Open Access. Powered by Scholars. Published by Universities.®

Artificial Intelligence and Robotics Commons™

Open Access. Powered by Scholars. Published by Universities.®

Research Collection School Of Computing and Information Systems

Discipline
Keyword
Publication Year
File Type

Articles 901 - 930 of 1664

Full-Text Articles in Artificial Intelligence and Robotics

Imagining New Futures Beyond Predictive Systems In Child Welfare: A Qualitative Study With Impacted Stakeholders, Logan Stapleton, Min Hun Lee, Diana Qing, Marya Wright, Alexandra Chouldechova, Ken Holstein, Zhiwei Steven Wu, Haiyi Zhu Jun 2022

Imagining New Futures Beyond Predictive Systems In Child Welfare: A Qualitative Study With Impacted Stakeholders, Logan Stapleton, Min Hun Lee, Diana Qing, Marya Wright, Alexandra Chouldechova, Ken Holstein, Zhiwei Steven Wu, Haiyi Zhu

Research Collection School Of Computing and Information Systems

Child welfare agencies across the United States are turning to datadriven predictive technologies (commonly called predictive analytics) which use government administrative data to assist workers’ decision-making. While some prior work has explored impacted stakeholders’ concerns with current uses of data-driven predictive risk models (PRMs), less work has asked stakeholders whether such tools ought to be used in the first place. In this work, we conducted a set of seven design workshops with 35 stakeholders who have been impacted by the child welfare system or who work in it to understand their beliefs and concerns around PRMs, and to engage them …

Go to article

Cross-Lingual Adaptation For Recipe Retrieval With Mixup, Bin Zhu, Chong-Wah Ngo, Jingjing Chen, Wing-Kwong Chan Jun 2022

Cross-Lingual Adaptation For Recipe Retrieval With Mixup, Bin Zhu, Chong-Wah Ngo, Jingjing Chen, Wing-Kwong Chan

Research Collection School Of Computing and Information Systems

Cross-modal recipe retrieval has attracted research attention in recent years, thanks to the availability of large-scale paired data for training. Nevertheless, obtaining adequate recipe-image pairs covering the majority of cuisines for supervised learning is difficult if not impossible. By transferring knowledge learnt from a data-rich cuisine to a data-scarce cuisine, domain adaptation sheds light on this practical problem. Nevertheless, existing works assume recipes in source and target domains are mostly originated from the same cuisine and written in the same language. This paper studies unsupervised domain adaptation for image-to-recipe retrieval, where recipes in source and target domains are in different …

Go to article

Reinforcement Learning-Based Interactive Video Search, Zhixin Ma, Jiaxin Wu, Zhijian Hou, Chong-Wah Ngo Jun 2022

Reinforcement Learning-Based Interactive Video Search, Zhixin Ma, Jiaxin Wu, Zhijian Hou, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Despite the rapid progress in text-to-video search due to the advancement of cross-modal representation learning, the existing techniques still fall short in helping users to rapidly identify the search targets. Particularly, in the situation that a system suggests a long list of similar candidates, the user needs to painstakingly inspect every search result. The experience is frustrated with repeated watching of similar clips, and more frustratingly, the search targets may be overlooked due to mental tiredness. This paper explores reinforcement learning-based (RL) searching to relieve the user from the burden of brute force inspection. Specifically, the system maintains a graph …

Go to article

Group Contextualization For Video Recognition, Yanbin Hao, Hao Zhang, Chong-Wah Ngo, Xiangnan He Jun 2022

Group Contextualization For Video Recognition, Yanbin Hao, Hao Zhang, Chong-Wah Ngo, Xiangnan He

Research Collection School Of Computing and Information Systems

Learning discriminative representation from the complex spatio-temporal dynamic space is essential for video recognition. On top of those stylized spatio-temporal computational units, further refining the learnt feature with axial contexts is demonstrated to be promising in achieving this goal. However, previous works generally focus on utilizing a single kind of contexts to calibrate entire feature channels and could hardly apply to deal with diverse video activities. The problem can be tackled by using pair-wise spatio-temporal attentions to recompute feature response with cross-axis contexts at the expense of heavy computations. In this paper, we propose an efficient feature refinement method that …

