Effective Version Space Reduction for Convolutional Neural Networks

06/22/2020
by   Jiayu Liu, et al.
0

In active learning, sampling bias could pose a serious inconsistency problem and hinder the algorithm from finding the optimal hypothesis. However, many methods for neural networks are hypothesis space agnostic and do not address this problem. We examine active learning with convolutional neural networks through the principled lens of version space reduction. We identify the connection between two approaches—prior mass reduction and diameter reduction—and propose a new diameter-based querying method—the minimum Gibbs-vote disagreement. By estimating version space diameter and bias, we illustrate how version space of neural networks evolves and examine the realizability assumption. With experiments on MNIST, Fashion-MNIST, SVHN and STL-10 datasets, we demonstrate that diameter reduction methods reduce the version space more effectively and perform better than prior mass reduction and other baselines, and that the Gibbs vote disagreement is on par with the best query method.

READ FULL TEXT
research
11/17/2022

Active Learning with Expected Error Reduction

Active learning has been studied extensively as a method for efficient d...
research
03/05/2023

Streaming Active Learning with Deep Neural Networks

Active learning is perhaps most naturally posed as an online learning pr...
research
02/27/2017

Diameter-Based Active Learning

To date, the tightest upper and lower-bounds for the active learning of ...
research
11/18/2019

Bias-Aware Heapified Policy for Active Learning

The data efficiency of learning-based algorithms is more and more import...
research
01/09/2020

What is the Value of Data? On Mathematical Methods for Data Quality Estimation

Data is one of the most important assets of the information age, and its...
research
10/18/2021

Diameter constrained Steiner tree and related problems

We give a dynamic programming solution to find the minimum cost of a dia...
research
07/24/2018

A Structured Perspective of Volumes on Active Learning

Active Learning (AL) is a learning task that requires learners interacti...

Please sign up or login with your details

Forgot password? Click here to reset