretraining and alignment?→LLM & GenAI FundamentalsWhat is catastrophic forgetting, and how do you prevent it when fine-tuning or continually training an LLM?→LLM & GenAI FundamentalsWhen do you choose prompting vs RAG vs fine-tuning for a customer problem?→LLM & GenAI FundamentalsWalk through RLHF, then explain DPO and why it has largely displaced PPO-based RLHF.→LLM & GenAI FundamentalsExplain LoRA, QLoRA, and parameter-efficient fine-tuning. Why train a fraction of the parameters?→
COMPANIES THAT ASSUME THIS