Few-shot Learning Courses and Certifications

Coursera

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

Apply pretrained models, semantic embeddings, and transfer learning to build zero-shot and few-shot pipelines using prompt engineering, prototypical networks, and contrastive learning when labeled data is scarce.

• Coursera
• 3 weeks, 1 hour a week
• Self-Paced
• Paid Course

HuggingFace

Few-Shot Learning in Production

Train and deploy few-shot language models with SetFit, then compress them through knowledge distillation and quantization for efficient inference.

• YouTube
• 1 hour 22 minutes
• Self-Paced
• Free Video

GAIA

Few-Shot Learning for Health: How Sleep Cycle Separates Multiple People's Snoring

Discover how Sleep Cycle uses few-shot learning to differentiate snoring sounds, enhancing sleep analysis and health insights. Learn about the importance of snoring detection for overall well-being.

• YouTube
• 26 minutes
• Self-Paced
• Free Video

OpenSource Connections

A Practical Approach for Few Shot Learning with SetFit - Haystack EU 2023

Explore SetFit for few-shot learning in classification and ranking, with a focus on legal research applications. Discover its potential to outperform GPT-3 in label-scarce settings.

• YouTube
• 28 minutes
• Self-Paced
• Free Video

Zero-Shot and Few-Shot Learning

56 ratings at Udacity

Optimize generative AI prompts with zero-shot and few-shot learning techniques.

• Udacity
• 1 hour
• Self-Paced
• Free Certificate

Machine Learning with Small Data Part 1

Learn deep learning techniques for data-scarce settings: transfer learning, domain adaptation with DDC and DANNs, weak supervision, zero-shot learning, and few-shot Matching Networks.

• Coursera
• 7 weeks, 2 hours a week
• Self-Paced
• Paid Course

Machine Learning with Small Data Part 2

Train models that thrive on limited data: multi-task learning, MAML and prototypical networks, generative and physics-based augmentation, NeRF, diffusion models, and 3D Gaussian Splatting.

• Coursera
• 7 weeks, 2 hours a week
• Self-Paced
• Paid Course

Deep Multi-Task and Meta Learning - Autumn 2022

Master multi-task and meta-learning algorithms to build AI systems that efficiently learn new tasks from limited data and transfer knowledge across domains.

• YouTube
• 21 hours 30 minutes
• Self-Paced
• Free Video

Stanford Seminar - Transformers in Language: The Development of GPT Models Including GPT-3

Trace the evolution from n-gram and recurrent models to GPT-3 and Codex, including few-shot learning, image generation, and code generation.

• YouTube
• 49 minutes
• Self-Paced
• Free Online Course

Donato Capitella

GPT, Instruction Fine-Tuning, and Reinforcement Learning from Human Feedback - Understanding ChatGPT's Foundation

Delve into the technical evolution of GPT models, exploring their architecture, instruction fine-tuning processes, and the role of RLHF in developing more capable language models.

• YouTube
• 18 minutes
• Self-Paced
• Free Video

James Briggs

GUI-Based Few Shot Classification Model Trainer - Demo

Use vector search to focus annotation and fine-tuning on samples most likely to improve classification with fewer labeled examples.

• YouTube
• 32 minutes
• Self-Paced
• Free Video

Google Cloud Tech

Tuning Foundation Models: A Comprehensive Guide

Explore techniques for customizing foundation models with your data, improving performance across tasks while understanding limitations and future prospects.

• YouTube
• 42 minutes
• Self-Paced
• Free Video

MIT HAN Lab

Efficient Fine-tuning and Prompt Engineering - Lecture 20

Explore efficient fine-tuning techniques and prompt engineering strategies for optimizing large language models in machine learning applications.

• YouTube
• 1 hour 17 minutes
• Self-Paced
• Free Video

Trelis Research

Automated Prompt Engineering with DSPy - A Comprehensive Tutorial

Explore automated prompt engineering using DSPy, covering installation, benchmarking, chain of thought, vector search, few-shot examples, multi-hop queries, and result comparisons.

• YouTube
• 46 minutes
• Self-Paced
• Free Video

MLOps World: Machine Learning in Production

How Many Labelled Examples Do You Need for a BERT-sized Model to Beat GPT4 on Predictive Tasks?

Explore the effectiveness of in-context learning vs. labelled data for predictive tasks, comparing BERT-sized models to GPT-4 in text categorization and entity recognition.

• YouTube
• 28 minutes
• Self-Paced
• Free Video