Supervised learning
Training method where a model is given inputs with known correct answers and its connections are adjusted to produce those answers.
As defined in Erik Hoel on the Threat to Humanity from AI
Other definitions
Machine learning where models are trained on data with human-provided labels, learning to map inputs to outputs based on these labeled examples
Yann LeCun's $1B Bet Against LLMs [Part 1]
Where it comes up · 12
- Yann LeCun's $1B Bet Against LLMs [Part 1]5 claims
- Machine Learning in Investing3 claims
- AI: Grappling with a New Kind of Intelligence | World Science Festival3 claims
- You need to learn AI in 2024! (And here is your roadmap)3 claims
- Ilya Sutskever: Deep Learning | Lex Fridman Podcast #942 claims
- Richard Sutton – Father of RL thinks LLMs are a dead end2 claims
- Freenet - Services Without Servers2 claims
- How to Live with Computers1 claim
and 4 more
Most important claims · 10 of 25Search all claims for “Supervised learning” →
- 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
- A system trained with self-supervised learning on images needs only 2-3 examples of a new object (like an elephant) to recognize it, making it more efficient than supervised learning which requires thousands of labeled examples—this is closer to how humans learn.AI: Grappling with a New Kind of Intelligence | World Science Festival
- 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
- GPT-1's success with a two-stage training process—extensive self-supervised pre-training on 7,000 books followed by supervised fine-tuning on labeled language tasks—proved that self-supervised pre-training could break models free from dependence on human-labeled data at scale.Yann LeCun's $1B Bet Against LLMs [Part 1]
- Children learn general representations with very few explicitly labeled examples, unlike supervised learning approaches like AlexNet that required the enormous manually-labeled ImageNet dataset, suggesting human learning relies on different mechanisms than supervised learning.Yann LeCun's $1B Bet Against LLMs [Part 1]
- Supervised/imitation learning is not a basic process by which animals learn; psychology shows the basic animal learning processes are prediction and trial-and-error control, and supervised learning with examples of desired behavior does not occur in nature.Richard Sutton – Father of RL thinks LLMs are a dead end
- Self-supervised learning achieved success in language (next-token prediction) much faster than in vision and other modalities, suggesting language is a particularly rich and informative domain for self-supervised pre-training.Yann LeCun's $1B Bet Against LLMs [Part 1]
- Supervised learning requires large labeled datasets where a human tells the system what each input corresponds to, making it impractical for obscure languages, unwritten languages, or specialized domains where labeled data is scarce; this limitation motivated the development of self-supervised learning.AI: Grappling with a New Kind of Intelligence | World Science Festival
- Self-supervised learning works by showing models text with missing words, removing words, and training the system to predict the missing words, which forces the network to learn representations that capture meaning, syntax, grammar, and internal structure of language that can then be applied to downstream tasks.AI: Grappling with a New Kind of Intelligence | World Science Festival
- Self-supervised pre-training on self-supervised learning is the 'bulk of the cake' for intelligence, supervised learning is the 'icing,' and reinforcement learning is the 'cherry'—a hierarchy suggesting reinforcement learning alone is too inefficient to reach human-level intelligence.Yann LeCun's $1B Bet Against LLMs [Part 1]