Artificial Intelligence and Robotics Commons^™

Wider Vision: Enriching Convolutional Neural Networks Via Alignment To External Knowledge Bases, Xuehao Liu, Sarah Jane Delany, Susan Mckeever

Conference papers

Deep learning models suffer from opaqueness. For Convolutional Neural Networks (CNNs), current research strategies for explaining models focus on the target classes within the associated training dataset. As a result, the understanding of hidden feature map activations is limited by the discriminative knowledge gleaned during training. The aim of our work is to explain and expand CNNs models via the mirroring or alignment of the network to an external knowledge base. This will allow us to give a semantic context or label for each visual feature. Using the resultant aligned embedding space, we can match CNN feature activations to nodes …

Fairer Evaluation Of Zero Shot Action Recognition In Videos, Kaiqiang Huang, Sarah Jane Delany, Susan Mckeever

Conference Papers

Zero-shot learning (ZSL) for human action recognition (HAR) aims to recognise video action classes that have never been seen during model training. This is achieved by building mappings between visual and semantic embeddings. These visual embeddings are typically provided via a pre-trained deep neural network (DNN). The premise of ZSL is that the training and testing classes should be disjoint. In the parallel domain of ZSL for image input, the widespread poor evaluation protocol of pre-training on ZSL test classes has been highlighted. This is akin to providing a sneak preview of the evaluation classes. In this work, we investigate …

Zero-Shot Action Recognition With Knowledge Enhanced Generative Adversarial Networks, Kaiqiang Huang, Luis Miralles-Pechuán, Susan Mckeever

Conference papers

Zero-Shot Action Recognition (ZSAR) aims to recognise action classes in videos that have never been seen during model training. In some approaches, ZSAR has been achieved by generating visual features for unseen classes based on the semantic information of the unseen class labels using generative adversarial networks (GANs). Therefore, the problem is converted to standard supervised learning since the unseen visual features are accessible. This approach alleviates the lack of labelled samples of unseen classes. In addition, objects appearing in the action instances could be used to create enriched semantics of action classes and therefore, increase the accuracy of ZSAR. …

K-Nearest Neighbour Classifiers - A Tutorial, Padraig Cunningham, Sarah Jane Delany

Conference papers

Perhaps the most straightforward classifier in the arsenal or Machine Learning techniques is the Nearest Neighbour Classifier – classification is achieved by identifying the nearest neighbours to a query example and using those neighbours to determine the class of the query. This approach to classification is of particular importance because issues of poor run-time performance is not such a problem these days with the computational power that is available. This paper presents an overview of techniques for Nearest Neighbour classification focusing on; mechanisms for assessing similarity (distance), computational issues in identifying nearest neighbours and mechanisms for reducing the dimension of …

Virtual Tutor Personality In Computer Assisted Language Learning, Johanna Dobbriner, Cathy Ennis, Robert J. Ross

Conference papers

The use of intelligent virtual agents in language learning has increased in recent years. Studies into several aspects of personalisation aiming to increase user engagement are an ongoing research topic with avatar personality being one such aspect. As a step towards our development of intelligent virtual avatars, we present two of our initial experiments to explore differences in user interaction with two contrasting avatar personalities -- P1: open-minded, friendly and sociable and P2: closed-off, curt and distant. Each user interacted with a single personality in a video-call setting and gave feedback on the interaction. Our expectations, that P1 would be …

Data: The Good, The Bad And The Ethical, John D. Kelleher, Filipe Cabral Pinto, Luis M. Cortesao

Articles

It is often the case with new technologies that it is very hard to predict their long-term impacts and as a result, although new technology may be beneficial in the short term, it can still cause problems in the longer term. This is what happened with oil by-products in different areas: the use of plastic as a disposable material did not take into account the hundreds of years necessary for its decomposition and its related long-term environmental damage. Data is said to be the new oil. The message to be conveyed is associated with its intrinsic value. But as in …

