Derek Doran
YOU?
Author Swipe
View article: Explainable Deep Learning: A Field Guide for the Uninitiated
Explainable Deep Learning: A Field Guide for the Uninitiated Open
Deep neural networks (DNNs) are an indispensable machine learning tool despite the difficulty of diagnosing what aspects of a model’s input drive its decisions. In countless real-world domains, from legislation and law enforcement to healt…
View article: Explainable Deep Learning: A Field Guide for the Uninitiated
Explainable Deep Learning: A Field Guide for the Uninitiated Open
Deep neural networks (DNNs) have become a proven and indispensable machine learning tool. As a black-box model, it remains difficult to diagnose what aspects of the model's input drive the decisions of a DNN. In countless real-world domain…
View article: A First Look at References from the Dark to Surface Web World
A First Look at References from the Dark to Surface Web World Open
Tor is one of the most well-known networks that protects the identity of both content providers and their clients against any tracking or tracing on the Internet. So far, most research attention has been focused on investigating the securi…
View article: Contextual Grounding of Natural Language Entities in Images
Contextual Grounding of Natural Language Entities in Images Open
In this paper, we introduce a contextual grounding approach that captures the context in corresponding text entities and image regions to improve the grounding accuracy. Specifically, the proposed architecture accepts pre-trained text toke…
View article: A Broad Evaluation of the Tor English Content Ecosystem
A Broad Evaluation of the Tor English Content Ecosystem Open
Tor is among most well-known dark net in the world. It has noble uses, including as a platform for free speech and information dissemination under the guise of true anonymity, but may be culturally better known as a conduit for criminal ac…
View article: Fuzzy Rough Set Feature Selection to Enhance Phishing Attack Detection
Fuzzy Rough Set Feature Selection to Enhance Phishing Attack Detection Open
Phishing as one of the most well-known cybercrime activities is a deception of online users to steal their personal or confidential information by impersonating a legitimate website. Several machine learning-based strategies have been prop…
View article: Knowledge Graph Enhanced Community Detection and Characterization
Knowledge Graph Enhanced Community Detection and Characterization Open
Recent studies show that by combining network topology and node attributes, we can better understand community structures in complex networks. However, existing algorithms do not explore “contextually” similar node attribute values, and th…
View article: Visual Entailment: A Novel Task for Fine-Grained Image Understanding
Visual Entailment: A Novel Task for Fine-Grained Image Understanding Open
Existing visual reasoning datasets such as Visual Question Answering (VQA), often suffer from biases conditioned on the question, image or answer distributions. The recently proposed CLEVR dataset addresses these limitations and requires f…
View article: <b>dbscan</b>: Fast Density-Based Clustering with <i>R</i>
<b>dbscan</b>: Fast Density-Based Clustering with <i>R</i> Open
This article describes the implementation and use of the R package dbscan, which provides complete and fast implementations of the popular density-based clustering algorithm DBSCAN and the augmented ordering algorithm OPTICS. Package dbsca…
View article: Contextual Grounding of Natural Language Entities in Images
Contextual Grounding of Natural Language Entities in Images Open
In this paper, we introduce a contextual grounding approach that captures the context in corresponding text entities and image regions to improve the grounding accuracy. Specifically, the proposed architecture accepts pre-trained text toke…
View article: HELOC Applicant Risk Performance Evaluation by Topological Hierarchical Decomposition
HELOC Applicant Risk Performance Evaluation by Topological Hierarchical Decomposition Open
Strong regulations in the financial industry mean that any decisions based on machine learning need to be explained. This precludes the use of powerful supervised techniques such as neural networks. In this study we propose a new unsupervi…
View article: Visual Entailment Task for Visually-Grounded Language Learning
Visual Entailment Task for Visually-Grounded Language Learning Open
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. A novel dataset SNL…
View article: Reasoning over RDF Knowledge Bases using Deep Learning
Reasoning over RDF Knowledge Bases using Deep Learning Open
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. Reasoning, i.e., the drawing of logical inference…
View article: Contrasting Web Robot and Human Behaviors with Network Models
Contrasting Web Robot and Human Behaviors with Network Models Open
