Computer Sciences Commons^™

Semantic-Based Neural Network Repair, Richard Schumi, Jun Sun

Research Collection School Of Computing and Information Systems

Recently, neural networks have spread into numerous fields including many safety-critical systems. Neural networks are built (and trained) by programming in frameworks such as TensorFlow and PyTorch. Developers apply a rich set of pre-defined layers to manually program neural networks or to automatically generate them (e.g., through AutoML). Composing neural networks with different layers is error-prone due to the non-trivial constraints that must be satisfied in order to use those layers. In this work, we propose an approach to automatically repair erroneous neural networks. The challenge is in identifying a minimal modification to the network so that it becomes valid. …

Augmenting Low-Resource Text Classification With Graph-Grounded Pre-Training And Prompting, Zhihao Wen, Yuan Fang

Research Collection School Of Computing and Information Systems

ext classification is a fundamental problem in information retrieval with many real-world applications, such as predicting the topics of online articles and the categories of e-commerce product descriptions. However, low-resource text classification, with few or no labeled samples, poses a serious concern for supervised learning. Meanwhile, many text data are inherently grounded on a network structure, such as a hyperlink/citation network for online articles, and a user-item purchase network for e-commerce products. These graph structures capture rich semantic relationships, which can potentially augment low-resource text classification. In this paper, we propose a novel model called Graph-Grounded Pre-training and Prompting (G2P2) …

Proactive Conversational Agents In The Post-Chatgpt World, Lizi Liao, Grace Hui Yang, Chirag Shah

Research Collection School Of Computing and Information Systems

ChatGPT and similar large language model (LLM) based conversational agents have brought shock waves to the research world. Although astonished by their human-like performance, we find they share a significant weakness with many other existing conversational agents in that they all take a passive approach in responding to user queries. This limits their capacity to understand the users and the task better and to offer recommendations based on a broader context than a given conversation. Proactiveness is still missing in these agents, including their ability to initiate a conversation, shift topics, or offer recommendations that take into account a more …

An Efficient Hybrid Genetic Algorithm For The Quadratic Traveling Salesman Problem, Quang Anh Pham, Hoong Chuin Lau, Minh Hoang Ha, Lam Vu

Research Collection School Of Computing and Information Systems

The traveling salesman problem (TSP) is the most well-known problem in combinatorial optimization which hasbeen studied for many decades. This paper focuses on dealing with one of the most difficult TSP variants named thequadratic traveling salesman problem (QTSP) that has numerous planning applications in robotics and bioinformatics.The goal of QTSP is similar to TSP which finds a cycle visiting all nodes exactly once with minimum total costs. However, the costs in QTSP are associated with three vertices traversed in succession (instead of two like in TSP). This leadsto a quadratic objective function that is much harder to solve.To efficiently solve …

Modularized Zero-Shot Vqa With Pre-Trained Models, Rui Cao, Jing Jiang

Research Collection School Of Computing and Information Systems

Large-scale pre-trained models (PTMs) show great zero-shot capabilities. In this paper, we study how to leverage them for zero-shot visual question answering (VQA).Our approach is motivated by a few observations. First, VQA questions often require multiple steps of reasoning, which is still a capability that most PTMs lack. Second, different steps in VQA reasoning chains require different skills such as object detection and relational reasoning, but a single PTM may not possess all these skills. Third, recent work on zero-shot VQA does not explicitly consider multi-step reasoning chains, which makes them less interpretable compared with a decomposition-based approach. We propose …

Augmenting Fake Content Detection In Online Platforms: A Domain Adaptive Transfer Learning Via Adversarial Training Approach, Ka Chung Ng, Ping Fan Ke, Mike K. P. So, Kar Yan Tam

Research Collection School Of Computing and Information Systems

Online platforms are experimenting with interventions such as content screening to moderate the effects of fake, biased, and incensing content. Yet, online platforms face an operational challenge in implementing machine learning algorithms for managing online content due to the labeling problem, where labeled data used for model training are limited and costly to obtain. To address this issue, we propose a domain adaptive transfer learning via adversarial training approach to augment fake content detection with collective human intelligence. We first start with a source domain dataset containing deceptive and trustworthy general news constructed from a large collection of labeled news …

Singapore's Hospital To Home Program: Raising Patient Engagement Through Ai, John Abisheganaden, Kheng Hock Lee, Lian Leng Low, Eugene Shum, Han Leong Goh, Christine Gian Lee Ang, Andy Wee An Ta, Steven M. Miller

Research Collection School Of Computing and Information Systems

Because of their complex care needs, many elderly patients are discharged from hospitals only to be readmitted for multiple stays within the following twelve months. John Abisheganaden and his fellow authors describe Singapore’s Hospital to Home program, a community care initiative fueled by artificial intelligence.

