How to Train AI using Bitcoin

Outsource the training to others

Previously, we have implemented a single-layer perceptron, which can be continuously trained on Bitcoin. This can quickly become prohibitively expensive when the dataset is large and it takes many iterations to find the desired weights.

We develop a contract to outsource the training. It is a public bounty that can be collected by anyone offering the right weights that make predictions match outputs for all training dataset inputs. The computationally intensive training is done off chain and the contract only verifies the training is valid, thus making training a perceptron on Bitcoin significantly more cost efficient.