Go to article

Mlp-3d: A Mlp-Like 3d Architecture With Grouped Time Mixing, Zhaofan Qiu, Ting Yao, Chong-Wah Ngo, Tao Mei Jun 2022

Mlp-3d: A Mlp-Like 3d Architecture With Grouped Time Mixing, Zhaofan Qiu, Ting Yao, Chong-Wah Ngo, Tao Mei

Research Collection School Of Computing and Information Systems

Convolutional Neural Networks (CNNs) have been re-garded as the go-to models for visual recognition. More re-cently, convolution-free networks, based on multi-head self-attention (MSA) or multi-layer perceptrons (MLPs), become more and more popular. Nevertheless, it is not trivial when utilizing these newly-minted networks for video recognition due to the large variations and complexities in video data. In this paper, we present MLP-3D networks, a novel MLP-like 3D architecture for video recognition. Specifically, the architecture consists of MLP-3D blocks, where each block contains one MLP applied across tokens (i.e., token-mixing MLP) and one MLP applied independently to each token (i.e., channel MLP). …

Go to article

Catching Both Gray And Black Swans: Open-Set Supervised Anomaly Detection, Choubo Ding, Guansong Pang, Chunhua Shen Jun 2022

Catching Both Gray And Black Swans: Open-Set Supervised Anomaly Detection, Choubo Ding, Guansong Pang, Chunhua Shen

Research Collection School Of Computing and Information Systems

Despite most existing anomaly detection studies assume the availability of normal training samples only, a few labeled anomaly examples are often available in many real-world applications, such as defect samples identified during random quality inspection, lesion images confirmed by radiologists in daily medical screening, etc. These anomaly examples provide valuable knowledge about the application-specific abnormality, enabling significantly improved detection of similar anomalies in some recent models. However, those anomalies seen during training often do not illustrate every possible class of anomaly, rendering these models ineffective in generalizing to unseen anomaly classes. This paper tackles open-set supervised anomaly detection, in which …

Go to article

Generative Flows With Invertible Attentions, Rhea Sanjay Sukthanker, Zhiwu Huang, Suryansh Kumar, Radu Timofte, Luc Van Gool Jun 2022

Generative Flows With Invertible Attentions, Rhea Sanjay Sukthanker, Zhiwu Huang, Suryansh Kumar, Radu Timofte, Luc Van Gool

Research Collection School Of Computing and Information Systems

Flow-based generative models have shown an excellent ability to explicitly learn the probability density function of data via a sequence of invertible transformations. Yet, learning attentions in generative flows remains understudied, while it has made breakthroughs in other domains. To fill the gap, this paper introduces two types of invertible attention mechanisms, i.e., map-based and transformer-based attentions, for both unconditional and conditional generative flows. The key idea is to exploit a masked scheme of these two attentions to learn long-range data dependencies in the context of generative flows. The masked scheme allows for invertible attention modules with tractable Jacobian determinants, …

Go to article

Officers: Operational Framework For Intelligent Crime-And-Emergency Response Scheduling, Jonathan David Chase, Siong Thye Goh, Tran Phong, Hoong Chuin Lau Jun 2022

Officers: Operational Framework For Intelligent Crime-And-Emergency Response Scheduling, Jonathan David Chase, Siong Thye Goh, Tran Phong, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

In the quest to achieve better response times in dense urban environments, law enforcement agencies are seeking AI-driven planning systems to inform their patrol strategies. In this paper, we present a framework, OFFICERS, for deployment planning that learns from historical data to generate deployment schedules on a daily basis. We accurately predict incidents using ST-ResNet, a deep learning technique that captures wide-ranging spatio-temporal dependencies, and solve a large-scale optimization problem to schedule deployment, significantly improving its scalability through a simulated annealing solver. Methodologically, our approach outperforms our previous works where prediction was done using Generative Adversarial Networks, and optimization was …

Go to article

Reinforcement Learning Approach To Solve Dynamic Bi-Objective Police Patrol Dispatching And Rescheduling Problem, Waldy Joe, Hoong Chuin Lau, Jonathan Pan Jun 2022

Reinforcement Learning Approach To Solve Dynamic Bi-Objective Police Patrol Dispatching And Rescheduling Problem, Waldy Joe, Hoong Chuin Lau, Jonathan Pan

