Question

1. which two training methods were used to teach alphago to play go?

backpropagation only
transfer learning and curriculum learning
supervised learning and reinforcement learning
unsupervised learning and genetic algorithms

Explanation:

AlphaGo was trained using supervised learning (learning from human - played games) and reinforcement learning (learning from self - play and rewards). Supervised learning helped it learn patterns from expert games, and reinforcement learning enabled it to improve through trial - and - error in self - play scenarios.

Answer:

Supervised learning and reinforcement learning