Zero-Shot & Few-Shot Learning: Master AI with Minimal Data

位教师：Hurix Digital

访问权限由 Coursera Learning Team 提供

3个模块

深入了解一个主题并学习基础知识。

中级等级

推荐体验

4 小时完成

灵活的计划

自行安排学习进度

3个模块

深入了解一个主题并学习基础知识。

中级等级

推荐体验

4 小时完成

灵活的计划

自行安排学习进度

您将获得的技能

要了解的详细信息

可分享的证书

添加到您的领英档案

作业

5 任务¹

AI 评分请参见免责声明

授课语言：英语（English）

了解顶级公司的员工如何掌握热门技能

了解关于 Coursera for Business 的更多信息

Petrobras, TATA, Danone, Capgemini, P&G 和 L'Oreal 的徽标

该课程共有3个模块

Zero-Shot & Few-Shot Learning is an intermediate-level course designed for data scientists, ML engineers, and AI practitioners who want to build models that perform well—even when labeled data is limited. Traditional supervised learning breaks down when examples are scarce or tasks are constantly evolving. This course shows you how to solve that problem using cutting-edge zero-shot and few-shot learning techniques.

You'll learn how to apply pre trained models, semantic embeddings, and transfer learning to generalize across tasks without retraining from scratch. Through case-driven videos, hands-on labs, and decision-focused projects, you'll explore tools like prompt engineering, prototypical networks, and contrastive learning. Along the way, you'll build and defend full pipelines tailored to real-world constraints—choosing the right method based on data availability, task requirements, and deployment goals. Whether you're diagnosing fraud with few samples or classifying new product types without labels, this course will equip you to build smarter, leaner models that learn more with less.

In this introductory lesson, learners will explore the core principles of zero-shot and few-shot learning, including how they differ from traditional supervised learning. Through clear examples and intuitive analogies, learners will build a foundational understanding of these approaches and why they matter in modern machine learning.

涵盖的内容

3个视频3篇阅读材料1个作业

3个视频总计19分钟

Introduction and Welcome 3分钟
Learning with Less: The Why Behind Zero-Shot and Few-Shot Approaches 8分钟
How Few Examples Can Be Enough: Real-World Use Cases in NLP, Finance & More 8分钟

3篇阅读材料总计24分钟

Welcome to the Course: Course Overview 4分钟
Zero-Shot vs. Few-Shot vs. Supervised: A Primer for ML Practitioners 10分钟
How It Works: Embeddings, Prompts, and Pretraining in Zero- and Few-Shot Learning 10分钟

1个作业总计20分钟

HOL: The Appropriate Choice — Zero-Shot, Few-Shot, or Supervised? 20分钟

In this lesson, learners will examine how pretrained models, semantic embeddings, and transfer learning enable generalization in low-data environments. They'll break down each component’s role through hands-on exercises and visualizations—gaining clarity on how models can recognize patterns or make predictions with minimal labeled data.

涵盖的内容

4个视频2篇阅读材料1个作业

4个视频总计29分钟

Pretrained Models: Why They Boost Low-Data Learning 8分钟
Semantic Embeddings: How Models Learn Meaning 7分钟
The Architecture Matters: LSTMs or BERT? 7分钟
MKeCL in Action: Few-Shot Diagnosis with Pre Trained Contrastive Learning 6分钟

2篇阅读材料总计18分钟

A Gentle Introduction to Transfer Learning 8分钟
From Embeddings to Transfer: Techniques That Generalize Well 10分钟

1个作业总计20分钟

HOL: Train from Scratch vs. Transfer: Test Generalization Power 20分钟

In this lesson, learners will evaluate and apply zero-shot and few-shot strategies—such as prompt engineering, meta-learning, and prototypical networks—to real-world tasks. Through scenario-based activities and model comparisons, learners will learn how to choose and implement the right method based on data limitations and task requirements.

涵盖的内容

4个视频1篇阅读材料3个作业

4个视频总计22分钟

Zero or Few? Choosing the Right Learning Strategy 8分钟
Auto-Harvest in Action: Few-Shot Learning Meets the Greenhouse 6分钟
Spotting the New Fraud: IFTrans and Few-Shot Classification 6分钟
Congratulations and Continuous Learning Journey 3分钟

1篇阅读材料总计10分钟

Prompt Engineering: A Practical Example 10分钟

3个作业总计70分钟

HOL: Scenario Match: Select the Right Few/Zero-Shot Approach 20分钟
From Concept to Deployment: Design a Zero- or Few-Shot Learning Pipeline for the Real World 30分钟
Final Assessment 20分钟