Artificial Intelligence and Robotics 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 …

Cone: An Efficient Coarse-To-Fine Alignment Framework For Long Video Temporal Grounding, Zhijian Hou, Wanjun Zhong, Lei Ji, Difei Gao, Kun Yan, Wing-Kwong Chan, Chong-Wah Ngo, Mike Z. Shou, Nan. Duan

Research Collection School Of Computing and Information Systems

This paper tackles an emerging and challenging problem of long video temporal grounding (VTG) that localizes video moments related to a natural language (NL) query. Compared with short videos, long videos are also highly demanded but less explored, which brings new challenges in higher inference computation cost and weaker multi-modal alignment. To address these challenges, we propose CONE, an efficient COarse-to-fiNE alignment framework. CONE is a plug-and-play framework on top of existing VTG models to handle long videos through a sliding window mechanism. Specifically, CONE (1) introduces a query-guided window selection strategy to speed up inference, and (2) proposes a …

Fine-Grained Domain Adaptive Crowd Counting Via Point-Derived Segmentation, Yongtuo Liu, Dan Xu, Sucheng Ren, Hanjie Wu, Hongmin Cai, Shengfeng He

Research Collection School Of Computing and Information Systems

Due to domain shift, a large performance drop is usually observed when a trained crowd counting model is deployed in the wild. While existing domain-adaptive crowd counting methods achieve promising results, they typically regard each crowd image as a whole and reduce domain discrepancies in a holistic manner, thus limiting further improvement of domain adaptation performance. To this end, we propose to untangle domain-invariant crowd and domain-specific background from crowd images and design a fine-grained domain adaption method for crowd counting. Specifically, to disentangle crowd from background, we propose to learn crowd segmentation from point-level crowd counting annotations in a …

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 …

Generative Ai And Chatgpt Impact On Technostress Of Teachers, Xuenan Huo, Keng Siau

Research Collection School Of Computing and Information Systems

Generative AI, such as ChatGPT, is a disruptive technology with significant impacts on education. While it has the potential to transform the delivery and accessibility of education, it can also undermine educational effectiveness by facilitating academic honesty and creating technostress for educators. This study aims to (i) evaluate the extent to which Generative AI, such as ChatGPT, brings technostress to teachers and (ii) how Generative AI changes teachers' professional identities and the technostress that results from such changes. We hypothesize that techno-eustress and techno-distress are determined by three types of self-discrepancies concerning professional identity construction: actual-ought, actual-ideal, and ought-ideal discrepancies. …

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 …

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 …

3d Dental Biometrics: Transformer-Based Dental Arch Extraction And Matching, Zhiyuan Zhang, Zhong Xin

Research Collection School Of Computing and Information Systems

The dental arch is a significant anatomical feature that is crucial in assessing tooth arrangement and configuration and has a potential for human identification in biometrics and digital forensic dentistry. In a previous study, we proposed an auto pose-invariant arch feature extraction Radial Ray Algorithm (RRA) and a matching framework [1] based solely on 3D dental geometry. To enhance the identification accuracy and speed of our previous work, we propose in this study a transformer architecture that can extract dental keypoints by encoding both local and global features. The dental arch is then constructed through robust interpolation of the dental …

Strategic Planning For Flexible Agent Availability In Large Taxi Fleets, Rajiv Ranjan Kumar, Pradeep Varakantham, Shih-Fen Cheng

Research Collection School Of Computing and Information Systems

In large scale multi-agent systems like taxi fleets, individual agents (taxi drivers) are self interested (maximizing their own profits) and this can introduce inefficiencies in the system. One such inefficiency is with regards to the "required" availability of taxis at different time periods during the day. Since a taxi driver can work for limited number of hours in a day (e.g., 8-10 hours in a city like Singapore), there is a need to optimize the specific hours, so as to maximize individual as well as social welfare. Technically, this corresponds to solving a large scale multi-stage selfish routing game with …

Improving Quantal Cognitive Hierarchy Model Through Iterative Population Learning, Yuhong Xu, Shih-Fen Cheng, Xinyu Chen

Research Collection School Of Computing and Information Systems

In this paper, we propose to enhance the state-of-the-art quantal cognitive hierarchy (QCH) model with iterative population learning (IPL) to estimate the empirical distribution of agents’ reasoning levels and fit human agents’ behavioral data. We apply our approach to a real-world dataset from the Swedish lowest unique positive integer (LUPI) game and show that our proposed approach outperforms the theoretical Poisson Nash equilibrium predictions and the QCH approach by 49.8% and 46.6% in Wasserstein distance respectively. Our approach also allows us to explicitly measure an agent’s reasoning level distribution, which is not previously possible.