Research Collection School Of Computing and Information Systems

Police patrol aims to fulfill two main objectives namely to project presence and to respond to incidents in a timely manner. Incidents happen dynamically and can disrupt the initially-planned patrol schedules. The key decisions to be made will be which patrol agent to be dispatched to respond to an incident and subsequently how to adapt the patrol schedules in response to such dynamically-occurring incidents whilst still fulfilling both objectives; which sometimes can be conflicting. In this paper, we define this real-world problem as a Dynamic Bi-Objective Police Patrol Dispatching and Rescheduling Problem and propose a solution approach that combines Deep …

Go to article

Do-Gan: A Double Oracle Framework For Generative Adversarial Networks, Aye Phyu Phye Aung, Xinrun Wang, Runsheng Yu, Bo An, Senthilnath Jayavelu, Xiaoli Li Jun 2022

Do-Gan: A Double Oracle Framework For Generative Adversarial Networks, Aye Phyu Phye Aung, Xinrun Wang, Runsheng Yu, Bo An, Senthilnath Jayavelu, Xiaoli Li

Research Collection School Of Computing and Information Systems

In this paper, we propose a new approach to train Gen-erative Adversarial Networks (GANs) where we deploy a double-oracle framework using the generator and discrim-inator oracles. GAN is essentially a two-player zero-sum game between the generator and the discriminator. Training GANs is challenging as a pure Nash equilibrium may not exist and even finding the mixed Nash equilibrium is difficult as GANs have a large-scale strategy space. In DO-GAN, we extend the double oracle framework to GANs. We first generalize the players' strategies as the trained models of generator and discriminator from the best response or-acles. We then compute the …

Go to article

Simultaneous Energy Harvesting And Gait Recognition Using Piezoelectric Energy Harvester, Dong Ma, Guohao Lan, Weitao Xu, Mahbub Hassan, Wen Hu Jun 2022

Simultaneous Energy Harvesting And Gait Recognition Using Piezoelectric Energy Harvester, Dong Ma, Guohao Lan, Weitao Xu, Mahbub Hassan, Wen Hu

Research Collection School Of Computing and Information Systems

Piezoelectric energy harvester, which generates electricity from stress or vibrations, is gaining increasing attention as a viable solution to extend battery life in wearables. Recent research further reveals that, besides generating energy, PEH can also serve as a passive sensor to detect human gait power-efficiently because its stress or vibration patterns are significantly influenced by the gait. However, as PEHs are not designed for precise measurement of motion, achievable gait recognition accuracy remains low with conventional classification algorithms. The accuracy deteriorates further when the generated electricity is stored simultaneously. To classify gait reliably while simultaneously storing generated energy, we make …

Go to article

Deep One-Class Classification Via Interpolated Gaussian Descriptor, Yuanhong Chen, Yu Tian, Guansong Pang, Gustavo Carneiro Jun 2022

Deep One-Class Classification Via Interpolated Gaussian Descriptor, Yuanhong Chen, Yu Tian, Guansong Pang, Gustavo Carneiro

Research Collection School Of Computing and Information Systems

One-class classification (OCC) aims to learn an effective data description to enclose all normal training samples and detect anomalies based on the deviation from the data description. Current state-of-the-art OCC models learn a compact normality description by hyper-sphere minimisation, but they often suffer from overfitting the training data, especially when the training set is small or contaminated with anomalous samples. To address this issue, we introduce the interpolated Gaussian descriptor (IGD) method, a novel OCC model that learns a one-class Gaussian anomaly classifier trained with adversarially interpolated training samples. The Gaussian anomaly classifier differentiates the training samples based on their …

Go to article

Indoor Localization Using Solar Cells, Hamada Rizk, Dong Ma, Mahbub Hassan, Moustafa Youssef May 2022

Indoor Localization Using Solar Cells, Hamada Rizk, Dong Ma, Mahbub Hassan, Moustafa Youssef

