Reward Penalties On Augmented States For Solving Richly Constrained Rl Effectively,
2024
Singapore Management University
Reward Penalties On Augmented States For Solving Richly Constrained Rl Effectively, Jiang Hao, Tien Mai, Pradeep Varakanthan, Minh Huy Hoang
Research Collection School Of Computing and Information Systems
Constrained Reinforcement Learning employs trajectory-based cost constraints (such as expected cost, Value at Risk, or Conditional VaR cost) to compute safe policies. The challenge lies in handling these constraints effectively while optimizing expected reward. Existing methods convert such trajectory-based constraints into local cost constraints, but they rely on cost estimates, leading to either aggressive or conservative solutions with regards to cost. We propose an unconstrained formulation that employs reward penalties over states augmented with costs to compute safe policies. Unlike standard primal-dual methods, our approach penalizes only infeasible trajectories through state augmentation. This ensures that increasing the penalty parameter always …
Leveraging Multimodal Features And Item‑Level User Feedback For Bundle Construction,
2024
Singapore Management University
Leveraging Multimodal Features And Item‑Level User Feedback For Bundle Construction, Yunshan Ma, Xiaohao Liu, Yinwei Wei, Zhulin Tao, Xiang Wang, Tat‑Seng Chua
Research Collection School Of Computing and Information Systems
Automatic bundle construction is a crucial prerequisite step in various bundle-aware online services. Previous approaches are mostly designed to model the bundling strategy of existing bundles. However, it is hard to acquire large-scale well-curated bundle dataset, especially for those platforms that have not offered bundle services before. Even for platforms with mature bundle services, there are still many items that are included in few or even zero bundles, which give rise to sparsity and cold-start challenges in the bundle construction models. To tackle these issues, we target at leveraging multimodal features, item-level user feedback signals, and the bundle composition information, …
Generative Ai In Finance: Risks And Potential Solutions,
2024
Singapore Management University
Generative Ai In Finance: Risks And Potential Solutions, Nydia Remolina Leon
Research Collection Yong Pung How School Of Law
Generative Artificial Intelligence captured the attention of academics, policymakers, the private sector, and some regulators in 2022 after the launch of ChatGPT and its widespread adoption worldwide. Then, during the World Economic Forum session in 2023, Microsoft Chairman and Chief Executive Officer Satya Nadella said that the ‘golden age’ of AI is underway and generative AI is set to play a big role in it. Accordingly, Microsoft has invested billions of dollars into OpenAI, the company behind the launch of ChatGPT. Additionally, Google and Meta have also created their own generative AI models. Given the multiplicity of potential use cases …
Math Word Problem Generation Via Disentangled Memory Retrieval,
2024
Singapore Management University
Math Word Problem Generation Via Disentangled Memory Retrieval, Wei Qin, Xiaowei Wang, Zhenzhen Hu, Lei Wang, Yunshi Lan, Richang Hong
Research Collection Lee Kong Chian School Of Business
The task of math word problem (MWP) generation, which generates an MWP given an equation and relevant topic words, has increasingly attracted researchers’ attention. In this work, we introduce a simple memory retrieval module to search related training MWPs, which are used to augment the generation. To retrieve more relevant training data, we also propose a disentangled memory retrieval module based on the simple memory retrieval module. To this end, we first disentangle the training MWPs into logical description and scenario description and then record them in respective memory modules. Later, we use the given equation and topic words as …
Path-Bigbird: An Ai-Driven Transformer Approach To Classification Of Cancer Pathology Reports,
2024
Oak Ridge National Laboratory
Path-Bigbird: An Ai-Driven Transformer Approach To Classification Of Cancer Pathology Reports, Mayanka Chandrashekar, Isaac Lyngaas, Heidi A. Hanson, Shang Gao, Xiao Cheng Wu, John Gounley
School of Public Health Faculty Publications