Singapore's Ai Applications In The Public Sector: Six Examples, Steven M. Miller

Research Collection School Of Computing and Information Systems

Steven M. Miller describes six instances in which Singapore has applied AI in the public sector, illustrating different ways of improving its engagement with the public by making government services more accessible, anywhere, anytime, and speeding its responses to public processes and feedback. He illustrates how its leaders made the city a living lab for AI use, and what they learned.

Imitation Improvement Learning For Large-Scale Capacitated Vehicle Routing Problems, The Viet Bui, Tien Mai

Research Collection School Of Computing and Information Systems

Recent works using deep reinforcement learning (RL) to solve routing problems such as the capacitated vehicle routing problem (CVRP) have focused on improvement learning-based methods, which involve improving a given solution until it becomes near-optimal. Although adequate solutions can be achieved for small problem instances, their efficiency degrades for large-scale ones. In this work, we propose a newimprovement learning-based framework based on imitation learning where classical heuristics serve as experts to encourage the policy model to mimic and produce similar or better solutions. Moreover, to improve scalability, we propose Clockwise Clustering, a novel augmented framework for decomposing large-scale CVRP into …

Goal Awareness For Conversational Ai: Proactivity, Non-Collaborativity, And Beyond, Yang Deng, Wenqiang Lei, Minlie Huang, Tat-Seng Chua

Research Collection School Of Computing and Information Systems

Conversational systems are envisioned to provide social support or functional service to human users via natural language interactions. Conventional conversation researches mainly focus on the responseability of the system, such as dialogue context understanding and response generation, but overlooks the design of an essential property in intelligent conversations, i.e., goal awareness. The awareness of goals means the state of not only being responsive to the users but also aware of the target conversational goal and capable of leading the conversation towards the goal, which is a significant step towards higher-level intelligence and artificial consciousness. It can not only largely improve …

Strategy‑Aware Bundle Recommender System, Yinwei Wei, Xiaohao Liu, Yunshan Ma, Xiang Wang, Liqiang Nie, Tat‑Seng Chua

Research Collection School Of Computing and Information Systems

A bundle is a group of items that provides improved services to users and increased profits for sellers. However, locating the desired bundles that match the users' tastes still challenges us, due to the sparsity issue. Despite the remarkable performance of existing approaches, we argue that they seldom consider the bundling strategy (i.e., how the items within a bundle are associated with each other) in the bundle recommendation, resulting in the suboptimal user and bundle representations for their interaction prediction. Therefore, we propose to model the strategy-aware user and bundle representations for the bundle recommendation.Towards this end, we develop a …

Generative Ai And Chatgpt: Applications, Challenges, And Ai-Human Collaboration, Fiona Nah, Ruilin Zheng, Jingyuan Cai, Keng Siau, Langtao Chen

Research Collection School Of Computing and Information Systems

Artificial intelligence (AI) has elicited much attention across disciplines and industries (Hyder et al., Citation2019). AI has been defined as “a system’s ability to correctly interpret external data, to learn from such data, and to use those learnings to achieve specific goals and tasks through flexible adaptation” (Kaplan & Haenlein, Citation2019, p. 15). AI has gone through several development stages and AI winters. In the first two decades (i.e., 1950s and 1960s), AI demonstrated success which included programs such as General Problem Solver (Newell et al., Citation1959) and ELIZA (Weizenbaum, Citation1966). However, limitations in processing capacity and reduced spending on …

Characterization And Estimation Of Musculoskeletal Pain Using Machine Learning, Boluwatife Faremi

Master's Theses

Traditional scales utilized for recording pain are known to be highly subjective and biased due to inaccuracies in recollecting actual pain intensities. As a result, machine learning (ML) models that are trained using these scores as ground truth are reported to have low performance for objective pain classification because of the huge disparity between what was felt in moments of pain and the scores recorded afterward.