Preference-Aware Delivery Planning For Last-Mile Logistics, Qian Shao, Shih-Fen Cheng

Research Collection School Of Computing and Information Systems

Optimizing delivery routes for last-mile logistics service is challenging and has attracted the attention of many researchers. These problems are usually modeled and solved as variants of vehicle routing problems (VRPs) with challenging real-world constraints (e.g., time windows, precedence). However, despite many decades of solid research on solving these VRP instances, we still see significant gaps between optimized routes and the routes that are actually preferred by the practitioners. Most of these gaps are due to the difference between what's being optimized, and what the practitioners actually care about, which is hard to be defined exactly in many instances. In …

A Mixed-Integer Linear Programming Reduction Of Disjoint Bilinear Programs Via Symbolic Variable Elimination, Jihwan Jeong, Scott Sanner, Akshat Kumar

Research Collection School Of Computing and Information Systems

A disjointly constrained bilinear program (DBLP) has various practical and industrial applications, e.g., in game theory, facility location, supply chain management, and multi-agent planning problems. Although earlier work has noted the equivalence of DBLP and mixed-integer linear programming (MILP) from an abstract theoretical perspective, a practical and exact closed-form reduction of a DBLP to a MILP has remained elusive. Such explicit reduction would allow us to leverage modern MILP solvers and techniques along with their solution optimality and anytime approximation guarantees. To this end, we provide the first constructive closed-form MILP reduction of a DBLP by extending the technique of …

The Bemi Stardust: A Structured Ensemble Of Binarized Neural Networks, Ambrogio Maria Bernardelli, Stefano Gualandi, Hoong Chuin Lau, Simone Milanesi

Research Collection School Of Computing and Information Systems

Binarized Neural Networks (BNNs) are receiving increasing attention due to their lightweight architecture and ability to run on low-power devices, given the fact that they can be implemented using Boolean operations. The state-of-the-art for training classification BNNs restricted to few-shot learning is based on a Mixed Integer Programming (MIP) approach. This paper proposes the BeMi ensemble, a structured architecture of classification-designed BNNs based on training a single BNN for each possible pair of classes and applying a majority voting scheme to predict the final output. The training of a single BNN discriminating between two classes is achieved by a MIP …

Imitating Opponent To Win: Adversarial Policy Imitation Learning In Two-Player Competitive Games, The Viet Bui, Tien Mai, Thanh H. Nguyen

Research Collection School Of Computing and Information Systems

Recent research on vulnerabilities of deep reinforcement learning (RL) has shown that adversarial policies adopted by an adversary agent can influence a target RL agent (victim agent) to perform poorly in a multi-agent environment. In existing studies, adversarial policies are directly trained based on experiences of interacting with the victim agent. There is a key shortcoming of this approach --- knowledge derived from historical interactions may not be properly generalized to unexplored policy regions of the victim agent, making the trained adversarial policy significantly less effective. In this work, we design a new effective adversarial policy learning algorithm that overcomes …

Curricular Contrastive Regularization For Physics-Aware Single Image Dehazing, Yu Zheng, Jiahui Zhan, Shengfeng He, Yong Du

Research Collection School Of Computing and Information Systems

Considering the ill-posed nature, contrastive regularization has been developed for single image dehazing, introducing the information from negative images as a lower bound. However, the contrastive samples are non-consensual, as the negatives are usually represented distantly from the clear (i.e., positive) image, leaving the solution space still under-constricted. Moreover, the interpretability of deep dehazing models is underexplored towards the physics of the hazing process. In this paper, we propose a novel curricular contrastive regularization targeted at a consensual contrastive space as opposed to a non-consensual one. Our negatives, which provide better lower-bound constraints, can be assembled from 1) the hazy …

Where Is My Spot? Few-Shot Image Generation Via Latent Subspace Optimization, Chenxi Zheng, Bangzhen Liu, Huaidong Zhang, Xuemiao Xu, Shengfeng He

Research Collection School Of Computing and Information Systems

Image generation relies on massive training data that can hardly produce diverse images of an unseen category according to a few examples. In this paper, we address this dilemma by projecting sparse few-shot samples into a continuous latent space that can potentially generate infinite unseen samples. The rationale behind is that we aim to locate a centroid latent position in a conditional StyleGAN, where the corresponding output image on that centroid can maximize the similarity with the given samples. Although the given samples are unseen for the conditional StyleGAN, we assume the neighboring latent subspace around the centroid belongs to …

Tracing The Twenty-Year Evolution Of Developing Ai For Eye Screening In Singapore: A Master Chronology Of Sidrp, Selena+ And Eyris, Steven M. Miller

Research Collection School Of Computing and Information Systems

This working paper is entirely comprised of a timeline table that begins in 2002 and runs through mid-2023. Across these two decades, this timeline traces the evolutionary development of the following:

• The early Singapore R&D efforts to apply software-based image analysis algorithms and methods to analyse eye retina images for diabetic retinopathy and other eye diseases. This was based on a collaboration between the Singapore Eye Research Institute (SERI) and its parent organization, the Singapore National Eye Centre (SNEC), with faculty from the School of Computing at National University of Singapore.
• The establishment and operation of the Singapore Integrated Diabetic …