检索结果-内蒙古大学图书馆

Python package for causal discovery based on LiNGAM

学校读者我要写书评

暂无评论

Journal of Machine Learning Research 2023年第1期24卷 1-8页

作者： Ikeuchi, Takashi Ide, Mayumi Zeng, Yan Maeda, Takashi Nicholas Shimizu, Shohei SCREEN Advanced System Solutions Co. Ltd. Japan Department of Computer Science and Technology Tsinghua University China School of System Design and Technology Tokyo Denki University Japan Center for Advanced Intelligence Project RIKEN Japan Faculty of Data Science Shiga University Japan

Causal discovery is a methodology for learning causal graphs from data, and LiNGAM is a well-known model for causal discovery. This paper describes an open-source Python package for causal discovery based on LiNGAM. The package implements various LiNGAM methods under different settings like time series cases, multiple-group cases, mixed data cases, and hidden common cause cases, in addition to evaluation of statistical reliability and model assumptions. The source code is freely available under the MIT license at https://***/cdt15/lingam. ©2023 Takashi Ikeuchi, Mayumi Ide, Yan Zeng, Takashi Nicholas Maeda, and Shohei Shimizu.

关键词： Python

Structure Learning for Groups of Variables in Nonlinear Time-Series data with Location-Scale Noise

学校读者我要写书评

暂无评论

Structure Learning for Groups of Variables in Nonlinear Time...

2023 Causal Analysis Workshop Series, CAWS 2023

作者： Kikuchi, Genta Shimizu, Shohei Denso Corporation Aichi Kariya448-8661 Japan Graduate School of Data Science Shiga University Japan Center for Advanced Intelligence Project RIKEN Japan

Learning causal structures from observational data has recently attracted considerable attention. Although many studies have focused on uncovering the connections between scalar random variables, estimation algorithms for groups of variables—particularly for multiple groups of variables—remain scarce. This paper proposes a novel differentiable algebraic constraint that can be used along with existing continuous optimization-based structure-learning algorithms to learn the causal relationships among groups of variables. Considering the complex functional relationships among variables in real-world scenarios, we propose a structure-learning algorithm for nonlinear time-series data with location-scale noise. Experimental results for synthetic and real-world data indicate that the proposed group acyclicity constraint significantly increases the estimation accuracy for the causal relationship among the groups of variables and verify the effectiveness of the proposed structure-learning algorithm. © 2023 G. Kikuchi & S. Shimizu.

关键词： Causal discovery continuous optimization structural causal models time series variable groups

Chiller faults detection and diagnosis with sensor network and adaptive 1D CNN

学校读者我要写书评

暂无评论

Digital Communications and Networks 2022年第4期8卷 531-539页

作者： Ke Yan Xiaokang Zhou Department of the Built Environment National University of Singapore4 Architecture Drive117566Singapore Faculty of Data Science Shiga UniversityHikone5228522Japan RIKEN Center for Advanced Intelligence Project RIKENTokyo1030027Japan

Computer-empowered detection of possible faults for Heating,Ventilation and Air-Conditioning(HVAC)subsystems,e.g.,chillers,is one of the most important applications in Artificial Intelligence(AI)integrated Internet of Things(IoT).The cyber-physical system greatly enhances the safety and security of the working facilities,reducing time,saving energy and protecting humans’*** the current trends of smart building design and energy management optimization,Automated Fault Detection and Diagnosis(AFDD)of chillers integrated with IoT is highly *** studies show that standard machine learning techniques,such as Principal Component Analysis(PCA),Support Vector Machine(SVM)and tree-structure-based algorithms,are useful in capturing various chiller faults with high accuracy *** the fast development of deep learning technology,Convolutional Neural Networks(CNNs)have been widely and successfully applied to various ***,for chiller AFDD,few existing works are adopting CNN and its extensions in the feature extraction and classification *** this study,we propose to perform chiller FDD using a CNN-based *** proposed approach has two distinct advantages over existing machine learning-based chiller AFDD ***,the CNN-based approach does not require the feature selection/extraction *** CNN is reputable with its feature extraction capability,the feature extraction and classification processes are merged,leading to a more neat AFDD framework compared to traditional ***,the classification accuracy is significantly improved compared to traditional methods using the CNN-based approach.

关键词： Chiller Fault detection and diagnosis Deep learning neural network Long short term memory Recurrent neural network Gated recurrent unit

Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning 38

学校读者我要写书评

暂无评论

Provably Transformers Harness Multi-Concept Word Semantics f...

