Self-Supervised Learning

Training approach that creates predictive learning signals from raw data without manually labeled targets.

Core metadata

ID: self_supervised_learning
Era: Modern
First known date: 2020 (exact)
Region: Global / multiple regions
Review status: source_checked
Maturity: established

Prerequisites

Dependents

Model Pretraining & Fine-Tuning (model_pretraining_finetuning)

Fields

Artificial Intelligence & Machine Learning

Field lanes

Artificial Intelligence & Machine Learning: Foundation Models

Node sources

Language Models are Few-Shot Learners (arXiv, 2020, primary_paper) • Supports: node, maturity
On the Opportunities and Risks of Foundation Models (arXiv / Stanford CRFM, 2021, primary_paper) • Supports: node, maturity

Prerequisite edge evidence

Edge/source evidence summary:

Prerequisite edges: 3
Average edge confidence: 68%
Prerequisite sources: 3
expert_inference: 3

Prerequisite	Type	Confidence	Evidence level	Note	Sources
Deep Learning Neural Networks (deep_learning_neural_networks)	enabling	68%	expert_inference	Deep Learning Neural Networks provides a capability that enables this technology without being the only possible path.	Language Models are Few-Shot Learners (arXiv, 2020, primary_paper) • Supports: node, maturity, edge
Big Data Analytics & Computational Statistics (big_data_analytics_computational_statistics)	enabling	68%	expert_inference	Big Data Analytics & Computational Statistics provides a capability that enables this technology without being the only possible path.	Language Models are Few-Shot Learners (arXiv, 2020, primary_paper) • Supports: node, maturity, edge
ML Benchmark Datasets (ml_benchmark_datasets)	enabling	68%	expert_inference	ML Benchmark Datasets provides a capability that enables this technology without being the only possible path.	Language Models are Few-Shot Learners (arXiv, 2020, primary_paper) • Supports: node, maturity, edge

This page is generated from canonical era JSON and is indexable by URL.