5 Questions
Deep Convolutional Networks for Go are used for image recognition
True
Go is a very visual game
True
The move prediction for Go improved from about 40% to 57% in two papers in 2015
True
The input for the Deep Convolutional Neural Networks to Play Go includes raw input with three channels
True
The architecture for the Deep Convolutional Networks for Go includes many small convolutional filters
True
Test your knowledge of deep convolutional networks for Go with this quiz. Learn about the significant improvement in move prediction for Go achieved through training deep convolutional neural networks on the full 19x19 board, as discussed in the papers by Clark and Storkey, and Maddison, Huang, Sutskever, and Silver.
Make Your Own Quizzes and Flashcards
Convert your notes into interactive study material.
Get started for free