Memory Network Algorithm: Difference between revisions
Jump to navigation
Jump to search
m (Text replacement - ". " to ". ") |
m (Text replacement - "> [[]]." to "> ....") |
||
Line 2: | Line 2: | ||
* <B>Context:</B> | * <B>Context:</B> | ||
** It can be implemented by a [[Memory Network System]]. | ** It can be implemented by a [[Memory Network System]]. | ||
* <B>See:</B> [[]]. | * <B>See:</B> [[...]]. | ||
---- | ---- |
Latest revision as of 01:15, 21 October 2024
A Memory Network Algorithm is a NNet that ...
- Context:
- It can be implemented by a Memory Network System.
- See: ....
References
2016a
- (Weston, 2016) ⇒ Jason Weston. (2016). “Memory Networks for Language Understanding.” Tutorial at ICML-2016.
- Memory Networks: General Framework
- Components: (m, I,G,O,R)
- A memory [math]\displaystyle{ m }[/math]: an array of objects indexed by m_i
- Four (potentially learned) components: I, G, O and R:
- I – input feature map: converts the incoming input to the internal feature representation.
- G – generalization: updates old memories given the new input.
- O – output feature map: produces a new output 2, given the new input and the current memory state.
- R – response: converts the output into the response format desired.
2016b
- (Miller et al., 2016) ⇒ Alexander Miller, Adam Fisch, Jesse Dodge, Amir-Hossein Karimi, Antoine Bordes, and Jason Weston. (2016). “Key-Value Memory Networks for Directly Reading Documents.” In: arXiv Journal, 1606.03126.
2015
- (Sukhbaatar et al., 2015) ⇒ Sainbayar Sukhbaatar, Jason Weston, and Rob Fergus. (2015). “End-to-end Memory Networks.” In: Advances in Neural Information Processing Systems.