In the present study, two devices were designed for gathering real-time, continuous in-session subjective pain scores and the recording of the autonomic nervous system (ANS) altered endodermal (EDA) activity. 24 participants were recruited to …

Reinforcement Learning For Sequential Decision Making With Constraints, Jiajing Ling

Dissertations and Theses Collection (Open Access)

Reinforcement learning is a widely used approach to tackle problems in sequential decision making where an agent learns from rewards or penalties. However, in decision-making problems that involve safety or limited resources, the agent's exploration is often limited by constraints. To model such problems, constrained Markov decision processes and constrained decentralized partially observable Markov decision processes have been proposed for single-agent and multi-agent settings, respectively. A significant challenge in solving constrained Dec-POMDP is determining the contribution of each agent to the primary objective and constraint violations. To address this issue, we propose a fictitious play-based method that uses Lagrangian Relaxation …

Managing The Creative Frontier Of Generative Ai: The Novelty-Usefulness Tradeoff, Anirban. Mukherjee, Hannah H. Chang

Research Collection Lee Kong Chian School Of Business

In this paper, drawing inspiration from the human creativity literature, we explore the optimal balance between novelty and usefulness in generative Artificial Intelligence (AI) systems. We posit that overemphasizing either aspect can lead to limitations such as hallucinations and memorization. Hallucinations, characterized by AI responses containing random inaccuracies or falsehoods, emerge when models prioritize novelty over usefulness. Memorization, where AI models reproduce content from their training data, results from an excessive focus on usefulness, potentially limiting creativity. To address these challenges, we propose a framework that includes domain-specific analysis, data and transfer learning, user preferences and customization, custom evaluation metrics, …

Safe Mdp Planning By Learning Temporal Patterns Of Undesirable Trajectories And Averting Negative Side Effects, Siow Meng Low, Akshat Kumar, Scott Sanner

Research Collection School Of Computing and Information Systems

In safe MDP planning, a cost function based on the current state and action is often used to specify safety aspects. In real world, often the state representation used may lack sufficient fidelity to specify such safety constraints. Operating based on an incomplete model can often produce unintended negative side effects (NSEs). To address these challenges, first, we associate safety signals with state-action trajectories (rather than just immediate state-action). This makes our safety model highly general. We also assume categorical safety labels are given for different trajectories, rather than a numerical cost function, which is harder to specify by the …

Learning Deep Time-Index Models For Time Series Forecasting, Jiale Gerald Woo, Chenghao Liu, Doyen Sahoo, Akshat Kumar, Steven Hoi

Research Collection School Of Computing and Information Systems

Deep learning has been actively applied to time series forecasting, leading to a deluge of new methods, belonging to the class of historicalvalue models. Yet, despite the attractive properties of time-index models, such as being able to model the continuous nature of underlying time series dynamics, little attention has been given to them. Indeed, while naive deep timeindex models are far more expressive than the manually predefined function representations of classical time-index models, they are inadequate for forecasting, being unable to generalize to unseen time steps due to the lack of inductive bias. In this paper, we propose DeepTime, a …

Recognizing Hand Gestures Using Solar Cells, Dong Ma, Guohao Lan, Mahbub Hassan, Wen Hu, B. Mushfika Upama, Ashraf Uddin, Youseef, Moustafa

Research Collection School Of Computing and Information Systems

We design a system, SolarGest, which can recognize hand gestures near a solar-powered device by analyzing the patterns of the photocurrent. SolarGest is based on the observation that each gesture interferes with incident light rays on the solar panel in a unique way, leaving its discernible signature in harvested photocurrent. Using solar energy harvesting laws, we develop a model to optimize design and usage of SolarGest. To further improve the robustness of SolarGest under non-deterministic operating conditions, we combine dynamic time warping with Z-score transformation in a signal processing pipeline to pre-process each gesture waveform before it is analyzed for …

Theme Park Visitors Prefer Human-Like Robots In Customer Service Interactions, Ady Milman, Asli D.A. Tasci

Rosen Research Review

Service robots are becoming increasingly popular in many industries and social settings, including education, childcare, elderly therapy centers, and even theme parks. Tourism and hospitality industries are adopting robots enthusiastically and are being closely studied to observe guest engagement and reaction to robotic services. Service robots are becoming increasingly popular in many industries and social settings, including education, childcare, elderly therapy centers, and even theme parks. Tourism and hospitality industries are adopting robots enthusiastically and are being closely studied to observe guest engagement and reaction to robotic services. UCF Rosen College of Hospitality Management researchers, Dr. Ady Milman and Dr. …

