zkML (Zero-Knowledge Machine Learning)
By CoinGecko | Updated on Jan 11, 2024
Zero-Knowledge Machine Learning (zkML) refers to an emerging method in the field of onchain machine learning, integrating the principles of zero-knowledge proofs with ML. Zero-knowledge proofs are cryptographic protocols allowing one party to confirm the truth of a statement to another party without revealing any information beyond the statement's validity. zkML provides a cryptographic certificate verifying an ML model's inference, including details like model size and parameters, ensuring that a prompt has been executed without revealing sensitive data.
Related Terms
Seed
A value used to initiate generation of pseudorandom number, ususally a string of 12 commen English words.
Proof of Stake (PoS)
A consensus algorthm that assigns block validation queue based on the coins/token locked in by the validator.
Full Node
Full Nodes are computers that verify the set of rules that are built into the protocols of a given cryptocurrency.
Stop-loss Order
Conditional market order to sell at the next available price, excuted if the price of an asset falls below set-upon limit
Hungry for more knowledge?
Back to Glossary or Subscribe to our newsletter.