Research Collection School Of Computing and Information Systems

The development of the Internet of Things (IoT) opens the doors for innovative solutions in indoor positioning systems. Recently, light-based positioning has attracted much attention due to the dense and pervasive nature of light sources (e.g., Light-emitting Diode lighting) in indoor environments. Nevertheless, most existing solutions necessitate carrying a high-end phone at hand in a specific orientation to detect the light intensity with the phone's light sensing capability (i.e., light sensor or camera). This limits the ease of deployment of these solutions and leads to drainage of the phone battery. We propose PVDeepLoc, a device-free light-based indoor localization system that …

Go to article

Feasibility Studies In Indoor Localization Through Intelligent Conversation, Sheshadri Smitha, Linus Cheng, Kotaro Hara May 2022

Feasibility Studies In Indoor Localization Through Intelligent Conversation, Sheshadri Smitha, Linus Cheng, Kotaro Hara

Research Collection School Of Computing and Information Systems

We propose a model to achieve human localization in indoor environments through intelligent conversation between users and an agent. We investigated the feasibility of conversational localization by conducting two studies. First, we conducted a Wizard-of-Oz study with N = 7 participants and studied the feasibility of localizing users through conversation. We identified challenges posed by users’ language and behavior. Second, we collected N = 800 user descriptions of virtual indoor locations from N = 80 Amazon Mechanical Turk participants to analyze user language. We explored the effects of conversational agent behavior and observed that people describe indoor locations differently based …

Go to article

Exploring And Adapting Chinese Gpt To Pinyin Input Method, Minghuan Tan, Yong Dai, Duyu Tang, Zhangyin Feng, Guoping Huang, Jing Jiang, Jiwei Li, Shuming Shi May 2022

Exploring And Adapting Chinese Gpt To Pinyin Input Method, Minghuan Tan, Yong Dai, Duyu Tang, Zhangyin Feng, Guoping Huang, Jing Jiang, Jiwei Li, Shuming Shi

Research Collection School Of Computing and Information Systems

While GPT has become the de-facto method for text generation tasks, its application to pinyin input method remains unexplored. In this work, we make the first exploration to leverage Chinese GPT for pinyin input method. We find that a frozen GPT achieves state-of-the-art performance on perfect pinyin. However, the performance drops dramatically when the input includes abbreviated pinyin. A reason is that an abbreviated pinyin can be mapped to many perfect pinyin, which links to even larger number of Chinese characters. We mitigate this issue with two strategies, including enriching the context with pinyin and optimizing the training process to …

Go to article

Benchmarking Library Recognition In Tweets, Ting Zhang, Divya Prabha Chandrasekaran, Ferdian Thung, David Lo May 2022

Benchmarking Library Recognition In Tweets, Ting Zhang, Divya Prabha Chandrasekaran, Ferdian Thung, David Lo

Research Collection School Of Computing and Information Systems

Software developers often use social media (such as Twitter) to shareprogramming knowledge such as new tools, sample code snippets,and tips on programming. One of the topics they talk about is thesoftware library. The tweets may contain useful information abouta library. A good understanding of this information, e.g., on thedeveloper’s views regarding a library can be beneficial to weigh thepros and cons of using the library as well as the general sentimentstowards the library. However, it is not trivial to recognize whethera word actually refers to a library or other meanings. For example,a tweet mentioning the word “pandas" may refer to …

Go to article

Exais: Executable Ai Semantics, Richard Schumi, Jun Sun May 2022

Exais: Executable Ai Semantics, Richard Schumi, Jun Sun

Research Collection School Of Computing and Information Systems

Neural networks can be regarded as a new programming paradigm, i.e., instead of building ever-more complex programs through (often informal) logical reasoning in the programmers' mind, complex 'AI' systems are built by optimising generic neural network models with big data. In this new paradigm, AI frameworks such as TensorFlow and PyTorch play a key role, which is as essential as the compiler for traditional programs. It is known that the lack of a proper semantics for programming languages (such as C), i.e., a correctness specification for compilers, has contributed to many problematic program behaviours and security issues. While it is …

Go to article

Tatl: Task Agnostic Transfer Learning For Skin Attributes Detection, Duy M.H. Nguyen, Thu T. Nguyen, Huong Vu, Hong Quang Pham, Manh-Duy Nguyen, Binh T. Nguyen, Daniel Sonntag May 2022