Roboboits: A Simulation-Based Tutoring System To Support Ai Education Through Robotics, Sara Guerreiro-Santalla, Helen Crompton, Francisco Bellas

STEMPS Faculty Publications

This paper presents a novel tutoring system to educate pre-university students about AI, a key issue to develop AI in Education for Sustainable Society. With the aim of following a learning-by-doing approach to AI, we decided to focus on robotics as the main application domain for the students’ activities. Specifically, the tutoring system is based on the Robobo educational robot, and its simulation environment. A prototype version of the tutoring system, called RoboboITS, has been released and tested in two in-person sessions with 17 students in a secondary school at Virginia (USA), leading to and promising outcomes for future development.

Deep Learning Model Compression Techniques: Advances, Opportunities, And Perspective, Hubert Msuya

Tanzania Journal of Engineering and Technology (TJET)

Recently, deep learning (DL) models have excelled in a wide range of fields. All of these successes are built on intricate DL models. The hundreds of millions or even billions of parameters and high-performance computing graphical processing units or tensor processing units are largely responsible for their achievement. DL model integration into real-time devices with tight latency limitations, limited memory, and power-constrained requirements is the key driving force behind investigation of DL model compression techniques. Also, there is an increase in data availability that encourages multimodal fusion in DL models to boost the models' predictive accuracy. In order to create …

Harnessing Artificial Intelligence For Early And Evolution Of Alzheimer’S Disease Detections And Enhancing Senior Mental Health Through Innovative Art-Singing Therapies: A Multidisciplinary Approach, Jocelyne Kiss, Geoffreyjen Edwards, Rachel Bouserhal, Elaine Champagne, Thierry Belleguic, Valéry Psyché, Charles Batcho, Carol Hudon, Sylsvie Ratté, Ingrid Verdruyckt, Marie-Hélène Parizeau, Aaron Liu-Rosenbaum, James Hudson, Marie-Louise Bourbeau, Marie Lemieux, Annik Charbonneau

Faculty Scholarship

The well-documented therapeutic potential of group singing for patients living with Alzheimer’s disease (PLAD) has been hindered by COVID-19 restrictions, exacerbating loneliness and cognitive decline among seniors in residential and long-term care centers (CHSLDs). Addressing this challenge, the multidisciplinary study aims to develop a patient-oriented virtual reality (XR) interaction system facilitating group singing for mental health support during confinement and enhancing the understanding of the links between Alzheimer’s disease, social interaction, and singing. The researchers also propose to establish an early AD detection system using voice, facial, and non-invasive biometric measurements and validate the efficacy of selected intervention practices. The …

System-Characterized Artificial Intelligence Approaches For Cardiac Cellular Systems And Molecular Signature Analysis, Ziqian Wu

Dartmouth College Ph.D Dissertations

The dissertation presents a significant advancement in the field of cardiac cellular systems and molecular signature systems by employing machine learning and generative artificial intelligence techniques. These methodologies are systematically characterized and applied to address critical challenges in these domains. A novel computational model is developed, which combines machine learning tools and multi-physics models. The main objective of this model is to accurately predict complex cellular dynamics, taking into account the intricate interactions within the cardiac cellular system. Furthermore, a comprehensive framework based on generative adversarial networks (GANs) is proposed. This framework is designed to generate synthetic data that faithfully …

Optical Response Of 3d Model Topological Nodal-Line Semimetal, Sita Kandel, Godfrey Gumbs, Oleg L. Berman

Publications and Research

Wepresent a semi-analytical expression for both longitudinal and transverse optical conductivities of a model TNLSM employing the Kubo formula with emphasis on the optical spectral weight redistribution, deduced from appropriate Green’s func tions. In this semimetal, the conduction and valence bands cross each other along a one- dimensional curve protected by certain symmetry group in the 3D Brillouin zone. Although the crossing cannot be removed by any perturbations, it can be adjusted by continuous tuning of the Hamiltonian with a parameter α. When α>0, the two bands cross each other near the Γ point in the (kx,ky) plane of …

Can You Answer This? - Exploring Zero-Shot Qa Generalization Capabilities In Large Language Models, Saptarshi Sengupta, Shreya Ghosh, Preslav Nakov, Prasenjit Mitra

