On the integration of symbolic and sub-symbolic techniques for XAI: A survey

2020 ◽  
Vol 14 (1) ◽  
pp. 7-32
Author(s):  
Roberta Calegari ◽  
Giovanni Ciatto ◽  
Andrea Omicini
Keyword(s):  
Intelligent Systems ◽  
State Of The Art ◽  
Symbolic Integration ◽  
Everyday Lives ◽  
Current State ◽  
Explainable Ai ◽  
Integration Techniques ◽  
General Effort

 The more intelligent systems based on sub-symbolic techniques pervade our everyday lives, the less human can understand them. This is why symbolic approaches are getting more and more attention in the general effort to make AI interpretable, explainable, and trustable. Understanding the current state of the art of AI techniques integrating symbolic and sub-symbolic approaches is then of paramount importance, nowadays—in particular in the XAI perspective. This is why this paper provides an overview of the main symbolic/sub-symbolic integration techniques, focussing in particular on those targeting explainable AI systems.

scholarly journals The National Academies Board on Human System Integration (BOHSI) Panel: Explainable AI, System Transparency, and Human Machine Teaming

2019 ◽  
Vol 63 (1) ◽  
pp. 631-635
Author(s):  
Toby Warden ◽  
Pascale Carayon ◽  
Emilie M. Roth ◽  
Jessie Chen ◽  
William J. Clancey ◽  
...  
Keyword(s):  
Human Factors ◽  
System Integration ◽  
Intelligent Systems ◽  
State Of The Art ◽  
Human System ◽  
Current State ◽  
Explainable Ai ◽  
Human Systems Integration ◽  
Automated Software ◽  
Research And Design

The National Academies Board on Human Systems Integration (BOHSI) has organized this session exploring the state of the art and research and design frontiers for intelligent systems that support effective human machine teaming. An important element in the success of human machine teaming is the ability of the person on the scene to develop appropriate trust in the automated software (including recognizing when it should not be trusted). Research is being conducted in the Human Factors community and the Artificial Intelligence (AI) community on the characteristics that software need to display in order to foster appropriate trust. For example, there is a DARPA program on Explainable AI (XAI). The Panel brings together prominent researchers from both the Human Factors and AI communities to discuss the current state of the art, challenges and short-falls and ways forward in developing systems that engender appropriate trust.

scholarly journals No AI Is an Island: The Case for Teaming Intelligence

AI Magazine ◽  
2019 ◽  
Vol 40 (1) ◽  
pp. 16-28 ◽  
Author(s):  
Matthew Johnson ◽  
Alonso Vera
Keyword(s):  
Crucial Role ◽  
Intelligent Systems ◽  
State Of The Art ◽  
General Structure ◽  
Technological System ◽  
Full Potential ◽  
Current State ◽  
The World ◽  
Collaborative Skills ◽  
Significant Attention

The purpose of this article is to draw attention to an aspect of intelligence that has not yet received significant attention from the AI community, but that plays a crucial role in a technology’s effectiveness in the world, namely teaming intelligence. We propose that Al will reach its full potential only if, as part of its intelligence, it also has enough teaming intelligence to work well with people. Although seemingly counterintuitive, the more intelligent the technological system, the greater the need for collaborative skills. This paper will argue why teaming intelligence is important to AI, provide a general structure for AI researchers to use in developing intelligent systems that team well, assess the current state of the art and, in doing so, suggest a path forward for future AI systems. This is not a call to develop a new capability, but rather, an approach to what AI capabilities should be built, and how, so as to imbue intelligent systems with teaming competence.

Behavioral Genetics: Concepts for Research and Practice in Language Development and Disorders

1995 ◽  
Vol 38 (5) ◽  
pp. 1126-1142 ◽  
Author(s):  
Jeffrey W. Gilger
Keyword(s):  
Language Development ◽  
Behavioral Genetics ◽  
State Of The Art ◽  
Genetic Research ◽  
Great Promise ◽  
Behavioral Genetic ◽  
Fine Grained ◽  
Future Goals ◽  
Current State ◽  
Research Designs

This paper is an introduction to behavioral genetics for researchers and practioners in language development and disorders. The specific aims are to illustrate some essential concepts and to show how behavioral genetic research can be applied to the language sciences. Past genetic research on language-related traits has tended to focus on simple etiology (i.e., the heritability or familiality of language skills). The current state of the art, however, suggests that great promise lies in addressing more complex questions through behavioral genetic paradigms. In terms of future goals it is suggested that: (a) more behavioral genetic work of all types should be done—including replications and expansions of preliminary studies already in print; (b) work should focus on fine-grained, theory-based phenotypes with research designs that can address complex questions in language development; and (c) work in this area should utilize a variety of samples and methods (e.g., twin and family samples, heritability and segregation analyses, linkage and association tests, etc.).

