unsupervised learning
Training method where a model learns patterns from data without explicit labeled correct answers; how more contemporary AI generally works.
As defined in Erik Hoel on the Threat to Humanity from AI
Other definitions
Machine learning approach where models learn patterns from data without explicit labels or targets; in OpenAI's 2017 paper, unsupervised prediction of the next character led to emergence of semantic understanding.
Sam Altman and Greg Brockman on AI and the Future (Full Audio)Training a model on unlabeled data, letting it discover structure on its own, rather than on labeled input-output examples.
Amjad Masad - The Future of Software Creation - [Invest Like the Best, EP.310]
Where it comes up · 11
- Machine Learning in Investing3 claims
- OpenAI Co-Founder: “I just had to Quit”2 claims
- Why Venture is Hard2 claims
- 180 | Camilla Pang on Instructions for Being Human2 claims
- How LLMs Took Over The World2 claims
- How ChatGPT Works Technically For Beginners2 claims
- You need to learn AI in 2024! (And here is your roadmap)2 claims
- Jeff Dean & Noam Shazeer — 25 years at Google: from PageRank to AGI1 claim
and 3 more
Most important claims · 10 of 19Search all claims for “unsupervised learning” →
- At OpenAI from the earliest days, the fundamental hypothesis was that predicting the next token (word, pixel, etc.) is sufficient for solving unsupervised learning, and prediction is equivalent to compression of data.The Mastermind Behind GPT-4 and the Future of AI | Ilya Sutskever
- Machine learning models can be organized in a two-by-two grid: classification versus regression on one axis and supervised versus unsupervised on the other, with linear and logistic regression, neural networks, clustering, and trees placed within it.Machine Learning in Investing
- Unlike traditional algorithms which are scrutable and transparent, neural networks are trained by mathematically reconfiguring connections to produce good outputs—analogous to alien neuroscientists rewiring a child's brain to pass a math test—so even though we can make them do impressive things, our ability to understand why they work lags far behind, leaving us epistemically unable to predict their behavior.Erik Hoel on the Threat to Humanity from AI
- Learning to recognize terminology like supervised/unsupervised learning and transformers helps you work out what the best tool is for the job, preventing wasteful use of overly complex models when simpler approaches suffice.You need to learn AI in 2024! (And here is your roadmap)
- Human babies learn language through unsupervised learning by observing and listening to multiple adults speaking about various topics, finding patterns in this unsupervised linguistic data without any formal grammar instruction, even before formal schooling begins.How ChatGPT Works Technically For Beginners
- ChatGPT's context-understanding neural network is trained using unsupervised learning by collecting all text-based content from the internet (blog posts, websites, etc.) without human annotation and dumping it into the neural network, allowing the network to discover linguistic patterns autonomously.How ChatGPT Works Technically For Beginners
- OpenAI's sentiment neuron paper showed a model trained only to predict the next word learned sentiment without labeled data, and this unsupervised approach foreshadowed the scaled language models that followed.Amjad Masad - The Future of Software Creation - [Invest Like the Best, EP.310]
- An early Google Brain unsupervised model trained on 10 million randomly selected YouTube frames across 2,000 computers using 16,000 cores spontaneously developed a high-level neuron that activated for cat faces—never having been told what a cat was—and the same model, about 50x bigger than prior models, improved the state of the art on the ImageNet 20,000-category challenge by 60% relative, demonstrating that scaling neural nets works.Jeff Dean & Noam Shazeer — 25 years at Google: from PageRank to AGI
- Early task-specific networks could only form narrow abstractions—each trained on one specific task, producing siloed systems good at one thing only—so the idea of a single neural network that could do anything in general still seemed hopeless, and as of 2016 unsupervised learning was an unsolved problem with no clear approach.How LLMs Took Over The World
- In 2016, unsupervised learning was an unsolved problem in machine learning with no clear insight into how to achieve it, and the breakthrough came when AI achieved nature's third layer of learning: language.How LLMs Took Over The World