PURPOSE: Surgical pathology reports are critical for cancer diagnosis and management. To accurately extract information about tumor characteristics from pathology reports in near real time, we explore the impact of using domain-specific transformer models that understand cancer pathology reports. METHODS: We built a pathology transformer model, Path-BigBird, by using 2.7 million pathology reports from six SEER cancer registries. We then compare different variations of Path-BigBird with two less computationally intensive methods: Hierarchical Self-Attention Network (HiSAN) classification model and an off-the-shelf clinical transformer model (Clinical BigBird). We use five pathology information extraction tasks for evaluation: site, subsite, laterality, histology, and behavior. …
Brain-Inspired Continual Learning: Robust Feature Distillation And Re-Consolidation For Class Incremental Learning,
2024
Rowan University
Brain-Inspired Continual Learning: Robust Feature Distillation And Re-Consolidation For Class Incremental Learning, Hikmat Khan, Nidhal Carla Bouaynaya, Ghulam Rasool
Henry M. Rowan College of Engineering Departmental Research
Artificial intelligence and neuroscience have a long and intertwined history. Advancements in neuroscience research have significantly influenced the development of artificial intelligence systems that have the potential to retain knowledge akin to humans. Building upon foundational insights from neuroscience and existing research in adversarial and continual learning fields, we introduce a novel framework that comprises two key concepts: feature distillation and re-consolidation. The framework distills continual learning (CL) robust features and rehearses them while learning the next task, aiming to replicate the mammalian brain's process of consolidating memories through rehearsing the distilled version of the waking experiences. Furthermore, the proposed …
Comprehensive Survey On Applications Of Internet Of Things, Machine Learning And Artificial Intelligence In Precision Agriculture,
2024
University of Malawi
Comprehensive Survey On Applications Of Internet Of Things, Machine Learning And Artificial Intelligence In Precision Agriculture, Paul Stone Stone Brown Macheso S.B.
Tanzania Journal of Engineering and Technology (TJET)
A comprehensive, multidisciplinary analysis of the latest developments in digital agriculture is conducted with the use of artificial intelligence (AI), machine learning (ML), and the Internet of Things. By automation and the use of modern, scalable technology solutions that reduce risks, support sustainability, and give farmers predictive advice, traditional agricultural processes are being updated and improved to maximize production. In this paper, the applications of AI, IoT, and ML in agricultural production systems are discussed in detail. The applications that have been explored can be broadly categorized into three areas: soil management, livestock management, and crop management. Weed detection, disease …
Generative Mechanisms Of Ai Implementation: A Critical Realist Perspective On Predictive Maintenance,
2024
Branch Business & Information Systems Engineering of the Fraunhofer FIT, Augsburg, Germany
Generative Mechanisms Of Ai Implementation: A Critical Realist Perspective On Predictive Maintenance, Alexander Stohr, Philip Ollig, Robert Keller, Alexander Rieger
Information Systems Faculty Publications and Presentations
Artificial intelligence (AI) promises various new opportunities to create and appropriate business value. However, many organizations – especially those in more traditional industries – struggle to seize these opportunities. To unpack the underlying reasons, we investigate how more traditional industries implement predictive maintenance, a promising application of AI in manufacturing organizations. For our analysis, we employ a multiple-case design and adopt a critical realist perspective to identify generative mechanisms of AI implementation. Overall, we find five interdependent mechanisms: experimentation; knowledge building and integration; data; anxiety; and inspiration. Using causal loop diagramming, we flesh out the socio-technical dynamics of these mechanisms …
A New Scientific Research Paradigm Driven By Ai And Its Applications In Academic Disciplines,
2024
Institutes of Science and Development, Chinese Academy of Sciences, Beijing 100190, China; School of Public Policy and Management, University of Chinese Academy of Sciences, Beijing 100049, China
A New Scientific Research Paradigm Driven By Ai And Its Applications In Academic Disciplines, Jiang Yu, Yue Zhang, Yi Zhou
Bulletin of Chinese Academy of Sciences (Chinese Version)
