Targeted Deep Learning: Framework, Methods, and Applications

TL;DR

This paper introduces targeted deep learning, a framework tailored for applications with small, known test input sets, demonstrating improved speed and accuracy through a simple data preprocessing approach.

Contribution

The paper proposes a novel targeted deep learning framework and a general, easy-to-implement method to adapt standard pipelines for such applications.

Findings

Faster and more accurate deep learning on known test inputs

Applicable to real-world data with small, targeted test sets

Simple data preprocessing enhances standard deep learning pipelines

Abstract

Deep learning systems are typically designed to perform for a wide range of test inputs. For example, deep learning systems in autonomous cars are supposed to deal with traffic situations for which they were not specifically trained. In general, the ability to cope with a broad spectrum of unseen test inputs is called generalization. Generalization is definitely important in applications where the possible test inputs are known but plentiful or simply unknown, but there are also cases where the possible inputs are few and unlabeled but known beforehand. For example, medicine is currently interested in targeting treatments to individual patients; the number of patients at any given time is usually small (typically one), their diagnoses/responses/... are still unknown, but their general characteristics (such as genome information, protein levels in the blood, and so forth) are known before the treatment. We propose to call deep learning in such applications targeted deep learning. In this paper, we introduce a framework for targeted deep learning, and we devise and test an approach for adapting standard pipelines to the requirements of targeted deep learning. The approach is very general yet easy to use: it can be implemented as a simple data-preprocessing step. We demonstrate on a variety of real-world data that our approach can indeed render standard deep learning faster and more accurate when the test inputs are known beforehand.