Estimate and Replace: A Novel Approach to Integrating Deep Neural Networks with Existing Applications

04/24/2018
by   Guy Hadash, et al.
0

Existing applications include a huge amount of knowledge that is out of reach for deep neural networks. This paper presents a novel approach for integrating calls to existing applications into deep learning architectures. Using this approach, we estimate each application's functionality with an estimator, which is implemented as a deep neural network (DNN). The estimator is then embedded into a base network that we direct into complying with the application's interface during an end-to-end optimization process. At inference time, we replace each estimator with its existing application counterpart and let the base network solve the task by interacting with the existing application. Using this 'Estimate and Replace' method, we were able to train a DNN end-to-end with less data and outperformed a matching DNN that did not interact with the external application.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
01/13/2019

Neural network gradient-based learning of black-box function interfaces

Deep neural networks work well at approximating complicated functions wh...
research
08/07/2018

Application of End-to-End Deep Learning in Wireless Communications Systems

Deep learning is a potential paradigm changer for the design of wireless...
research
12/28/2021

Fostering the Robustness of White-Box Deep Neural Network Watermarks by Neuron Alignment

The wide application of deep learning techniques is boosting the regulat...
research
02/09/2019

Hierarchical Multi-task Deep Neural Network Architecture for End-to-End Driving

A novel hierarchical Deep Neural Network (DNN) model is presented to add...
research
12/06/2018

End-to-End Streaming Keyword Spotting

We present a system for keyword spotting that, except for a frontend com...
research
03/07/2019

Learning deep neural networks in blind deblurring framework

Recently, end-to-end learning methods based on deep neural network (DNN)...
research
04/06/2022

Customizable End-to-end Optimization of Online Neural Network-supported Dereverberation for Hearing Devices

This work focuses on online dereverberation for hearing devices using th...

Please sign up or login with your details

Forgot password? Click here to reset