Viet-Anh on Software Logo

What is: End-To-End Memory Network?

SourceEnd-To-End Memory Networks
Year2000
Data SourceCC BY-SA - https://paperswithcode.com

An End-to-End Memory Network is a neural network with a recurrent attention model over a possibly large external memory. The architecture is a form of Memory Network, but unlike the model in that work, it is trained end-to-end, and hence requires significantly less supervision during training. It can also be seen as an extension of RNNsearch to the case where multiple computational steps (hops) are performed per output symbol.

The model takes a discrete set of inputs x_1,,x_nx\_{1}, \dots, x\_{n} that are to be stored in the memory, a query qq, and outputs an answer aa. Each of the x_ix\_{i}, qq, and aa contains symbols coming from a dictionary with VV words. The model writes all xx to the memory up to a fixed buffer size, and then finds a continuous representation for the xx and qq. The continuous representation is then processed via multiple hops to output aa.