Differentiable Adaptive Computation Time for Visual Reasoning

04/27/2020
by   Cristobal Eyzaguirre, et al.
0

This paper presents a novel attention-based algorithm for achieving adaptive computation called DACT, which, unlike existing ones, is end-to-end differentiable.Our method can be used in conjunction with many networks; in particular, we study its application to the widely know MAC architecture, obtaining a significant reduction in the number of recurrent steps needed to achieve similar accuracies, therefore improving its performance to computation ratio.Furthermore, we show that by increasing the maximum number of steps used, we surpass the accuracy of even our best non-adaptive MAC in the CLEVR dataset, demonstrating that our approach is able to control the number of steps without significant loss of performance.Additional advantages provided by our approach include considerably improving interpretability by discarding useless steps and providing more insights into the underlying reasoning process.Finally, we present adaptive computation as an equivalent to an ensemble of models, similar to a mixture of expert formulation.Both the code and the configuration files for our experiments are made available to support further research in this area.

READ FULL TEXT

page 1

page 6

page 7

page 8

page 10

page 11

research
10/24/2016

Learning to Reason With Adaptive Computation

Multi-hop inference is necessary for machine learning systems to success...
research
03/08/2018

Compositional Attention Networks for Machine Reasoning

We present the MAC network, a novel fully differentiable neural network ...
research
08/30/2018

End-to-end Speech Recognition with Adaptive Computation Steps

In this paper, we present Adaptive Computation Steps (ACS) algorithm, wh...
research
03/29/2016

Adaptive Computation Time for Recurrent Neural Networks

This paper introduces Adaptive Computation Time (ACT), an algorithm that...
research
03/21/2018

Comparing Fixed and Adaptive Computation Time for Recurrent Neural Networks

Adaptive Computation Time for Recurrent Neural Networks (ACT) is one of ...
research
11/27/2022

Neural Architecture for Online Ensemble Continual Learning

Continual learning with an increasing number of classes is a challenging...
research
03/15/2021

Maximum Number of Steps of Topswops on 18 and 19 Cards

Let f(n) be the maximum number of steps of Topswops on n cards. In this ...

Please sign up or login with your details

Forgot password? Click here to reset