scholarly journals Machine Learning Interpretability: A Survey on Methods and Metrics

Electronics ◽  
2019 ◽  
Vol 8 (8) ◽  
pp. 832 ◽  
Author(s):  
Diogo V. Carvalho ◽  
Eduardo M. Pereira ◽  
Jaime S. Cardoso
Keyword(s):  
Machine Learning ◽  
Social Impact ◽  
Research Field ◽  
Learning Systems ◽  
Future Directions ◽  
The Past ◽  
Current State ◽  
Black Boxes ◽  
Interpretable Models

Machine learning systems are becoming increasingly ubiquitous. These systems’s adoption has been expanding, accelerating the shift towards a more algorithmic society, meaning that algorithmically informed decisions have greater potential for significant social impact. However, most of these accurate decision support systems remain complex black boxes, meaning their internal logic and inner workings are hidden to the user and even experts cannot fully understand the rationale behind their predictions. Moreover, new regulations and highly regulated domains have made the audit and verifiability of decisions mandatory, increasing the demand for the ability to question, understand, and trust machine learning systems, for which interpretability is indispensable. The research community has recognized this interpretability problem and focused on developing both interpretable models and explanation methods over the past few years. However, the emergence of these methods shows there is no consensus on how to assess the explanation quality. Which are the most suitable metrics to assess the quality of an explanation? The aim of this article is to provide a review of the current state of the research field on machine learning interpretability while focusing on the societal impact and on the developed methods and metrics. Furthermore, a complete literature review is presented in order to identify future directions of work on this field.

“The Past, Present, and Future of Accounting History”: A Comment on the State of Accounting History

2020 ◽  
Vol 47 (1) ◽  
pp. 89-95 ◽  
Author(s):  
Garry D. Carnegie
Keyword(s):  
English Language ◽  
Research Field ◽  
The State ◽  
International Accounting ◽  
Scholarly Research ◽  
Recent Contribution ◽  
Global Society ◽  
Accounting History ◽  
The Past

ABSTRACT This response to the recent contribution by Matthews (2019) entitled “The Past, Present, and Future of Accounting History” specifically deals with the issues associated with concentrating on counting publication numbers in examining the state of a scholarly research field at the start of the 2020s. It outlines several pitfalls with the narrowly focused publications count analysis, in selected English language journals only, as provided by Matthews. The commentary is based on three key arguments: (1) accounting history research and publication is far more than a “numbers game”; (2) trends in the quality of the research undertaken and published are paramount; and (3) international publication and accumulated knowledge in accounting history are indeed more than a collection of English language publications. The author seeks to contribute to discussion and debate between accounting historians and other researchers for the benefit and development of the international accounting history community and global society.

scholarly journals Olfaction and Aging: A Review of the Current State of Research and Future Directions

i-Perception ◽  
2021 ◽  
Vol 12 (3) ◽  
pp. 204166952110203
Author(s):  
Jonas K. Olofsson ◽  
Ingrid Ekström ◽  
Maria Larsson ◽  
Steven Nordin
Keyword(s):  
Warning Signs ◽  
Future Directions ◽  
Current State ◽  
Challenging Tasks ◽  
State Of Research ◽  
To Come ◽  
Health Cognition ◽  
Olfactory Abilities ◽  
And Training

Olfaction, the sense of smell, is characterized by a notable age-dependency such that aging individuals are more likely to have poor olfactory abilities. These impairments are considered to be mostly irreversible and as having potentially profound effects on quality of life and food behavior, as well as constituting warning signs of mortality, cognitive dysfunction, and dementia. Here, we review the current state of research on aging and olfaction, focusing on five topics which we regard to be of particular relevance for the field: nutrition and health, cognition and dementia, mortality, environment and genetics, and training-based enhancement. Under each of these headlines, we provide a state-of-the-art overview and discuss gaps in our knowledge which might be filled by further research. Understanding how olfactory abilities are diminished in aging, and how they may be alleviated or recovered, involves a set of challenging tasks for researchers in the years to come.

scholarly journals Multi-Task Optimization and Multi-Task Evolutionary Computation in the Past Five Years: A Brief Review

Mathematics ◽  
2021 ◽  
Vol 9 (8) ◽  
pp. 864
Author(s):  
Qingzheng Xu ◽  
Na Wang ◽  
Lei Wang ◽  
Wei Li ◽  
Qian Sun
Keyword(s):  
Evolutionary Computation ◽  
Explicit Knowledge ◽  
Optimization Problems ◽  
Effective Means ◽  
Typical Application ◽  
The Past ◽  
Current State ◽  
Evolution Algorithms ◽  
Application Fields

