Compositional Attention Networks for Machine Reasoning
Opened this issue · 1 comments
howardyclo commented
Metadata
- Authors: Drew A. Hudson and Christopher D. Manning
- Organization: Stanford University
- Conference: ICLR 2018
- Paper: https://arxiv.org/pdf/1803.03067.pdf
- Code: https://github.com/stanfordnlp/mac-network
- Video: https://www.youtube.com/watch?v=jpNLp9SnTF8
howardyclo commented
Summary
This paper purpose a novel recurrent, attention and memory based neural architecture "Memory, Attention and Composition (MAC) cell" for VQA, featuring multi-step reasoning.
Three operations in MAC cell:
- Control unit: Updates the control state to attend at each iteration to some aspect of a given question.
- Read unit: Extracts information out of a knowledge base, guided by the control and memory states.
- Write unit: Integrates the retrieved information into the memory state, iteratively computing the answer.