Lightgwas: A Novel Machine Learning Procedure For Genome-Wide Association Study, Ambrozio Bruno, Luca Longo, Lucas Rizzo

Articles

This paper proposes a novel machine learning procedure for genome-wide association study (GWAS), named LightGWAS. It is based on the LightGBM framework, in addition to being a single, resilient, autonomous and scalable solution to address common limitations of GWAS implementations found in the literature. These include reliance on massive manual quality control steps and specific GWAS methods for each type of dataset morphology and size. Through this research, LightGWAS has been contrasted against PLINK2, one of the current state-of-the-art for GWAS implementations based on general linear model with support to firth regularisation. The mean differences measured upon standard classification metrics, …

A Comparative Analysis Of Rule-Based, Model-Agnostic Methods For Explainable Artificial Intelligence, Giulia Vilone, Lucas Rizzo, Luca Longo

Articles

The ultimate goal of Explainable Artificial Intelligence is to build models that possess both high accuracy and degree of explainability. Understanding the inferences of such models can be seen as a process that discloses the relationships between their input and output. These relationships can be represented as a set of inference rules which are usually not explicit within a model. Scholars have proposed several methods for extracting rules from data-driven machine-learned models. However, limited work exists on their comparison. This study proposes a novel comparative approach to evaluate and compare the rulesets produced by four post-hoc rule extractors by employing …

Exploring The Potential Of Defeasible Argumentation For Quantitative Inferences In Real-World Contexts: An Assessment Of Computational Trust, Lucas Rizzo, Pierpaolo Dondio, Luca Longo

Articles

Argumentation has recently shown appealing properties for inference under uncertainty and conflicting knowledge. However, there is a lack of studies focused on the examination of its capacity of exploiting real-world knowledge bases for performing quantitative, case-by-case inferences. This study performs an analysis of the inferential capacity of a set of argument-based models, designed by a human reasoner, for the problem of trust assessment. Precisely, these models are exploited using data from Wikipedia, and are aimed at inferring the trustworthiness of its editors. A comparison against non-deductive approaches revealed that these models were superior according to values inferred to recognised trustworthy …

Language-Driven Region Pointer Advancement For Controllable Image Captioning, Annika Lindh, Robert J. Ross, John D. Kelleher

Conference papers

Controllable Image Captioning is a recent sub-field in the multi-modal task of Image Captioning wherein constraints are placed on which regions in an image should be described in the generated natural language caption. This puts a stronger focus on producing more detailed descriptions, and opens the door for more end-user control over results. A vital component of the Controllable Image Captioning architecture is the mechanism that decides the timing of attending to each region through the advancement of a region pointer. In this paper, we propose a novel method for predicting the timing of region pointer advancement by treating the …

Energy-Based Neural Modelling For Large-Scale Multiple Domain Dialogue State Tracking, Anh Duong Trinh, Robert J. Ross, John D. Kelleher

Conference papers

Scaling up dialogue state tracking to multiple domains is challenging due to the growth in the number of variables being tracked. Furthermore, dialog state tracking models do not yet explicitly make use of relationships between dialogue variables, such as slots across domains. We propose using energy-based structure prediction methods for large-scale dialogue state tracking task in two multiple domain dialogue datasets. Our results indicate that: (i) modelling variable dependencies yields better results; and (ii) the structured prediction output aligns with the dialogue slot-value constraint principles. This leads to promising directions to improve state-of-the-art models by incorporating variable dependencies into their …

F-Measure Optimisation And Label Regularisation For Energy-Based Neural Dialogue State Tracking Models, Anh Duong Trinh, Robert J. Ross, John D. Kelleher

Conference papers

In recent years many multi-label classification methods have exploited label dependencies to improve performance of classification tasks in various domains, hence casting the tasks to structured prediction problems. We argue that multi-label predictions do not always satisfy domain constraint restrictions. For example when the dialogue state tracking task in task-oriented dialogue domains is solved with multi-label classification approaches, slot-value constraint rules should be enforced following real conversation scenarios.

