This article presents the design and pilot of an open online course, based on the principle of universal design for learning (Center for Applied Special Technology, 2011), to promote inclusive virtual education as an improvement transferable to other contexts. The course constitutes the first massive open online course (MOOC) training proposal of the University of Atlántico in Colombia. In this case study, we employed the instructional design methodology of analysis, design, development, implementation, and evaluation (Branch, 2009) and the universal design for learning guidelines. The design of this online training activity enhances the quality of inclusive virtual education, improves accessibility with no need for platform adjustments, and involves participants in their learning. This educational initiative complements the academic offer for students, graduates, administrators, teachers, and external guests, and contributes to the democratisation of education. The result is the creation of a MOOC, "Inclusive Educational Contexts: Design for all", which is accessible to a diverse range of learners. ; This work was supported by the Spanish Ministry of Economy and Competitiveness under project TIN2017-89517-P.
This research was funded by the French ANRT (Association Nationale Recherche Technologie - ANRT) industrial Cifre PhD contract with SEGULA Technologies, the Andalusian Excellence project P18FR-4961 and the Spanish National Project PID2020-119478GB-I00. S. Tabik was supported by the Ramon y Cajal Programme (RYC-201518136). N. Diaz-Rodriguez is currently supported by the Spanish Government Juan de la Cierva Incorporacion contract (IJC2019-039152-I). ; The latest Deep Learning (DL) models for detection and classification have achieved an unprecedented performance over classical machine learning algorithms. However, DL models are black-box methods hard to debug, interpret, and certify. DL alone cannot provide explanations that can be validated by a non technical audience such as end-users or domain experts. In contrast, symbolic AI systems that convert concepts into rules or symbols – such as knowledge graphs – are easier to explain. However, they present lower generalization and scaling capabilities. A very important challenge is to fuse DL representations with expert knowledge. One way to address this challenge, as well as the performance-explainability trade-off is by leveraging the best of both streams without obviating domain expert knowledge. In this paper, we tackle such problem by considering the symbolic knowledge is expressed in form of a domain expert knowledge graph. We present the eXplainable Neural-symbolic learning (X-NeSyL) methodology, designed to learn both symbolic and deep representations, together with an explainability metric to assess the level of alignment of machine and human expert explanations. The ultimate objective is to fuse DL representations with expert domain knowledge during the learning process so it serves as a sound basis for explainability. In particular, X-NeSyL methodology involves the concrete use of two notions of explanation, both at inference and training time respectively: (1) EXPLANet: Expert-aligned eXplainable Part-based cLAssifier NETwork Architecture, a compositional convolutional neural network that makes use of symbolic representations, and (2) SHAP-Backprop, an explainable AI-informed training procedure that corrects and guides the DL process to align with such symbolic representations in form of knowledge graphs. We showcase X-NeSyL methodology using MonuMAI dataset for monument facade image classification, and demonstrate that with our approach, it is possible to improve explainability at the same time as performance. ; French National Research Agency (ANR) ; SEGULA Technologies ; Andalusian Excellence project P18FR-4961 ; Spanish National Project PID2020-119478GB-I00 ; Spanish Government RYC-201518136 ; Spanish Government Juan de la Cierva Incorporacion contract IJC2019-039152-I
This work was supported by the contract OTRI-4408 between the University of Granada and the Royal Academy of Engineering of Spain financed by Ferrovial S.A. Eugenio Martinez Camara was supported by the Spanish Government fellowship programme Juan de la Cierva Incorporacion (IJC2018-036092-I). ; The United Nations Agenda 2030 established 17 Sustainable Development Goals (SDGs) as a guideline to guarantee a sustainable worldwide development. Recent advances in artificial intelligence and other digital technologies have already changed several areas of modern society, and they could be very useful to reach these sustainable goals. In this paper we propose a novel decision making model based on surveys that ranks recommendations on the use of different artificial intelligence and related technologies to achieve the SDGs. According to the surveys, our decision making method is able to determine which of these technologies are worth investing in to lead new research to successfully tackle with sustainability challenges. ; University of Granada - Ferrovial S.A. OTRI-4408 ; Royal Academy of Engineering of Spain - Ferrovial S.A. OTRI-4408 ; Spanish Government fellowship programme Juan de la Cierva Incorporacion IJC2018-036092-I
