Snorkel AI Courses

Data as the Programming Interface - The Future of AI Development

Explore how data-centric approaches revolutionize AI development, focusing on specialized evaluation, fine-grained analysis, and scalable solutions for capturing human feedback in enterprise systems.

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

The Essentials of Evaluating LLM Systems

Master practical techniques for evaluating LLM systems, from defining criteria and selecting evaluators to implementing heuristic models and conducting nuanced assessments for enterprise AI applications.

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

Optimizing Generative AI Systems with AWS and Snorkel

Discover how to optimize Generative AI systems by combining Snorkel Flow with AWS Bedrock and SageMaker, focusing on RAG workflow improvements, data labeling techniques, and enterprise deployment strategies.

• YouTube
• 1 hour 9 minutes
• Self-Paced
• Free Video

Improving the Accuracy of Domain Specific Tasks with LLM Distillation

Discover how to distill large language models into smaller, efficient ones for domain-specific tasks, balancing accuracy with cost and latency through techniques like weak supervision and limited-data fine-tuning for enterprise deployment.

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

Evaluating Generative AI: From Specialized Metrics to Actionable Insights

Discover a structured approach to evaluating GenAI systems through specialized metrics, data slicing, and actionable insights for enterprise-specific requirements and improved performance outcomes.

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

Building Accurate Prompts for Enterprise Chatbots Using Financial Datasets

Master prompt engineering techniques for enterprise chatbots, focusing on financial datasets and CLOs. Learn iterative refinement, performance evaluation, and optimization strategies for creating precise LLM outputs.

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

Prompt Engineering Techniques: A Practical Guide to Enhancing AI Outputs

Master practical prompt engineering techniques, from basic parameters to advanced workflows, with hands-on demonstrations using Snorkel Flow for optimizing AI model outputs at enterprise scale.

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

How to Build RAG Applications with Snorkel AI and AWS

Discover how to build end-to-end RAG systems using Snorkel AI and AWS, covering data ingestion, document chunking, embedding generation, vector stores, and LLM inference with Anthropic's Claude for reliable, grounded AI responses.

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

Fine-tuning AI Models for Healthcare Policy Analysis with AWS and Snorkel Flow

Master AWS and Snorkel Flow integration to enhance AI models through structured fine-tuning workflows, focusing on improving accuracy in analyzing health insurance policy documents and generating reliable responses.

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

Knowledge Distillation Demystified: Techniques and Applications

Explore knowledge distillation techniques for optimizing ML models in NLP. Learn extraction and transfer methods, target skill identification, and innovative data-centric approaches for efficient model training.

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

Model Distillation - From Large Models to Efficient Enterprise Solutions

Explore model distillation techniques for efficient enterprise AI systems. Learn strategies, real-world applications, and best practices to optimize performance and minimize costs in natural language processing.

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

Curate Training Data via Labeling Functions - 10 to 100x Faster

Accelerate data labeling for AI models using programmatic techniques. Learn to capture SME knowledge, improve label accuracy, and explore real-world use cases in banking, pharma, and healthcare.

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

Revolutionizing Data Analysis: Combining LLM, RAG, and Domain Knowledge

Leverage NLP and RAG systems to extract insights from structured and unstructured data, generate actionable insights, and empower data-driven analysis without SQL.

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

Task Me Anything: Revolutionizing Multimodal Model Benchmarking

Explore Task Me Anything platform for efficient multimodal model evaluation. Learn programmatic task generation and active learning techniques to create custom benchmarks for data science projects.

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

Alfred: Building Training Data with Foundation Models and Weak Supervision - Snorkel AI

Streamline data labeling with Alfred, combining foundation models and weak supervision to create high-quality training datasets for academic research and machine learning projects.

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