Tatl: Task Agnostic Transfer Learning For Skin Attributes Detection, Duy M.H. Nguyen, Thu T. Nguyen, Huong Vu, Hong Quang Pham, Manh-Duy Nguyen, Binh T. Nguyen, Daniel Sonntag

Research Collection School Of Computing and Information Systems

Existing skin attributes detection methods usually initialize with a pre-trained Imagenet network and then fine-tune on a medical target task. However, we argue that such approaches are suboptimal because medical datasets are largely different from ImageNet and often contain limited training samples. In this work, we propose Task Agnostic Transfer Learning (TATL), a novel framework motivated by dermatologists’ behaviors in the skincare context. TATL learns an attribute-agnostic segmenter that detects lesion skin regions and then transfers this knowledge to a set of attribute-specific classifiers to detect each particular attribute. Since TATL’s attribute-agnostic segmenter only detects skin attribute regions, it enjoys …

Go to article

Neighborhood Cooperative Multiagent Reinforcement Learning For Adaptive Traffic Signal Control In Epidemic Regions, Chengwei Zhang, Yu Tian, Zhibin Zhang, Wanli Xue, Xiaofei Xie, Tianpei Yang, Xin Ge, Rong Chen May 2022

Neighborhood Cooperative Multiagent Reinforcement Learning For Adaptive Traffic Signal Control In Epidemic Regions, Chengwei Zhang, Yu Tian, Zhibin Zhang, Wanli Xue, Xiaofei Xie, Tianpei Yang, Xin Ge, Rong Chen

Research Collection School Of Computing and Information Systems

Nowadays, multiagent reinforcement learning (MARL) have shared significant advances in the adaptive traffic signal control (ATSC) problems. For most of the researches, agents are all isomorphic, which disregards the situation in which isomerous intersections cooperative together in a real ATSC scenario, especially in epidemic regions where different intersections have quite different levels of importance. To this end, this paper models the ATSC problem as a networked Markov game (NMG), in which agents take into account information, including traffic conditions of it and its connected neighbors. A cooperative MARL framework named neighborhood cooperative hysteretic DQN (NC-HDQN) is proposed. Specifically, for each …

Go to article

Software Engineering User Study Recruitment On Prolific: An Experience Report, Brittany Reid, Markus Wagner, Marcelo D’Amorim, Christoph Treude May 2022

Software Engineering User Study Recruitment On Prolific: An Experience Report, Brittany Reid, Markus Wagner, Marcelo D’Amorim, Christoph Treude

Research Collection School Of Computing and Information Systems

Online participant recruitment platforms such as Prolific have been gaining popularity in research, as they enable researchers to easily access large pools of participants. However, participant quality can be an issue; participants may give incorrect information to gain access to more studies, adding unwanted noise to results. This paper details our experience recruiting participants from Prolific for a user study requiring programming skills in Node.js, with the aim of helping other researchers conduct similar studies. We explore a method of recruiting programmer participants using prescreening validation, attention checks and a series of programming knowledge questions. We received 680 responses, and …

Go to article

Diffusion Of Ai Governance, Langtao Chen, Brenda Eschenbrenner, Fiona Fui-Hoon Nah, Keng Siau, Yuzhou Qian May 2022

Diffusion Of Ai Governance, Langtao Chen, Brenda Eschenbrenner, Fiona Fui-Hoon Nah, Keng Siau, Yuzhou Qian

Research Collection School Of Computing and Information Systems

Artificial intelligence (AI) has the potential to address social, economic, and environmental challenges. However, effective use of AI in organizations relies on the establishment of an AI governance framework. Although existing studies have discussed a variety of issues raised by AI-based systems and proposed AI governance frameworks to overcome those issues, organizations face challenges in adopting AI governance. Informed by innovation diffusion theory, this research evaluates the impact of internal and external influences on AI governance adoption between highly regulated and less regulated industries. We also assess the effect of adopting AI governance on organizational performance. Findings from this study …

Go to article

Hierarchical Value Decomposition For Effective On-Demand Ride Pooling, Hao Jiang, Pradeep Varakantham May 2022

Hierarchical Value Decomposition For Effective On-Demand Ride Pooling, Hao Jiang, Pradeep Varakantham

