BYU

Abstract by Tyler Etchart

Personal Infomation


Presenter's Name

Tyler Etchart

Co-Presenters

William Myers

Degree Level

Masters

Co-Authors

William Myers
Josh Greaves

Abstract Infomation


Department

Computer Science

Faculty Advisor

David Wingate

Title

Auxiliary Memory Models for Deep Neural Networks

Abstract

3M. There has been strong premilinary work in the field of auxiliary memory models for deep neural networks. Examples include the Neural Turing Machine and the Differential Neural Computer by Google Deepmind. While these models have proven successful, they are fundamentally limited by their need for differentiable memory structures. We present a new method for using neural networks with non-differentiable memory structures by removing the non-differentiable operation from the computation graph. This is significant because it frees us to utilize all kinds of memory structures, such as arrays, maps, and more.