Traditional evolution algorithms tend to start the search from scratch. However, real-world problems seldom exist in isolation and humans effectively manage and execute multiple tasks at the same time. Inspired by this concept, the paradigm of multi-task evolutionary computation (MTEC) has recently emerged as an effective means of facilitating implicit or explicit knowledge transfer across optimization tasks, thereby potentially accelerating convergence and improving the quality of solutions for multi-task optimization problems. An increasing number of works have thus been proposed since 2016. The authors collect the abundant specialized literature related to this novel optimization paradigm that was published in the past five years. The quantity of papers, the nationality of authors, and the important professional publications are analyzed by a statistical method. As a survey on state-of-the-art of research on this topic, this review article covers basic concepts, theoretical foundation, basic implementation approaches of MTEC, related extension issues of MTEC, and typical application fields in science and engineering. In particular, several approaches of chromosome encoding and decoding, intro-population reproduction, inter-population reproduction, and evaluation and selection are reviewed when developing an effective MTEC algorithm. A number of open challenges to date, along with promising directions that can be undertaken to help move it forward in the future, are also discussed according to the current state. The principal purpose is to provide a comprehensive review and examination of MTEC for researchers in this community, as well as promote more practitioners working in the related fields to be involved in this fascinating territory.

A Survey on Document-level Neural Machine Translation

2021 ◽  
Vol 54 (2) ◽  
pp. 1-36
Author(s):  
Sameen Maruf ◽  
Fahimeh Saleh ◽  
Gholamreza Haffari
Keyword(s):  
Machine Translation ◽  
Language Processing ◽  
Research Field ◽  
Translation Process ◽  
Future Directions ◽  
Translation Quality ◽  
Current State ◽  
Evaluation Strategies ◽  
Almost All ◽  
Document Level

Machine translation (MT) is an important task in natural language processing (NLP), as it automates the translation process and reduces the reliance on human translators. With the resurgence of neural networks, the translation quality surpasses that of the translations obtained using statistical techniques for most language-pairs. Up until a few years ago, almost all of the neural translation models translated sentences independently , without incorporating the wider document-context and inter-dependencies among the sentences. The aim of this survey article is to highlight the major works that have been undertaken in the space of document-level machine translation after the neural revolution, so researchers can recognize the current state and future directions of this field. We provide an organization of the literature based on novelties in modelling and architectures as well as training and decoding strategies. In addition, we cover evaluation strategies that have been introduced to account for the improvements in document MT, including automatic metrics and discourse-targeted test sets. We conclude by presenting possible avenues for future exploration in this research field.

scholarly journals Quality and Operations Management in Food Supply Chains: A Literature Review

2018 ◽  
Vol 2018 ◽  
pp. 1-14 ◽  
Author(s):  
Yong He ◽  
Hongfu Huang ◽  
Dong Li ◽  
Chunming Shi ◽  
Sarah J. Wu
Keyword(s):  
Literature Review ◽  
Supply Chains ◽  
Operations Research ◽  
Operations Management ◽  
Food Supply ◽  
Research Field ◽  
Food Supply Chains ◽  
The Past ◽  
Starting Point

We present a literature review on quality and operations management problems in food supply chains. In food industry, the quality of the food products declines over time and should be addressed in the supply chain operations management. Managing food supply chains with operations management methods not only generates economic benefit, but also contributes to environmental and social benefits. The literature on this topic has been burgeoning in the past few years. Since 2005, more than 100 articles have been published on this topic in major operations research and management science journals. In this literature review, we concentrate on the quantitative models in this research field and classify the related articles into four categories, that is, storage problems, distribution problems, marketing problems, and food traceability and safety problems. We hope that this review serves as a reference for interested researchers and a starting point for those who wish to explore it further.

Reflections on Thirty Years of Muqarnas

2014 ◽  
Vol 30 (1) ◽  
pp. 1-12 ◽  
Author(s):  
Gülru Necipoğlu
Keyword(s):  
Board Members ◽  
Islamic Art ◽  
Future Directions ◽  
The Past ◽  
Advisory Boards ◽  
Current State ◽  
Thirtieth Anniversary ◽  
History Of ◽  
Art And Architecture ◽  
State Of The Field

In this volume marking the thirtieth anniversary of Muqarnas, the Editor reflects on the evolution of the journal over the years. To that end, the members of the Editorial and Advisory Boards were sent a questionnaire, asking them to comment on the contributions of Muqarnas and its Supplements series to the field of Islamic art and architecture studies over the past three decades, and to provide suggestions for future directions. Their observations, thoughts, and hopes for Muqarnas have been anonymously incorporated into this essay, which, in conversation with their comments, looks back on the history of the publication and offers some possibilities for the path it might take going forward.
The goal here is neither to assess the historiography nor to examine the current state of the field thirty years after the opening essay of volume 1. Instead, the focus is on the development and impact of both Muqarnas and the Supplements series in a highly specialized field with relatively few and short-lived or sporadic journals, before turning to the successes and shortcomings of these publications, as outlined by some of the board members. 