Natural Language Processing Faculty Publications

The buzz around Transformer-based Language Models (TLMs) such as BERT, RoBERTa, etc. is well-founded owing to their impressive results on an array of tasks. However, when applied to areas needing specialized knowledge (closed-domain), such as medical, finance, etc. their performance takes drastic hits, sometimes more than their older recurrent/convolutional counterparts. In this paper, we explore zero-shot capabilities of large language models for extractive Question Answering. Our objective is to examine the performance change in the face of domain drift, i.e., when the target domain data is vastly different in semantic and statistical properties from the source domain, in an attempt …

Adversarial Alignment For Source Free Object Detection, Qiaosong Chu, Shuyan Li, Guangyi Chen, Kai Li, Xiu Li

Machine Learning Faculty Publications

Source-free object detection (SFOD) aims to transfer a detector pre-trained on a label-rich source domain to an unlabeled target domain without seeing source data. While most existing SFOD methods generate pseudo labels via a source-pretrained model to guide training, these pseudo labels usually contain high noises due to heavy domain discrepancy. In order to obtain better pseudo supervisions, we divide the target domain into source-similar and source-dissimilar parts and align them in the feature space by adversarial learning. Specifically, we design a detection variance-based criterion to divide the target domain. This criterion is motivated by a finding that larger detection …

Corruption-Tolerant Algorithms For Generalized Linear Models, Bhaskar Mukhoty, Debojyoti Dey, Purushottam Kar

Machine Learning Faculty Publications

This paper presents SVAM (Sequential Variance-Altered MLE), a unified framework for learning generalized linear models under adversarial label corruption in training data. SVAM extends to tasks such as least squares regression, logistic regression, and gamma regression, whereas many existing works on learning with label corruptions focus only on least squares regression. SVAM is based on a novel variance reduction technique that may be of independent interest and works by iteratively solving weighted MLEs over variance-altered versions of the GLM objective. SVAM offers provable model recovery guarantees superior to the state-of-the-art for robust regression even when a constant fraction of training …

Graphprompt: Graph-Based Prompt Templates For Biomedical Synonym Prediction, Hanwen Xu, Jiayou Zhang, Zhirui Wang, Shizhuo Zhang, Megh Bhalerao, Yucong Liu, Dawei Zhu, Sheng Wang

Computer Vision Faculty Publications

In the expansion of biomedical dataset, the same category may be labeled with different terms, thus being tedious and onerous to curate these terms. Therefore, automatically mapping synonymous terms onto the ontologies is desirable, which we name as biomedical synonym prediction task. Unlike biomedical concept normalization (BCN), no clues from context can be used to enhance synonym prediction, making it essential to extract graph features from ontology. We introduce an expert-curated dataset OBO-syn encompassing 70 different types of concepts and 2 million curated concept-term pairs for evaluating synonym prediction methods. We find BCN methods perform weakly on this task for …

Stability-Based Generalization Analysis For Mixtures Of Pointwise And Pairwise Learning, Jiahuan Wang, Jun Chen, Hong Chen, Bin Gu, Weifu Li, Xin Tang

Machine Learning Faculty Publications

Recently, some mixture algorithms of pointwise and pairwise learning (PPL) have been formulated by employing the hybrid error metric of “pointwise loss + pairwise loss” and have shown empirical effectiveness on feature selection, ranking and recommendation tasks. However, to the best of our knowledge, the learning theory foundation of PPL has not been touched in the existing works. In this paper, we try to fill this theoretical gap by investigating the generalization properties of PPL. After extending the definitions of algorithmic stability to the PPL setting, we establish the high-probability generalization bounds for uniformly stable PPL algorithms. Moreover, explicit convergence …

Class-Independent Regularization For Learning With Noisy Labels, Rumeng Yi, Dayan Guan, Yaping Huang, Shijian Lu

Computer Vision Faculty Publications

Training deep neural networks (DNNs) with noisy labels often leads to poorly generalized models as DNNs tend to memorize the noisy labels in training. Various strategies have been developed for improving sample selection precision and mitigating the noisy label memorization issue. However, most existing works adopt a class-dependent softmax classifier that is vulnerable to noisy labels by entangling the classification of multi-class features. This paper presents a class-independent regularization (CIR) method that can effectively alleviate the negative impact of noisy labels in DNN training. CIR regularizes the class-dependent softmax classifier by introducing multi-binary classifiers each of which takes care of …