BitTensor: A Peer-to-Peer Intelligence Market
Abstract
As with other commodities, markets could help us efficiently produce machine intelligence. We propose a market where intelligence is priced by other intelligence systems peer-to-peer across the internet. Peers rank each other by training neural networks which learn the value of their neighbors. Scores accumulate on a digital ledger where high ranking peers are monetarily rewarded with additional weight in the network. However, this form of peer-ranking is not resistant to collusion, which could disrupt the accuracy of the mechanism. The solution is a connectivity-based regularization which exponentially rewards trusted peers, making the system resistant to collusion of up to 50 percent of the network weight. The result is a collectively run intelligence market which continual produces newly trained models and pays contributors who create information theoretic value.
- Publication:
-
arXiv e-prints
- Pub Date:
- March 2020
- DOI:
- 10.48550/arXiv.2003.03917
- arXiv:
- arXiv:2003.03917
- Bibcode:
- 2020arXiv200303917R
- Keywords:
-
- Computer Science - Artificial Intelligence;
- Computer Science - Machine Learning;
- Computer Science - Multiagent Systems;
- I.2.6;
- I.2.11;
- C.2.4
- E-Print:
- This paper is incomplete. A more complete version is being worked on at the moment. Additionally one of the authors (daniel attevelt) has been removed from the work and so this paper is now obsolete from both a content and an author perspective. Please help us remove it