scholarly journals Computer-Assisted Cohort Identification in Practice

2022 ◽  
Vol 3 (2) ◽  
pp. 1-28
Author(s):  
Besat Kassaie ◽  
Elizabeth L. Irving ◽  
Frank Wm. Tompa
Keyword(s):  
Machine Learning ◽  
Theoretical Model ◽  
Active Learning ◽  
Health Research ◽  
Research Problem ◽  
Computer Assisted ◽  
Prior Work ◽  
Alternative Approach ◽  
Cohort Identification

The standard approach to expert-in-the-loop machine learning is active learning, where, repeatedly, an expert is asked to annotate one or more records and the machine finds a classifier that respects all annotations made until that point. We propose an alternative approach, IQRef , in which the expert iteratively designs a classifier and the machine helps him or her to determine how well it is performing and, importantly, when to stop, by reporting statistics on a fixed, hold-out sample of annotated records. We justify our approach based on prior work giving a theoretical model of how to re-use hold-out data. We compare the two approaches in the context of identifying a cohort of EHRs and examine their strengths and weaknesses through a case study arising from an optometric research problem. We conclude that both approaches are complementary, and we recommend that they both be employed in conjunction to address the problem of cohort identification in health research.

scholarly journals ActiveThief: Model Extraction Using Active Learning and Unannotated Public Data

2020 ◽  
Vol 34 (01) ◽  
pp. 865-872
Author(s):  
Soham Pal ◽  
Yash Gupta ◽  
Aditya Shukla ◽  
Aditya Kanade ◽  
Shirish Shevade ◽  
...  
Keyword(s):  
Machine Learning ◽  
Active Learning ◽  
Domain Knowledge ◽  
Third Party ◽  
Prior Work ◽  
Model Extraction ◽  
Public Data ◽  
Adversarial Examples ◽  
Application Programming ◽  
Public Datasets

Machine learning models are increasingly being deployed in practice. Machine Learning as a Service (MLaaS) providers expose such models to queries by third-party developers through application programming interfaces (APIs). Prior work has developed model extraction attacks, in which an attacker extracts an approximation of an MLaaS model by making black-box queries to it. We design ActiveThief – a model extraction framework for deep neural networks that makes use of active learning techniques and unannotated public datasets to perform model extraction. It does not expect strong domain knowledge or access to annotated data on the part of the attacker. We demonstrate that (1) it is possible to use ActiveThief to extract deep classifiers trained on a variety of datasets from image and text domains, while querying the model with as few as 10-30% of samples from public datasets, (2) the resulting model exhibits a higher transferability success rate of adversarial examples than prior work, and (3) the attack evades detection by the state-of-the-art model extraction detection method, PRADA.

scholarly journals Application of Machine Learning in Auditing Teaching: A Case Study of Predicting the Audit Report Type of China ST Listed Companies

2020 ◽  
Vol 2 (1) ◽  
pp. 023-040
Author(s):  
Shi-Ming Huang Shi-Ming Huang ◽  
Chang-ping Chen Shi-Ming Huang ◽  
Tzu-ching Wong Chang-ping Chen
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Listed Company ◽  
Accounting Students ◽  
Computer Assisted ◽  
Research Database ◽  
Audit Report ◽  
Professional Fields ◽  
Future Work

<p>Artificial intelligence is an important emerging technology in the accounting industry. Fear and hype associated with artificial intelligence and its impact on accounting and auditing jobs have pervaded the professional fields of accounting and auditing. It is important to develop AI competency in accountants and auditors. This paper presents a teaching case for a professor or lecturer to use for teaching machine learning to accounting students. The case is based on openly available data from the China Stock Market & Accounting Research database and aims to teach students how to predict the future audit report type of a China ST listed company. Through case teaching, students can learn skills related to computer-assisted auditing tools and machine learning (such as ACL) develop the confidence to apply artificial intelligence in their education and future work.</p> <p>&nbsp;</p>

scholarly journals Neural Embeddings for Text Analysis: A Case Study in Neoliberal Discourse

2021 ◽  
pp. 196-204
Author(s):  
Katerina Mandenaki ◽  
Catherine Sotirakou ◽  
Constantinos Mourlas ◽  
Spiros Moschonas
Keyword(s):  
Machine Learning ◽  
Language Processing ◽  
Text Analysis ◽  
Public Life ◽  
Machine Learning Algorithms ◽  
Computer Assisted ◽  
Distributional Semantics ◽  
Computational Tools ◽  
The Given

This paper examines the notions of neoliberalism and the financialization and marketisation of public life by using computational tools such as sentence embeddings on a novel corpus of neoliberal articles. More specifically, we experimented with distributional semantics along with several Natural Language Processing (NLP) techniques and machine learning algorithms in order to extract conceptual dictionaries and “seed” words. Our findings show that sentence embeddings reveal repetitive patterns constructed around the given concepts and highlight the mechanical character of an ideology in its function of providing solutions, policies and constructing stereotypes. This work introduces a novel pipeline for computer-assisted research in discourse analysis and ideology.

Teaching Computer Based Historical Data Analysis

1994 ◽  
Vol 6 (1) ◽  
pp. 52-58 ◽  
Author(s):  
Charles Anderson ◽  
Robert J. Morris
Keyword(s):  
Data Analysis ◽  
Social History ◽  
Historical Data ◽  
Good Practice ◽  
Computer Assisted ◽  
Historical Data Analysis ◽  
University Of Edinburgh ◽  
Computer Based ◽  
The University

A case study ofa third year course in the Department of Economic and Social History in the University of Edinburgh isusedto considerandhighlightaspects of good practice in the teaching of computer-assisted historical data analysis.

A Case Study on the Effects of Active Learning Classrooms in Higher Education

2018 ◽  
Vol 24 (4) ◽  
pp. 733-754
Author(s):  
Hyeon Woo Lee ◽  
Yoon Mi Cha ◽  
Kibeom Kim Kibeom Kim
Keyword(s):  
Higher Education ◽  
Active Learning

A Problem in the Making: How Firms Formulate Sharable Problems for Open Innovation Contests

2018 ◽  
Author(s):  
Martin W. Wallin ◽  
Georg von Krogh ◽  
Jan Henrik Sieg
Keyword(s):  
Knowledge Creation ◽  
Open Innovation ◽  
Problem Formulation ◽  
Theoretical Framework ◽  
Monetary Reward ◽  
Technical Innovation ◽  
Prior Work ◽  
Exploratory Case Study ◽  
External Sources

Crowdsourcing in the form of innovation contests stimulates knowledge creation external to the firm by distributing technical, innovation-related problems to external solvers and by proposing a fixed monetary reward for solutions. While prior work demonstrates that innovation contests can generate solutions of value to the firm, little is known about how problems are formulated for such contests. We investigate problem formulation in a multiple exploratory case study of seven firms and inductively develop a theoretical framework that explains the mechanisms of formulating sharable problems for innovation contests. The chapter contributes to the literatures on crowdsourcing and open innovation by providing a rare account of the intra-organizational implications of engaging in innovation contests and by providing initial clues to problem formulation—a critical antecedent to firms’ ability to leverage external sources of innovation.

Sign in / Sign up

Export Citation Format

Share Document