To address these issues we propose an energy-based neural model to solve the dialogue state tracking task as a structured prediction problem. Furthermore we propose two improvements over previous methods with respect …

Automatic Flood Detection In Sentinei-2 Images Using Deep Convolutional Neural Networks, Pallavi Jain, Bianca Schoen-Phelan, Robert J. Ross

Conference papers

The early and accurate detection of floods from satellite imagery can aid rescue planning and assessment of geophysical damage. Automatic identification of water from satellite images has historically relied on hand-crafted functions, but these often do not provide the accuracy and robustness needed for accurate and early flood detection. To try to overcome these limitations we investigate a tiered methodology combining water index like features with a deep convolutional neural network based solution to flood identification against the MediaEval 2019 flood dataset. Our method builds on existing deep neural network methods, and in particular the VGG16 network. Specifically, we explored …

Noise Reduction Of Eeg Signals Using Autoencoders Built Upon Gru Based Rnn Layers, Esra Aynali

Dissertations

Understanding the cognitive and functional behaviour of the brain by its electrical activity is an important area of research. Electroencephalography (EEG) is a method that measures and record electrical activities of the brain from the scalp. It has been used for pathology analysis, emotion recognition, clinical and cognitive research, diagnosing various neurological and psychiatric disorders and for other applications. Since the EEG signals are sensitive to activities other than the brain ones, such as eye blinking, eye movement, head movement, etc., it is not possible to record EEG signals without any noise. Thus, it is very important to use an …

Preface To The Special Issue On Advances In Argumentation In Artificial Intelligence, Pierpaolo Dondio, Luca Longo, Stefano Bistarelli

Articles

Now at the forefront of automated reasoning, argumentation has become a key research topic within Artificial Intelligence. It involves the investigation of those activities for the production and exchange of arguments, where arguments are attempts to persuade someone of something by giving reasons for accepting a particular conclusion or claim as evident. The study of argumentation has been the focus of attention of philosophers and scholars, from Aristotle and classical rhetoric to the present day. The computational study of arguments has emerged as a field of research in AI in the last two decades, mainly fuelled by the interest from …

Beyond Reasonable Doubt: A Proposal For Undecidedness Blocking In Abstract Argumentation, Pierpaolo Dondio, Luca Longo

Articles

In Dung’s abstract semantics, the label undecided is always propagated from the attacker to the attacked argument, unless the latter is also attacked by an accepted argument. In this work we propose undecidedness blocking abstract argumentation semantics where the undecided label is confined to the strong connected component where it was generated and it is not propagated to the other parts of the argumentation graph. We show how undecidedness blocking is a fundamental reasoning pattern absent in abstract argumentation but present in similar fashion in the ambiguity blocking semantics of Defeasible logic, in the beyond reasonable doubt legal principle or …

Multimodal Fusion Strategies For Outcome Prediction In Stroke, Esra Zihni, John D. Kelleher, Vince I. Madai, Ahmed Khalil, Ivana Galinovic, Jochen Fiebach, Michelle Livne, Dietmar Frey

Conference papers

Data driven methods are increasingly being adopted in the medical domain for clinical predictive modeling. Prediction of stroke outcome using machine learning could provide a decision support system for physicians to assist them in patient-oriented diagnosis and treatment. While patient-specific clinical parameters play an important role in outcome prediction, a multimodal fusion approach that integrates neuroimaging with clinical data has the potential to improve accuracy. This paper addresses two research questions: (a) does multimodal fusion aid in the prediction of stroke outcome, and (b) what fusion strategy is more suitable for the task at hand. The baselines for our experimental …

Language Model Co-Occurrence Linking For Interleaved Activity Discovery, Eoin Rogers, Robert J. Ross, John D. Kelleher

