Incorporating AI/Machine Learning (e.g., Recurrent Neural Networks) into EVM/Solidity via Oracles

External question — Ethereum Stack Exchange Author: Nathan Aw Original post: https://ethereum.stackexchange.com/questions/50450 License: CC BY-SA 4.0 — https://creativecommons.org/licenses/by-sa/4.0/ Adaptation: HTML converted to plain text; contact email addresses removed. I am exploring the viability and avenues to incorporate AI/ML with EVM and/or Smart Contracts via solidity or oracles. For example, I wish to leverage Recurrent Neural Networks, which demonstrates how to use a recurrent neural network to predict the next word in a sentence. I wish to predict what function the ethereum nodes will call as a first step to using AI/ML to make smart contracts even smarter.

External answer — Ethereum Stack Exchange Author: Jaime Original post: https://ethereum.stackexchange.com/a/50454 License: CC BY-SA 4.0 — https://creativecommons.org/licenses/by-sa/4.0/ Adaptation: HTML converted to plain text; contact email addresses removed. You could use: Oraclize or ETH-Tempus . In both cases you can develop an api for your ML application and with tehse services your can send a request and get the response from your API in your smart contract. Hope this helps

External answer — Ethereum Stack Exchange Author: Gokul Alex Original post: https://ethereum.stackexchange.com/a/94199 License: CC BY-SA 4.0 — https://creativecommons.org/licenses/by-sa/4.0/ Adaptation: HTML converted to plain text; contact email addresses removed. We could add RNN or LSTM to select the set of feeds from Chainlink Oracles or the Subgraphs of the Graph Protocol. The RNN or LSTM networks can be deployed on the Chainlink nodes to sample and select the particular pattern of feeds. With the recent addition of Offline reporting feature in Chainlink this becomes more useful.