Weak Supervision Courses and Certifications

USC Information Sciences Institute

Towards Open World Event Knowledge Extraction with Weak Supervision

Explore open-world event knowledge extraction using weak supervision. Learn query-and-extract paradigms and self-training techniques to improve extraction capabilities across domains and languages with minimal human effort.

• YouTube
• 52 minutes
• On-Demand
• Free Video

Self-Training - Weak Supervision Using Untrained Neural Nets for MR Reconstruction - Beliz Gunel

Exploring untrained neural networks for MR reconstruction, comparing self-training and weak supervision methods to improve performance with limited data while addressing slow inference times.

• YouTube
• 47 minutes
• On-Demand
• Free Video

Snorkel AI

Scaling Past Rule-Based Systems at the Petabyte Level

Discover how weak supervision scales NLP problems on petabyte-level data, surpassing traditional rule-based and expert-curated systems.

• YouTube
• 25 minutes
• On-Demand
• Free Video

Aleksa Gordić - The AI Epiphany

OpenAI Whisper - Robust Speech Recognition via Large-Scale Weak Supervision

Explore OpenAI's Whisper: a robust speech recognition system using large-scale weak supervision. Dive into the paper, code, and architecture, covering dataset collection, evaluation metrics, and practical implementation.

• YouTube
• 1 hour 3 minutes
• On-Demand
• Free Video

Adversarial Scene Editing: Automatic Object Removal from Weak Supervision

Learn to automatically remove objects from images using weak supervision, exploring mask generation and image inpainting techniques for seamless scene editing.

• YouTube
• 30 minutes
• On-Demand
• Free Video

Snorkel AI

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
• On-Demand
• Free Video

Snorkel AI

Extending Weak Supervision Beyond Classification - New Research Insights

Explore groundbreaking research extending weak supervision to new task types, including ranking, and its potential impact on AGI superalignment.

• YouTube
• 25 minutes
• On-Demand
• Free Video

Snorkel AI

Weak Supervision and Next-Gen AI-Based Threat Detection

Explore weak supervision for efficient AI-based threat detection in network security, leveraging analyst heuristics to build predictable models and overcome traditional machine learning challenges.

• YouTube
• 27 minutes
• On-Demand
• Free Video

Snorkel AI

How Comcast Powers AI Speech Recognition with Weak Supervision

Explore Comcast's innovative approach to AI speech recognition using weak supervision and efficient inference techniques, achieving improved accuracy and speed for voice-enabled smart TVs.

• YouTube
• 28 minutes
• On-Demand
• Free Video

Snorkel AI

LIGER: Fusing Model Embeddings and Weak Supervision for Improved NLP and Vision Tasks

Explore LIGER: a novel approach fusing foundation model embeddings with expert-driven labeling functions to enhance NLP and vision tasks.

• YouTube
• 11 minutes
• On-Demand
• Free Video

Machine Learning with Small Data Part 1

Discover modern deep learning techniques for training effective models with limited datasets, addressing challenges in healthcare, military, and industry applications.

• Coursera
• 14 hours 21 minutes
• On-Demand
• Paid Course

Aladdin Persson

Whisper Paper Explained - Robust Speech Recognition via Large-Scale Weak Supervision

Detailed explanation of OpenAI's Whisper model for speech recognition, covering dataset collection, model architecture, experiments, and scaling considerations.

• YouTube
• 33 minutes
• On-Demand
• Free Video

Simons Institute

Weak-to-Strong Generalization: Exploring Supervision Methods for Advanced Language Models

Explore how weak model supervision can elicit capabilities from stronger AI models, examining implications for alignment and scaling of techniques like RLHF through empirical studies.

• YouTube
• 43 minutes
• On-Demand
• Free Video

Yannic Kilcher

TAPAS - Weakly Supervised Table Parsing via Pre-training

Explore TAPAS, an innovative approach to table parsing and question answering using pre-training and weak supervision, outperforming traditional semantic parsing models with a simpler architecture.

• YouTube
• 32 minutes
• On-Demand
• Free Video

MLOps.community

Automating Data Annotation with Large Language Models - Workshop 1

Explore techniques for automating data annotation using Large Language Models. Learn workflows, result interpretation, validation, and integration into machine learning pipelines for efficient model finetuning.

• YouTube
• 1 hour 3 minutes
• On-Demand
• Free Video