The artificial intelligence (AI) -driven paradigm of scientific research, deeply embedded through the integration of data, computing power, and algorithms, has triggered profound changes in the research process, thinking logic, and organizational patterns. This study systematically summarizes the main characteristics and forms of the AI-driven new scientific research paradigm. It proposes that the evolution of the AI-driven research paradigm is shifting from “automated research” to “model-based research” and “intelligent research.” The depth and scope of AI applications in scientific research continue to expand, and this will drive significant changes in research organization and governance models. In addition, this study discusses …
Data And Intelligent Driven Space Science Experimental Research: New Exploration Under Ai4s Paradigm,
2024
Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences, Beijing 100094, China; Key Laboratory of Space Utilization, Chinese Academy of Sciences, Beijing 100094, China; School of Aeronautics and Astronautics, University of Chinese Academy of Sciences, Beijing 100049, China
Data And Intelligent Driven Space Science Experimental Research: New Exploration Under Ai4s Paradigm, Shengyang Li, Kang Liu, Yunfei Liu, Chufan Lai
Bulletin of Chinese Academy of Sciences (Chinese Version)
As artificial intelligence (AI) technology continues to advance, it is revolutionizing various scientific fields, giving rise to a new research paradigm known as AI for Science (AI4S). This study highlights the unique multidisciplinary advantages of AI in space science experiments conducted under microgravity conditions. It provides a comprehensive analysis of AI-driven approaches to multimodal space science experiment data pattern mining, domain knowledge extraction, interdisciplinary knowledge integration, and cognitive intelligence. The study reveals AI’s substantial potential to enhance intelligent scientific research, cognition, and discovery within the realm of space science experiments. The findings suggest that data-driven space science research, as a …
Path And Strategy Of Pollution And Carbon Reduction By Digitization In Electric Power Enterprises,
2024
School of Advanced Interdisciplinary Studies, Hunan University of Technology and Business, Changsha 410205, China
Business School, Central South University, Changsha 410083, China
Path And Strategy Of Pollution And Carbon Reduction By Digitization In Electric Power Enterprises, Xiaohong Chen, Runcheng Tang, Dongbin Hu, Xuesong Xu, Xiangbo Tang, Guodong Yi, Weiwei Zhang
Bulletin of Chinese Academy of Sciences (Chinese Version)
With the extensive application and innovation of digital technology in the energy sector, digital technology has become increasingly crucial for the power industry to achieve the goal of reducing pollution and carbon emissions. How digital technology enables electric power enterprises to achieve this goal has attracted much attention. Firstly, the study analyzes the progress of digital technology applications in pollution reduction and carbon reduction in electric power enterprises. Then, it identifies the existing problems in the current application of digital technology in the power industry for reducing pollution and carbon emissions. Finally, it explores the potential ways and approaches of …
Analysis And Recommendations For Energy Conservation And Carbon Emission Reduction In Industry Boosted By Digital Energy Management Systems,
2024
Institute for Manufacturing, Department of Engineering, University of Cambridge, Cambridge CB3 0FS, UK
Analysis And Recommendations For Energy Conservation And Carbon Emission Reduction In Industry Boosted By Digital Energy Management Systems, Duanyang Geng, Tong Xu, Qinghua Zhu, Steve Evans
Bulletin of Chinese Academy of Sciences (Chinese Version)
Energy consumption during production processes in the industry is a main source of carbon dioxide emissions. Therefore, for China’s dual-carbon goals, industrial enterprises need to focus on reducing energy waste to achieve energy-efficient production, thereby effectively reducing carbon emissions in industrial production. In recent years, with the continuous development and popularization of digital technology, digital energy management systems have played a crucial role in energy saving by visualizing invisible energy in the industry. In this context, this study first analyses the current status of digital energy management system applications in the UK, the US, Germany, and Sweden, summarizes their characteristics …
Development Path And Policy Guarantee Of China's Advanced Manufacturing Industry Under Background Of Fourth Industrial Revolution,