Research Collection School Of Computing and Information Systems

On-demand ride-pooling (e.g., UberPool, GrabShare) services focus on serving multiple different customer requests using each vehicle, i.e., an empty or partially filled vehicle can be assigned requests from different passengers with different origins and destinations. On the other hand, in Taxi on Demand (ToD) services (e.g., UberX), one vehicle is assigned to only one request at a time. On-demand ride pooling is not only beneficial to customers (lower cost), drivers (higher revenue per trip) and aggregation companies (higher revenue), but is also of crucial importance to the environment as it reduces the number of vehicles required on the roads. Since …

Go to article

Improving Feature Generalizability With Multitask Learning In Class Incremental Learning, Dong Ma, Chi Ian Tang, Cecilia Mascolo Apr 2022

Improving Feature Generalizability With Multitask Learning In Class Incremental Learning, Dong Ma, Chi Ian Tang, Cecilia Mascolo

Research Collection School Of Computing and Information Systems

Many deep learning applications, like keyword spotting [1], [2], require the incorporation of new concepts (classes) over time, referred to as Class Incremental Learning (CIL). The major challenge in CIL is catastrophic forgetting, i.e., preserving as much of the old knowledge as possible while learning new tasks. Various techniques, such as regularization, knowledge distillation, and the use of exemplars, have been proposed to resolve this issue. However, prior works primarily focus on the incremental learning step, while ignoring the optimization during the base model training. We hypothesise that a more transferable and generalizable feature representation from the base model would …

Go to article

Asteroids: Exploring Swarms Of Mini-Telepresence Robots For Physical Skill Demonstration, Jiannan Li, Maurício Sousa, Chu Li, Jessie Liu, Yan Chen, Ravin Balakrishnan, Tovi Grossman Apr 2022

Asteroids: Exploring Swarms Of Mini-Telepresence Robots For Physical Skill Demonstration, Jiannan Li, Maurício Sousa, Chu Li, Jessie Liu, Yan Chen, Ravin Balakrishnan, Tovi Grossman

Research Collection School Of Computing and Information Systems

Online synchronous tutoring allows for immediate engagement between instructors and audiences over distance. However, tutoring physical skills remains challenging because current telepresence approaches may not allow for adequate spatial awareness, viewpoint control of the demonstration activities scattered across an entire work area, and the instructor’s sufficient awareness of the audience. We present Asteroids, a novel approach for tangible robotic telepresence, to enable workbench-scale physical embodiments of remote people and tangible interactions by the instructor. With Asteroids, the audience can actively control a swarm of mini-telepresence robots, change camera positions, and switch to other robots’ viewpoints. Demonstrators can perceive the audiences’ …

Go to article

Sibnet: Food Instance Counting And Segmentation, Huu-Thanh. Nguyen, Chong-Wah Ngo, Wing-Kwong Chan Apr 2022

Sibnet: Food Instance Counting And Segmentation, Huu-Thanh. Nguyen, Chong-Wah Ngo, Wing-Kwong Chan

Research Collection School Of Computing and Information Systems

Food computing has recently attracted considerable research attention due to its significance for health risk analysis. In the literature, the majority of research efforts are dedicated to food recognition. Relatively few works are conducted for food counting and segmentation, which are essential for portion size estimation. This paper presents a deep neural network, named SibNet, for simultaneous counting and extraction of food instances from an image. The problem is challenging due to varying size and shape of food as well as arbitrary viewing angle of camera, not to mention that food instances often occlude each other. SibNet is novel for …

Go to article

Algorithm Selection For The Team Orienteering Problem, Mustafa Misir, Aldy Gunawan, Pieter Vansteenwegen Apr 2022

Algorithm Selection For The Team Orienteering Problem, Mustafa Misir, Aldy Gunawan, Pieter Vansteenwegen

Research Collection School Of Computing and Information Systems

This work utilizes Algorithm Selection for solving the Team Orienteering Problem (TOP). The TOP is an NP-hard combinatorial optimization problem in the routing domain. This problem has been modelled with various extensions to address different real-world problems like tourist trip planning. The complexity of the problem motivated to devise new algorithms. However, none of the existing algorithms came with the best performance across all the widely used benchmark instances. This fact suggests that there is a performance gap to fill. This gap can be targeted by developing more new algorithms as attempted by many researchers before. An alternative strategy is …