The web graph is a commonly-used network representation of the hyperlink structure of a website. A network of similar structure to the web graph, which we call the session graph has properties that reflect the browsing habits of the agents…
View article: Seasonal Stochastic Blockmodeling for Anomaly Detection in Dynamic Networks
Seasonal Stochastic Blockmodeling for Anomaly Detection in Dynamic Networks Open
Sociotechnological and geospatial processes exhibit time varying structure that make insight discovery challenging. To detect abnormal moments in these processes, a definition of `normal' must be established. This paper proposes a new stat…
View article: Intrinsic Point of Interest Discovery from Trajectory Data
Intrinsic Point of Interest Discovery from Trajectory Data Open
This paper presents a framework for intrinsic point of interest discovery from trajectory databases. Intrinsic points of interest are regions of a geospatial area innately defined by the spatial and temporal aspects of trajectory data, and…
View article: Realistic Traffic Generation for Web Robots
Realistic Traffic Generation for Web Robots Open
Critical to evaluating the capacity, scalability, and availability of web systems are realistic web traffic generators. Web traffic generation is a classic research problem, no generator accounts for the characteristics of web robots or cr…
View article: Relating Input Concepts to Convolutional Neural Network Decisions
Relating Input Concepts to Convolutional Neural Network Decisions Open
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. The methods hypothesize that the recognition of these …
View article: Explaining Trained Neural Networks with Semantic Web Technologies: First Steps
Explaining Trained Neural Networks with Semantic Web Technologies: First Steps Open
The ever increasing prevalence of publicly available structured data on the World Wide Web enables new applications in a variety of domains. In this paper, we provide a conceptual approach that leverages such data in order to explain the i…
View article: Explaining Trained Neural Networks with Semantic Web Technologies: First\n Steps
Explaining Trained Neural Networks with Semantic Web Technologies: First\n Steps Open
The ever increasing prevalence of publicly available structured data on the\nWorld Wide Web enables new applications in a variety of domains. In this paper,\nwe provide a conceptual approach that leverages such data in order to explain\nth…
View article: What Does Explainable AI Really Mean? A New Conceptualization of Perspectives
What Does Explainable AI Really Mean? A New Conceptualization of Perspectives Open
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 mechani…
View article: EmojiNet: An Open Service and API for Emoji Sense Discovery
EmojiNet: An Open Service and API for Emoji Sense Discovery Open
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. EmojiNet is a dataset consisting of: (i) 12,904 sens…
View article: EmojiNet: An Open Service and API for Emoji Sense Discovery
EmojiNet: An Open Service and API for Emoji Sense Discovery Open
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. EmojiNet is a dataset consisting of: (i) 12,904 sens…
View article: What Does Explainable AI Really Mean? a New Conceptualization of Perspectives
What Does Explainable AI Really Mean? a New Conceptualization of Perspectives Open
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 mechani…
View article: Finding Street Gang Members on Twitter
Finding Street Gang Members on Twitter Open
Most street gang members use Twitter to intimidate others, to present outrageous images and statements to the world, and to share recent illegal activities. Their tweets may thus be useful to law enforcement agencies to discover clues abou…
View article: Word Embeddings to Enhance Twitter Gang Member Profile Identification
Word Embeddings to Enhance Twitter Gang Member Profile Identification Open
Gang affiliates have joined the masses who use social media to share thoughts and actions publicly. Interestingly, they use this public medium to express recent illegal actions, to intimidate others, and to share outrageous images and stat…
View article: EmojiNet: Building a Machine Readable Sense Inventory for Emoji
EmojiNet: Building a Machine Readable Sense Inventory for Emoji Open
Emoji are a contemporary and extremely popular way to enhance electronic communication. Without rigid semantics attached to them, emoji symbols take on different meanings based on the context of a message. Thus, like the word sense disambi…
View article: Finding Street Gang Members on Twitter.
Finding Street Gang Members on Twitter. Open
Most street gang members use Twitter to intimidate others, to present outrageous images and statements to the world, and to share recent illegal activities. Their tweets may thus be useful to law enforcement agencies to discover clues abou…