2024
Business School, Central South University, Changsha 410083, China
Development Path And Policy Guarantee Of China's Advanced Manufacturing Industry Under Background Of Fourth Industrial Revolution, Chang Wang, Siyuan Zhou, Hongjun Geng
Bulletin of Chinese Academy of Sciences (Chinese Version)
How to seize the opportunity window opened by the fourth industrial revolution and enhance the international competitive advantage of advanced manufacturing has become an important issue concerned by existing research and policy practitioners. This study analyzes the background, characteristics, and influence of the fourth industrial revolution on the development of advanced manufacturing industry. Based on this, it discusses the development status and problems of four types of advanced manufacturing industries, including digitally empowered new infrastructure industries, intelligent manufacturing high-end equipment industries, brand-oriented new consumption industries, and science-based industries. The development paths of “fusion innovation”, “intelligent manufacturing upgrade”, “quality improvement”, and …
Thoughts On Transformation Of Scientific And Technological Achievements In Field Of Information Technology,
2024
Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China
Thoughts On Transformation Of Scientific And Technological Achievements In Field Of Information Technology, Ninghui Sun, Xiaojuan Li
Bulletin of Chinese Academy of Sciences (Chinese Version)
To promote the transformation of scientific and technological achievements is one of the key points of China’s national science and technology innovation policy. Nevertheless, due to the particularity, complexity, and professionalism of technological achievements, being difficult to transform scientific and technological achievements is a worldwide common problem. There are many issues worth discussing and exploring in China’s transformation of scientific and technological achievements, especially when it comes to whether research institutes can transform their achievements by establishing enterprises, the answers remain controversial. The authors intend to take the field of information technology as an example, by analyzing the advantages, disadvantages, …
Key Elements, Mechanism Analysis And Evaluation Indicators Of Digital And Intelligent Integration Transformation And Development Of Manufacturing Industry,
2024
College of Economics and Management, Qingdao University of Science and Technology, Qingdao 266061, China
Key Elements, Mechanism Analysis And Evaluation Indicators Of Digital And Intelligent Integration Transformation And Development Of Manufacturing Industry, Xiaoqiang Sun, Xiuyun Gao, Yumei Wang
Bulletin of Chinese Academy of Sciences (Chinese Version)
The digital and intelligent integration transformation of manufacturing industry has become an important driving force for the high-quality development of traditional manufacturing enterprises. This study clarifies the main research context and key issues of scholars on the digital and intelligent integration transformation of manufacturing industry, refines the goals, main elements, and influencing factors of digital and intelligent integration transformation of manufacturing industry, builds a power network model for the transformation and development of digital and intelligent integration of manufacturing industry according to the system feedback principle of system dynamics, analyzes the mechanism of action between various elements of the system, …
Cancergpt For Few Shot Drug Pair Synergy Prediction Using Large Pretrained Language Models,
2024
The Texas Medical Center Library
Cancergpt For Few Shot Drug Pair Synergy Prediction Using Large Pretrained Language Models, Tianhao Li, Sandesh Shetty, Advaith Kamath, Ajay Jaiswal, Xiaoqian Jiang, Ying Ding, Yejin Kim
Faculty, Staff and Student Publications
Large language models (LLMs) have been shown to have significant potential in few-shot learning across various fields, even with minimal training data. However, their ability to generalize to unseen tasks in more complex fields, such as biology and medicine has yet to be fully evaluated. LLMs can offer a promising alternative approach for biological inference, particularly in cases where structured data and sample size are limited, by extracting prior knowledge from text corpora. Here we report our proposed few-shot learning approach, which uses LLMs to predict the synergy of drug pairs in rare tissues that lack structured data and features. …