Schizophrenia Research: Current State of the Art

1976 ◽  
Vol 21 (7) ◽  
pp. 497-498
Author(s):  
STANLEY GRAND
Keyword(s):  
State Of The Art ◽  
Current State

Umbral Calculus

10.37236/24 ◽  
2002 ◽  
Vol 1000 ◽  
Author(s):  
A. Di Bucchianico ◽  
D. Loeb
Keyword(s):  
19Th Century ◽  
Finite Differences ◽  
State Of The Art ◽  
Umbral Calculus ◽  
Current State ◽  
Logical Foundation ◽  
Complete Bibliography ◽  
The 19Th Century ◽  
Mathematical Literature

We survey the mathematical literature on umbral calculus (otherwise known as the calculus of finite differences) from its roots in the 19th century (and earlier) as a set of “magic rules” for lowering and raising indices, through its rebirth in the 1970’s as Rota’s school set it on a firm logical foundation using operator methods, to the current state of the art with numerous generalizations and applications. The survey itself is complemented by a fairly complete bibliography (over 500 references) which we expect to update regularly.

Automated C-11 Methyl Iodide/Triflate Production: Current State of the Art

2013 ◽  
Vol 17 (19) ◽  
pp. 2119-2126 ◽  
Author(s):  
Bruce Mock
Keyword(s):  
Methyl Iodide ◽  
State Of The Art ◽  
Current State

The Receptor-Dependent QSAR Paradigm: An Overview of the Current State of the Art

2009 ◽  
Vol 5 (4) ◽  
pp. 359-366 ◽  
Author(s):  
Osvaldo Santos-Filho ◽  
Anton Hopfinger ◽  
Artem Cherkasov ◽  
Ricardo de Alencastro
Keyword(s):  
State Of The Art ◽  
Current State

scholarly journals CoCoX: Generating Conceptual and Counterfactual Explanations via Fault-Lines

2020 ◽  
Vol 34 (03) ◽  
pp. 2594-2601
Author(s):  
Arjun Akula ◽  
Shuai Wang ◽  
Song-Chun Zhu
Keyword(s):  
Neural Network ◽  
State Of The Art ◽  
Input Image ◽  
Classification Model ◽  
Learning Models ◽  
Fault Line ◽  
Semantic Level ◽  
Explainable Ai ◽  
Fault Lines ◽  
Classification Category

We present CoCoX (short for Conceptual and Counterfactual Explanations), a model for explaining decisions made by a deep convolutional neural network (CNN). In Cognitive Psychology, the factors (or semantic-level features) that humans zoom in on when they imagine an alternative to a model prediction are often referred to as fault-lines. Motivated by this, our CoCoX model explains decisions made by a CNN using fault-lines. Specifically, given an input image I for which a CNN classification model M predicts class cpred, our fault-line based explanation identifies the minimal semantic-level features (e.g., stripes on zebra, pointed ears of dog), referred to as explainable concepts, that need to be added to or deleted from I in order to alter the classification category of I by M to another specified class calt. We argue that, due to the conceptual and counterfactual nature of fault-lines, our CoCoX explanations are practical and more natural for both expert and non-expert users to understand the internal workings of complex deep learning models. Extensive quantitative and qualitative experiments verify our hypotheses, showing that CoCoX significantly outperforms the state-of-the-art explainable AI models. Our implementation is available at https://github.com/arjunakula/CoCoX

scholarly journals Smoothing additive manufactured parts using ns-pulsed laser radiation

2021 ◽  
Author(s):  
Florian Kuisat ◽  
Fernando Lasagni ◽  
Andrés Fabián Lasagni
Keyword(s):  
Surface Roughness ◽  
Mechanical Performance ◽  
State Of The Art ◽  
Pulsed Laser ◽  
Industrial Applications ◽  
Laser Source ◽  
Pulsed Laser Radiation ◽  
Current State ◽  
The Impact

AbstractIt is well known that the surface topography of a part can affect its mechanical performance, which is typical in additive manufacturing. In this context, we report about the surface modification of additive manufactured components made of Titanium 64 (Ti64) and Scalmalloy®, using a pulsed laser, with the aim of reducing their surface roughness. In our experiments, a nanosecond-pulsed infrared laser source with variable pulse durations between 8 and 200 ns was applied. The impact of varying a large number of parameters on the surface quality of the smoothed areas was investigated. The results demonstrated a reduction of surface roughness Sa by more than 80% for Titanium 64 and by 65% for Scalmalloy® samples. This allows to extend the applicability of additive manufactured components beyond the current state of the art and break new ground for the application in various industrial applications such as in aerospace.

Sign in / Sign up

Export Citation Format

Share Document