Machine Learning Methods for Commonsense Reasoning Processes

Naidenova, Xenia

doi:10.4018/978-1-60566-810-9

Cited by 5 publications

(7 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An event based formal system is defined for a multi modal UI interface with cloud functions using Amazon AWS as an illustration . A comparison with other formal systems, (Pommaret, Haddak, and Bendiab 1989;Torbensen 2008) Introduced in this publication, (Naidenova and Xenia 2009;Mueller 2014;Minsky 2007;Sun 1994;Friedman, Forbus, and Sherin 2018;McCarthy and Lifschitz 1990) There has been a plethora on formalizing common sense, with many early attempts at creating a A.…”

Section: Discussionmentioning

confidence: 99%

Formal Methods for Multi Modal UI for Robotics

Bheemaiah¹

2019

Preprint

View full text Add to dashboard Cite

A formal system of mathematics the dog-ears, is introduced to describe javascript or object notation, sensor event and action event with state modelling in the framework of DPA for a smart home and work robotics . It is assumed that a multi modal interface can be developed similar to AWS APL for this purpose.The RAVA natural programming language is introduced, which simplifies coding by eliminating the need for syntax.

show abstract

Section: Discussionmentioning

confidence: 99%

Formal Methods for Multi Modal UI for Robotics

Bheemaiah¹

2019

Preprint

View full text Add to dashboard Cite

show abstract

“…The following subsections discuss assumptions, definitions and hypotheses leading to the design of the proposed AXAI capability framework. These assumptions and definitions were inspired by and adopted from the relevant literature (Michie, 1998;Muggleton et al, 2018;Schmid et al, 2017;Mohseni, Zarei & Ragan, 2021;Naidenova, 2009;Poria et al, 2014;Mueller, 2014).…”

Section: The Three-dimensional Space Of Accountable Explainability (A...mentioning

confidence: 99%

“…The term 'AI system' in this paper encompasses: supervised learning-supported classifiers and regression systems, unsupervised learning-supported clustering and labelling systems and, reinforced learning systems including deep neural networks. Therefore, an AI system would include definite symbols, definite functions, definite propositions, definite predicates, logical symbols, object variables and propositional variables (Naidenova, 2009;Mueller, 2014).…”

Section: The Three-dimensional Space Of Accountable Explainability (A...mentioning

confidence: 99%

“…A human possessing the background knowledge » is also considered as a definite program P. Here, D n denotes a definition D having a number n. ½ in this paper denotes a domain. Having these notations and based on the previous works (Liao, Gruen & Miller, 2020;Dignum, 2017;Tai, 2018;Naidenova, 2009), the following subsections describe all measurable parameters belonging to each of the three vectors forming the 3D AXAI measurement space shown in Figure 2.…”

Section: The Three-dimensional Space Of Accountable Explainability (A...mentioning

confidence: 99%

“…Hence, the comprehensibility of P in the context of AXAI refers to the mean readiness ( ) of a human s (s ) for applying the knowledge given in program P to assign a public name to a new definition q with respect to the domain ½ after inspecting P for times T it , T pr and T pn . It is worth mentioning that clustering, primarily an unsupervised method can also be integrated with supervised learning in AI systems such that each cluster can be given an intended definition (Naidenova, 2009). D4A: The inspection time (T it ) is the mean time that a human s (s ) requires for inspecting the information presented by P before using the knowledge provided by P for solving a new problem within the domain ½.…”

Section: Definitionsmentioning

confidence: 99%

See 2 more Smart Citations

Toward Accountable and Explainable Artificial Intelligence Part one: Theory and Examples

Khan¹,

Vice²

2022

Preprint

View full text Add to dashboard Cite

<div>After reviewing the current state of explainable Artificial Intelligence (XAI) capabilities in artificial Intelligence (AI) systems developed for critical domains like criminology, engineering, governance, health, law and psychology, this paper proposes a domain-independent Accountable explainable Artificial Intelligence (AXAI) capability framework. The proposed AXAI framework extends the XAI capability to let AI systems share their decisions and adequately explain the underlying reasoning processes. The idea is to help AI system developers overcome algorithmic biases and system limitations through incorporation of domain independent AXAI capabilities. Moreover, existing XAI methods would neither separate nor quantify measures of comprehensibility, accuracy and accountability so incorporating and assessing XAI capabilities remains difficult. Assessment of the AXAI capabilities of two AI systems in this paper demonstrates that the proposed AXAI framework facilitates separation and measurement of comprehensibility, predictive accuracy and accountability. The AXAI framework allows for the delineation of AI systems in a three-dimensional AXAI space. It measures comprehensibility as the readiness of a human to apply the acquired knowledge. The system accuracy is measured as the ratio of the test and training data, training data size and the observed number of false-positive inferences. Finally, the AXAI framework measures accountability in terms of the inspect ability of the input cues, the processed data and the output information, for addressing any legal and ethical issues.</div>

show abstract

Good Classification Tests as Formal Concepts

Naidenova

2012

Formal Concept Analysis

View full text Add to dashboard Cite

Machine Learning Methods for Commonsense Reasoning Processes

Cited by 5 publications

References 0 publications

Formal Methods for Multi Modal UI for Robotics

Formal Methods for Multi Modal UI for Robotics

Toward Accountable and Explainable Artificial Intelligence Part one: Theory and Examples

Good Classification Tests as Formal Concepts

Contact Info

Product

Resources

About