no code implementations • 30 Apr 2020 • Gabrielle Ras, Ning Xie, Marcel van Gerven, Derek Doran
The field guide: i) Introduces three simple dimensions defining the space of foundational methods that contribute to explainable deep learning, ii) discusses the evaluations for model explanations, iii) places explainability in the context of other related deep learning research areas, and iv) finally elaborates on user-oriented explanation designing and potential future directions on explainable deep learning.
1 code implementation • 5 Nov 2019 • Farley Lai, Ning Xie, Derek Doran, Asim Kadav
Next, the model learns the contextual representations of the text tokens and image objects through layers of high-order interaction respectively.
no code implementations • 13 Mar 2019 • Mahdieh Zabihimayvan, Derek Doran
To evaluate the FRS feature selection in developing a generalizable phishing detection, the classifiers are trained by a separate out-of-sample data set of 14, 000 website samples.
1 code implementation • 20 Jan 2019 • Ning Xie, Farley Lai, Derek Doran, Asim Kadav
We evaluate various existing VQA baselines and build a model called Explainable Visual Entailment (EVE) system to address the VE task.
Ranked #8 on Visual Entailment on SNLI-VE test
1 code implementation • 26 Nov 2018 • Ning Xie, Farley Lai, Derek Doran, Asim Kadav
We introduce a new inference task - Visual Entailment (VE) - which differs from traditional Textual Entailment (TE) tasks whereby a premise is defined by an image, rather than a natural language sentence as in TE tasks.
no code implementations • 26 Nov 2018 • Kyle Brown, Derek Doran, Ryan Kramer, Brad Reynolds
Strong regulations in the financial industry mean that any decisions based on machine learning need to be explained.
2 code implementations • 9 Nov 2018 • Monireh Ebrahimi, Md. Kamruzzaman Sarker, Federico Bianchi, Ning Xie, Derek Doran, Pascal Hitzler
Semantic Web knowledge representation standards, and in particular RDF and OWL, often come endowed with a formal semantics which is considered to be of fundamental importance for the field.
no code implementations • 23 Oct 2018 • Giuseppe Nebbione, Derek Doran, Srikanth Nadella, Brandon Minnery
We develop a forecast aggregation model that integrates topical information about a question, meta-data about a pair of forecasters, and their predictions in a deep siamese neural network that decides which forecasters' predictions are more likely to be close to the correct response.
no code implementations • 15 Dec 2017 • Kyle Brown, Derek Doran
Web traffic generation is a classic research problem, no generator accounts for the characteristics of web robots or crawlers that are now the dominant source of traffic to a web server.
no code implementations • 14 Dec 2017 • Matthew Piekenbrock, Derek Doran
Spatial and temporal aspects are qualities of any trajectory database, making the framework applicable to data from any domain and of any resolution.
no code implementations • 21 Nov 2017 • Ning Xie, Md. Kamruzzaman Sarker, Derek Doran, Pascal Hitzler, Michael Raymer
Many current methods to interpret convolutional neural networks (CNNs) use visualization techniques and words to highlight concepts of the input seemingly relevant to a CNN's decision.
no code implementations • 11 Oct 2017 • Md. Kamruzzaman Sarker, Ning Xie, Derek Doran, Michael Raymer, Pascal Hitzler
The ever increasing prevalence of publicly available structured data on the World Wide Web enables new applications in a variety of domains.
no code implementations • 2 Oct 2017 • Derek Doran, Sarah Schulz, Tarek R. Besold
We characterize three notions of explainable AI that cut across research fields: opaque systems that offer no insight into its algo- rithmic mechanisms; interpretable systems where users can mathemat- ically analyze its algorithmic mechanisms; and comprehensible systems that emit symbols enabling user-driven explanations of how a conclusion is reached.
2 code implementations • 14 Jul 2017 • Sanjaya Wijeratne, Lakshika Balasuriya, Amit Sheth, Derek Doran
This paper presents a comprehensive analysis of the semantic similarity of emoji through embedding models that are learned over machine-readable emoji meanings in the EmojiNet knowledge base.
no code implementations • 14 Jul 2017 • Sanjaya Wijeratne, Lakshika Balasuriya, Amit Sheth, Derek Doran
This paper presents the release of EmojiNet, the largest machine-readable emoji sense inventory that links Unicode emoji representations to their English meanings extracted from the Web.
no code implementations • 29 Oct 2016 • Lakshika Balasuriya, Sanjaya Wijeratne, Derek Doran, Amit Sheth
A review of these profiles establishes differences in the language, images, YouTube links, and emojis gang members use compared to the rest of the Twitter population.
no code implementations • 27 Oct 2016 • Sanjaya Wijeratne, Lakshika Balasuriya, Derek Doran, Amit Sheth
Gang affiliates have joined the masses who use social media to share thoughts and actions publicly.
no code implementations • 25 Oct 2016 • Sanjaya Wijeratne, Lakshika Balasuriya, Amit Sheth, Derek Doran
It is automatically constructed by integrating multiple emoji resources with BabelNet, which is the most comprehensive multilingual sense inventory available to date.