DeepAI AI Chat
Log In Sign Up

Explaining AlphaGo: Interpreting Contextual Effects in Neural Networks

by   Zenan Ling, et al.

In this paper, we propose to disentangle and interpret contextual effects that are encoded in a pre-trained deep neural network. We use our method to explain the gaming strategy of the alphaGo Zero model. Unlike previous studies that visualized image appearances corresponding to the network output or a neural activation only from a global perspective, our research aims to clarify how a certain input unit (dimension) collaborates with other units (dimensions) to constitute inference patterns of the neural network and thus contribute to the network output. The analysis of local contextual effects w.r.t. certain input units is of special values in real applications. Explaining the logic of the alphaGo Zero model is a typical application. In experiments, our method successfully disentangled the rationale of each move during the Go game.


page 2

page 3

page 6

page 10

page 11

page 12


Methods for Interpreting and Understanding Deep Neural Networks

This paper provides an entry point to the problem of interpreting a deep...

Interpreting Layered Neural Networks via Hierarchical Modular Representation

Interpreting the prediction mechanism of complex models is currently one...

Quantifying Layerwise Information Discarding of Neural Networks

This paper presents a method to explain how input information is discard...

Representer Point Selection for Explaining Deep Neural Networks

We propose to explain the predictions of a deep neural network, by point...

Explaining Neural Networks Semantically and Quantitatively

This paper presents a method to explain the knowledge encoded in a convo...

Understanding Community Structure in Layered Neural Networks

A layered neural network is now one of the most common choices for the p...

AES Systems Are Both Overstable And Oversensitive: Explaining Why And Proposing Defenses

Deep-learning based Automatic Essay Scoring (AES) systems are being acti...