Efficiency Optimization Method For Data Sampling In Power Grid Topology Scheduling Simulation,
2024
State Grid Shanghai Electrical Power Research Institute, Shanghai 200437, China; State Grid Shanghai Municipal Electric Power Company, Shanghai 200125, China
Efficiency Optimization Method For Data Sampling In Power Grid Topology Scheduling Simulation, Yingying Zhao, Pusen Dong, Tianchen Zhu, Fan Li, Yun Su, Zhenying Tai, Qingyun Sun, Hang Fan
Journal of System Simulation
Abstract: To address the large simulation computational workload and low simulation speed caused by the scale and complexity of the new power system, a simulation acceleration method for topology scheduling based on the distributed and quantization mechanisms is proposed. The parallelization of topology scheduling models is used to increase the scale of data simulation sampling in unit time. The introduced quantization operators accelerate the computation speed of the topology scheduling model operators, reduces the time cost of the every single simulation. Case studies confirm the effectiveness of the topology simulation acceleration, in which the available transfer capacity of the simulated …
Runoff Intelligent Prediction Method Based On Broad-Deep Fusion Time-Frequency Analysis,
2024
School of Automation, Nanjing University of Information Science & Technology, Nanjing 210044, China; Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology, Nanjing University of Information Science & Technology, Nanjing 210044, China
Runoff Intelligent Prediction Method Based On Broad-Deep Fusion Time-Frequency Analysis, Ying Han, Lehao Wang, Shumei Wang, Xiang Zhang, Xingxing Luo
Journal of System Simulation
Abstract: Broad learning system(BLS) is introduced to tackle the existed disadvantage that LSTM-based runoff prediction model is easy to fall into local optimization. To reduce the influence of noise on the prediction results, the variational mode decomposition (VMD) is adopted to transform the onedimensional time-domain runoff signal to the two-dimensional time-frequency plane. The runoff prediction model based on VMD-LSTM-BLS is proposed. The simulation results demonstrate that the prediction accuracy of the new model is more significantly improved compared with the baseline model and the existing LSTM-based runoff prediction model.
Simulation Platform Of Agv System Scheduling Algorithms In Uncertain Environment,
2024
Sino-US Global Logistics Institute, Antai College of Economics and Management, Shanghai Jiao Tong University, Shanghai 200030, China
Simulation Platform Of Agv System Scheduling Algorithms In Uncertain Environment, Zhihao Shi, Haihui Shen
Journal of System Simulation
Abstract: As a complete automated guided vehicle(AGV) system scheduling algorithm, it must include conflict-handling strategy, together with common dispatching strategy and routing algorithm. However, due to the uncertainty, characteristics of such scheduling algorithm are difficult to be analyzed theoretically, and the relevant study is lacking. An AGV system simulation platform based on the discreteevent simulation technique is designed and developed, which can flexibly set the scheduling problem, choose the dispatching strategy, routing algorithm, and conflict-handling strategy for the scheduling algorithm, to run the simulation. The platform has a visual interface, from which the running status of AGVs and the performance …
Research On Motion Planning Of Hexapod Robot Based On Drl And Free Gait,
2024
School of Manufacturing Science and Engineering, Southwest University of Science and Technology, Mianyang 621010, China; Manufacturing Process Testing Technology Key Laboratory of the Ministry of Education, Mianyang 621000, China
Research On Motion Planning Of Hexapod Robot Based On Drl And Free Gait, Xinpeng Wang, Huiqiao Fu, Guizhou Deng, Kaiqiang Tang, Chunlin Chen, Canghao Liu
Journal of System Simulation
Abstract: To improve the passability and the motion performance of the hexapod robot in the unstructured environment, a multi-contact motion planning algorithm based on DRL and free gait planner is proposed. Firstly, the free gait planner obtains the reachable footholds under the target state and outputs the optimal gait sequence. The center of mass motion policy of the hexapod robot in the randomly generated plum blossom pile environment is obtained by using deep reinforcement learning training. To ensure the reachability between adjacent states of the robot in motion, the state transition feasibility model is used to judge the state transition …