Go to article

Comai: Enabling Lightweight, Collaborative Intelligence By Retrofitting Vision Dnns, Kasthuri Jayarajah, Dhanuja Wanniarachchige, Tarek Abdelzaher, Archan Misra Apr 2022

Comai: Enabling Lightweight, Collaborative Intelligence By Retrofitting Vision Dnns, Kasthuri Jayarajah, Dhanuja Wanniarachchige, Tarek Abdelzaher, Archan Misra

Research Collection School Of Computing and Information Systems

While Deep Neural Network (DNN) models have transformed machine vision capabilities, their extremely high computational complexity and model sizes present a formidable deployment roadblock for AIoT applications. We show that the complexity-vs-accuracy-vs-communication tradeoffs for such DNN models can be significantly addressed via a novel, lightweight form of “collaborative machine intelligence” that requires only runtime changes to the inference process. In our proposed approach, called ComAI, the DNN pipelines of different vision sensors share intermediate processing state with one another, effectively providing hints about objects located within their mutually-overlapping Field-of-Views (FoVs). CoMAI uses two novel techniques: (a) a secondary shallow ML …

Go to article

Metaheuristics For Time-Dependent Vehicle Routing Problem With Time Windows, Yun-C Liang, Vanny Minanda, Aldy Gunawan, Hsiang-L. Chen Apr 2022

Metaheuristics For Time-Dependent Vehicle Routing Problem With Time Windows, Yun-C Liang, Vanny Minanda, Aldy Gunawan, Hsiang-L. Chen

Research Collection School Of Computing and Information Systems

Vehicle routing problem (VRP), a combinatorial problem, deals with the vehicle’s capacity visiting a particular set of nodes while its variants attempt to fit real-world scenarios. Our study aims to minimise total travelling time, total distance, and the number of vehicles under time-dependent and time windows constraints (TDVRPTW). The harmony search algorithm (HSA) focuses on the harmony memory and pitch adjustment mechanism for new solution construction. Several local search operators and a roulette wheel for the performance improvement were verified via 56 Solomon’s VRP instances by adding a speed matrix. The performance comparison with a genetic algorithm (GA) was completed …

Go to article

Meta-Transfer Learning Through Hard Tasks, Qianru Sun, Yaoyao Liu, Zhaozheng Chen, Chua Tat-Seng, Schiele Bernt Mar 2022

Meta-Transfer Learning Through Hard Tasks, Qianru Sun, Yaoyao Liu, Zhaozheng Chen, Chua Tat-Seng, Schiele Bernt

Research Collection School Of Computing and Information Systems

Meta-learning has been proposed as a framework to address the challenging few-shot learning setting. The key idea is to leverage a large number of similar few-shot tasks in order to learn how to adapt a base-learner to a new task for which only a few labeled samples are available. As deep neural networks (DNNs) tend to overfit using a few samples only, typical meta-learning models use shallow neural networks, thus limiting its effectiveness. In order to achieve top performance, some recent works tried to use the DNNs pre-trained on large-scale datasets but mostly in straight-forward manners, e.g., (1) taking their …

Go to article

Learning Variable Ordering Heuristics For Solving Constraint Satisfaction Problems, Wen Song, Zhiguang Cao, Jie Zhang, Chi Xu, Andrew Lim Mar 2022

Learning Variable Ordering Heuristics For Solving Constraint Satisfaction Problems, Wen Song, Zhiguang Cao, Jie Zhang, Chi Xu, Andrew Lim

Research Collection School Of Computing and Information Systems

Backtracking search algorithms are often used to solve the Constraint Satisfaction Problem (CSP), which is widely applied in various domains such as automated planning and scheduling. The efficiency of backtracking search depends greatly on the variable ordering heuristics. Currently, the most commonly used heuristics are hand-crafted based on expert knowledge. In this paper, we propose a deep reinforcement learning based approach to automatically discover new variable ordering heuristics that are better adapted for a given class of CSP instances, without the need of relying on hand-crafted features and heuristics. We show that directly optimizing the search tree size is not …

Go to article

First Prev Next Last