Elastic Neural Networks: A Scalable Framework for Embedded Computer Vision

07/02/2018
by   Yue Bai, et al.
0

We propose a new framework for image classification with deep neural networks. The framework introduces intermediate outputs to the computational graph of a network. This enables flexible control of the computational load and balances the tradeoff between accuracy and execution time. Moreover, we present an interesting finding that the intermediate outputs can act as a regularizer at training time, improving the prediction accuracy. In the experimental section we demonstrate the performance of our proposed framework with various commonly used pretrained deep networks in the use case of apparent age estimation.

READ FULL TEXT
research
10/01/2018

Elastic Neural Networks for Classification

In this work we propose a framework for improving the performance of any...
research
10/26/2017

Knowledge Projection for Deep Neural Networks

While deeper and wider neural networks are actively pushing the performa...
research
05/20/2016

Ristretto: Hardware-Oriented Approximation of Convolutional Neural Networks

Convolutional neural networks (CNN) have achieved major breakthroughs in...
research
03/07/2022

Graph Neural Networks for Image Classification and Reinforcement Learning using Graph representations

In this paper, we will evaluate the performance of graph neural networks...
research
11/28/2018

Predicting the Computational Cost of Deep Learning Models

Deep learning is rapidly becoming a go-to tool for many artificial intel...
research
09/18/2017

A Probabilistic Framework for Nonlinearities in Stochastic Neural Networks

We present a probabilistic framework for nonlinearities, based on doubly...
research
05/14/2019

Interpretable Deep Neural Networks for Patient Mortality Prediction: A Consensus-based Approach

Deep neural networks have achieved remarkable success in challenging tas...

Please sign up or login with your details

Forgot password? Click here to reset