Conference papers

As ubiquitous computer and sensor systems become abundant, the potential for automatic identification and tracking of human behaviours becomes all the more evident. Annotating complex human behaviour datasets to achieve ground truth for supervised training can however be extremely labour-intensive, and error prone. One possible solution to this problem is activity discovery: the identification of activities in an unlabelled dataset by means of an unsupervised algorithm. This paper presents a novel approach to activity discovery that utilises deep learning based language production models to construct a hierarchical, tree-like structure over a sequential vector of sensor events. Our approach differs from …

Modelling Interleaved Activities Using Language Models, Eoin Rogers, Robert J. Ross, John D. Kelleher

Conference papers

We propose a new approach to activity discovery, based on the neural language modelling of streaming sensor events. Our approach proceeds in multiple stages: we build binary links between activities using probability distributions generated by a neural language model trained on the dataset, and combine the binary links to produce complex activities. We then use the activities as sensor events, allowing us to build complex hierarchies of activities. We put an emphasis on dealing with interleaving, which represents a major challenge for many existing activity discovery systems. The system is tested on a realistic dataset, demonstrating it as a promising …

Mutual Information Decay Curves And Hyper-Parameter Grid Search Design For Recurrent Neural Architectures, Abhijit Mahalunkar, John Kelleher

Conference papers

We present an approach to design the grid searches for hyper-parameter optimization for recurrent neural architectures. The basis for this approach is the use of mutual information to analyze long distance dependencies (LDDs) within a dataset. We also report a set of experiments that demonstrate how using this approach, we obtain state-of-the-art results for DilatedRNNs across a range of benchmark datasets.

Update Frequency And Background Corpus Selection In Dynamic Tf-Idf Models For First Story Detection, Fei Wang, Robert J. Ross, John D. Kelleher

Conference papers

First Story Detection (FSD) requires a system to detect the very first story that mentions an event from a stream of stories. Nearest neighbour-based models, using the traditional term vector document representations like TF-IDF, currently achieve the state of the art in FSD. Because of its online nature, a dynamic term vector model that is incrementally updated during the detection process is usually adopted for FSD instead of a static model. However, very little research has investigated the selection of hyper-parameters and the background corpora for a dynamic model. In this paper, we analyse how a dynamic term vector model …

Capturing Dialogue State Variable Dependencies With An Energy-Based Neural Dialogue State Tracker, Anh Duong Trinh, Robert J. Ross, John D. Kelleher

Conference papers

Dialogue state tracking requires the population and maintenance of a multi-slot frame representation of the dialogue state. Frequently, dialogue state tracking systems assume independence between slot values within a frame. In this paper we argue that treating the prediction of each slot value as an independent prediction task may ignore important associations between the slot values, and, consequently, we argue that treating dialogue state tracking as a structured prediction problem can help to improve dialogue state tracking performance. To support this argument, the research presented in this paper is structured into three stages: (i) analyzing variable dependencies in dialogue data; …

Investigating Variable Dependencies In Dialogue States, Anh Duong Trinh, Robert J. Ross, John D. Kelleher

Conference papers

Dialogue State Tracking is arguably one of the most challenging tasks among dialogue processing problems due to the uncertainties of language and complexity of dialogue contexts. We argue that this problem is made more challenging by variable dependencies in the dialogue states that must be accounted for in processing. In this paper we give details on our motivation for this argument through statistical tests on a number of dialogue datasets. We also propose a machine learning-based approach called energy-based learning that tackles variable dependencies while performing prediction on the dialogue state tracking tasks.

Bigger Versus Similar: Selecting A Background Corpus For First Story Detection Based On Distributional Similarity, Fei Wang, Robert J. Ross, John D. Kelleher

Conference papers

The current state of the art for First Story Detection (FSD) are nearest neighbour-based models with traditional term vector representations; however, one challenge faced by FSD models is that the document representation is usually defined by the vocabulary and term frequency from a background corpus. Consequently, the ideal background corpus should arguably be both large-scale to ensure adequate term coverage, and similar to the target domain in terms of the language distribution. However, given these two factors cannot always be mutually satisfied, in this paper we examine whether the distributional similarity of common terms is more important than the scale …

