CompTIA · SecAI+ CY0-001
Training and prompts
SecAI+ CY0-001 · Lesson 2 of 18 · 10:09
YouTube loads only after you press play. This chapter opens at its timestamp in the full course. Watch on YouTube ↗
In this lesson
Prepare for the CompTIA SecAI+ CY0-001 exam. In this lesson: supervised, unsupervised, reinforcement, and federated learning, model validation, fine-tuning with epochs, pruning, and quantization, and prompt engineering: system and user prompts, system roles, zero-shot, one-shot, and multi-shot prompting, and prompt templates, with Fernhill Telecom as the running example. Includes three original practice questions.
Preview the topics
- Five hospitals want to train one shared model on patient records, but no record may leave its own hospital. Which training technique fits?
- A fraud model scores 98% on its training data, but only 60% on data that it never saw. What is the most likely problem?
- Fernhill’s application inserts each customer message into a fixed prompt, at a marked spot between delimiters. What is this?