scholarly journals Economics in the Former Soviet Union

1992 ◽  
Vol 6 (2) ◽  
pp. 137-148 ◽  
Author(s):  
Michael Alexeev ◽  
Clifford Gaddy ◽  
Jim Leitzel
Keyword(s):  
Graduate Students ◽  
Soviet Union ◽  
Former Soviet Union ◽  
Political Leadership ◽  
Future Directions ◽  
The Past ◽  
Current State ◽  
Course Of Action ◽  
The Soviet Union ◽  
Economics Profession

One of the most notable, but least discussed, aspects of the halting attempts during the past six years to reform the economies of the Soviet Union, and now those of its successor states, has been the prominent role played by professional economists. Not since the mid-1920s has the Soviet political leadership felt so strongly the need to draw upon the expertise of the economics profession to help determine its course of action. In this paper, we attempt to characterize the current state of economics in the former Soviet Union, investigate the implications that the condition of Soviet economics has for reform, and suggest possible future directions for the discipline. Our information comes from four main sources: professional publications of Soviet and Western economists, published remarks by Soviet economists, personal interviews and discussions which we conducted with young Soviet economists in the summers of 1990 and 1991, and a questionnaire administered to Soviet economists and graduate students in the Soviet Union.

scholarly journals Drug-eluting Biliary Stent

2020 ◽  
Vol 25 (1) ◽  
pp. 11-17
Author(s):  
Sung Ill Jang ◽  
Dong Ki Lee
Keyword(s):  
Biliary Drainage ◽  
Development Process ◽  
Primary Treatment ◽  
Biliary Stent ◽  
Biliary Stents ◽  
Stent Patency ◽  
Future Directions ◽  
The Past ◽  
Drug Eluting

Biliary drainage is necessary to improve the survival or quality of life of patients with malignant biliary obstruction. In the past, surgery was the primary treatment for biliary drainage, but recently, endoscopic or percutaneous stent implantation has been recognized as the main treatment. Various materials and structures have been devised and developed to increase the patency of the biliary stent. In the development of these stents, drug-eluting biliary stents with an anti-tumoral agent (DES) have emerged to increase the stent patency period by chemically inhibiting tumor growth in the stent through the change of the coating material. The DESs have been proved to be stable through several animal and clinical trials, but their effectiveness has not been demonstrated. We will discuss the development process, problems, and future directions of DES that has been clinically applied.

scholarly journals Developing the platform model for problem solving of automated machine learning

2021 ◽  
Vol 2094 (3) ◽  
pp. 032049
Author(s):  
V A Chastikova ◽  
S A Zherlitsyn
Keyword(s):  
Machine Learning ◽  
Information Exchange ◽  
Complete Solution ◽  
Learning Systems ◽  
Distribution Model ◽  
System Operation ◽  
Current State ◽  
Automated Machine Learning ◽  
Testing Module ◽  
The Given

Abstract The article discusses the current state of technologies for automated machine learning. The development trends and the nature of the distribution model - MLaaS - are defined. There is highlighted a number of problems of automating the machine learning process, such as: excessive simplification and specialization of tools, vagueness of implemented processes, lack of flexibility in the infrastructure hardware, using closed algorithms. As a partial or complete solution to them, we have proposed the architecture, consisting of separate modules: models, hybridizer, learning algorithms module, testing module, user support module, and a theoretical framework. The main feature of the given architecture is its modularity, transparency and encapsulation of components. Each module is described as a separate element, implemented as an independent microservice. The paper describes the benefits of applying the given approach to the implementation of automated machine learning systems, the need to implement the given or similar standards. For each of the modules, its purposes, the tasks it solves and the implemented functionality, as well as the data necessary for the functioning and their sources are described. A general diagram showing the flows of information exchange between modules is presented. The main scenarios for the resulting system operation, as well as ways of interacting with it and the result of its operation - the generated model - are described.

scholarly journals Mechanisms for QoE optimisation of Video Traffic: A review paper

2020 ◽  
Author(s):  
qahhar muhammad qadir ◽  
Alexander A. Kist ◽  
ZHONGWEI ZHANG
Keyword(s):  
Quality Of Experience ◽  
Review Paper ◽  
End Users ◽  
The Internet ◽  
Video Traffic ◽  
Future Directions ◽  
The Past ◽  
New Methods ◽  
Increasing Demand

Transmission of video traffic over the Internet has grown exponentially in the past few years<br>with no sign of waning. This increasing demand for video services has changed user expectation of quality. Various mechanisms have been proposed to optimise the Quality of Experience (QoE) of end users’ video. Studying these approaches are necessary for new methods to be proposed or combination of existing ones to be tailored. We discuss challenges facing the optimisation of QoE for video traffic in this paper. It surveys and classifies these mechanisms based on their functions. The limitation of each of them is identified and future directions are highlighted.

Sign in / Sign up

Export Citation Format

Share Document