Estimating Distributed Representation Performance In Disaster-Related Social Media Classification, Pallavi Jain, Robert J. Ross, Bianca Schoen-Phelan

Conference papers

This paper examines the effectiveness of a range of pre-trained language representations in order to determine the informativeness and information type of social media in the event of natural or man-made disasters. Within the context of disaster tweet analysis, we aim to accurately analyse tweets while minimising both false positive and false negatives in the automated information analysis. The investigation is performed across a number of well known disaster-related twitter datasets. Models that are built from pre-trained word embeddings from Word2Vec, GloVe, ELMo and BERT are used for performance evaluation. Given the relative ubiquity of BERT as a standout language …

Energy-Based Modelling For Dialogue State Tracking, Anh Duong Trinh, Robert J. Ross, John D. Kelleher

Conference papers

The uncertainties of language and the complexity of dialogue contexts make accurate dialogue state tracking one of the more challenging aspects of dialogue processing. To improve state tracking quality, we argue that relationships between different aspects of dialogue state must be taken into account as they can often guide a more accurate interpretation process. To this end, we present an energy-based approach to dialogue state tracking as a structured classification task. The novelty of our approach lies in the use of an energy network on top of a deep learning architecture to explore more signal correlations between network variables including …

Synthetic, Yet Natural: Properties Of Wordnet Random Walk Corpora And The Impact Of Rare Words On Embedding Performance, Filip Klubicka, Alfredo Maldonado, Abhijit Mahalunkar, John D. Kelleher

Conference papers

Creating word embeddings that reflect semantic relationships encoded in lexical knowledge resources is an open challenge. One approach is to use a random walk over a knowledge graph to generate a pseudo-corpus and use this corpus to train embeddings. However, the effect of the shape of the knowledge graph on the generated pseudo-corpora, and on the resulting word embeddings, has not been studied. To explore this, we use English WordNet, constrained to the taxonomic (tree-like) portion of the graph, as a case study. We investigate the properties of the generated pseudo-corpora, and their impact on the resulting embeddings. We find …

Comparative Study Of Feature Representations For Disaster Tweet Classification, Pallavi Jain, Bianca Schoen-Phelan, Robert J. Ross

Other resources

Twitter is a popular social media platform where users publicly broadcast short messages on a myriad of topics. In recent years it has enjoyed an increased usage around disaster events due to availability of information in near real time. Additionally, enhanced information representations to facilitate the classification of social media in terms of relevancy and type of information is currently a highly active research area (Ashktorab et al., 2014, Imran et al., 2014, Win et al., 2018). In this work we consider the usefulness and reliability of a range of representation models in the analysis of disaster related social media.

Examining The Limits Of Predictability Of Human Mobility, Vaibhav Klukarni, Abhijit Mahalunkar, Benoit Garbinato, John D. Kelleher

Articles

We challenge the upper bound of human-mobility predictability that is widely used to corroborate the accuracy of mobility prediction models. We observe that extensions of recurrent-neural network architectures achieve significantly higher prediction accuracy, surpassing this upper bound. Given this discrepancy, the central objective of our work is to show that the methodology behind the estimation of the predictability upper bound is erroneous and identify the reasons behind this discrepancy. In order to explain this anomaly, we shed light on several underlying assumptions that have contributed to this bias. In particular, we highlight the consequences of the assumed Markovian nature of …

Automatic Acquisition Of Annotated Training Corpora For Test-Code Generation, Magdalena Kacmajor, John D. Kelleher

Articles

Open software repositories make large amounts of source code publicly available. Potentially, this source code could be used as training data to develop new, machine learning-based programming tools. For many applications, however, raw code scraped from online repositories does not constitute an adequate training dataset. Building on the recent and rapid improvements in machine translation (MT), one possibly very interesting application is code generation from natural language descriptions. One of the bottlenecks in developing these MT-inspired systems is the acquisition of parallel text-code corpora required for training code-generative models. This paper addresses the problem of automatically synthetizing parallel text-code corpora …