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Bu, Dake Huang, Wei Han, Andi Nitanda, Atsushi Suzuki, Taiji Zhang, Qingfu Wong, Hau-San Department of Computer Science City University of Hong Kong Hong Kong Center for Advanced Intelligence Project RIKEN Japan Singapore College of Computing and Data Science Nanyang Technological University Singapore Department of Mathematical Informatics The University of Tokyo Japan

Transformer-based large language models (LLMs) have displayed remarkable creative prowess and emergence capabilities. Existing empirical studies have revealed a strong connection between these LLMs' impressive emergence abilities and their in-context learning (ICL) capacity, allowing them to solve new tasks using only task-specific prompts without further fine-tuning. On the other hand, existing empirical and theoretical studies also show that there is a linear regularity of the multi-concept encoded semantic representation behind transformer-based LLMs. However, existing theoretical work fail to build up an understanding of the connection between this regularity and the innovative power of ICL. Additionally, prior work often focuses on simplified, unrealistic scenarios involving linear transformers or unrealistic loss functions, and they achieve only linear or sub-linear convergence rates. In contrast, this work provides a fine-grained mathematical analysis to show how transformers leverage the multi-concept semantics of words to enable powerful ICL and excellent out-of-distribution ICL abilities, offering insights into how transformers innovate solutions for certain unseen tasks encoded with multiple cross-concept semantics. Inspired by empirical studies on the linear latent geometry of LLMs, the analysis is based on a concept-based low-noise sparse coding prompt model. Leveraging advanced techniques, this work showcases the exponential 0-1 loss convergence over the highly non-convex training dynamics, which pioneeringly incorporates the challenges of softmax self-attention, ReLU-activated MLPs, and cross-entropy loss. Empirical simulations corroborate the theoretical findings. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

Finite-dimensional approximations of push-forwards on locally analytic functionals

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ishikawa, Isao Center for Data Science Ehime University Japan Center for Advanced Intelligence Project RIKEN Japan

This paper introduces a novel theoretical framework for investigating analytic maps from finite discrete data. Our approach is to consider the push-forward on the space of locally analytic functionals, instead of directly handling the analytic map itself. We establish a methodology enabling appropriate finite-dimensional approximation of the push-forward from finite discrete data, through the theory of the Fourier–Borel transform and the Fock space. Moreover, we prove a rigorous convergence result with a convergence rate. As an application, we prove that it is not the least-squares polynomial, but the polynomial obtained by truncating its higher-degree terms, that approximates analytic functions and further allows for approximation beyond the support of the data distribution. One advantage of our theory is that it enables us to apply linear algebraic operations to the finite-dimensional approximation of the push-forward. Utilizing this, we prove the convergence of a method for approximating an analytic vector field from finite data of the flow map of an ordinary differential *** Codes 32E30, 41A10, 65P99, 65D99, 30H20, 37M99, 37C30 Copyright © 2024, The Authors. All rights reserved.

关键词： Least squares approximations

Improving Fine-Tuning with Latent Cluster Correction

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Thanh, Cédric Ho Advanced Data Science Project RIKEN Information R&D and Strategy Headquarters RIKEN Tokyo Japan

The existence of salient semantic clusters in the latent spaces of a neural network during training strongly correlates its final accuracy on classification tasks. This paper proposes a novel fine-tuning method that boosts performance by optimising the formation of these latent clusters, using the Louvain community detection algorithm and a specifically designed clustering loss function. We present preliminary results that demonstrate the viability of this process on classical neural network architectures during fine-tuning on the CIFAR-100 dataset. © 2025, CC BY.

关键词： Network architecture

Hamiltonian Reordering for Shallower Trotterization Circuits

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Thanh, Cédric Ho Advanced Data Science Project RIKEN Information R&D and Strategy Headquarters RIKEN Tokyo Japan

Quantum simulation is a popular application of quantum computing, but its practical realization is hindered by the technical limitations of current devices. In this work, we focus on preprocessing Hamiltonians before Trotterization to generate shallower evolution circuits, which are less prone to noise and decoherence. Specifically, we apply graph coloring techniques to reorder Pauli terms and increase "gate parallelism". We benchmark two coloring algorithms, and report the depth reduction and computational overhead. Then, we examine how these optimized circuits affect the performance of the Quantum Approximate Optimization Algorithm (QAOA). Our results show that shallower circuits lead to faster convergence and reach higher energy levels compared to their non-reordered counterparts. © 2025, CC BY.

关键词： Hamiltonians

Does Financial Literacy Impact Investment Participation and Retirement Planning in Japan?

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Jiang, Yi Shimizu, Shohei Graduate School of Data Science Shiga University Japan Center for Advanced Intelligence Project RIKEN Japan

By employing causal discovery method, the Fast Causal Inference (FCI) model to analyze data from the 2022 "Financial Literacy Survey," we explore the causal relationships between financial literacy and financial activities, specifically investment participation and retirement planning. Our findings indicate that increasing financial literacy may not directly boost engagement in financial investments or retirement planning in Japan, which underscores the necessity for alternative strategies to motivate financial activities among Japanese households. This research offers valuable insights for policymakers focused on improving financial well-being by advancing the use of causal discovery algorithms in understanding financial behaviors. Copyright © 2024, The Authors. All rights reserved.

关键词： Investments

A Novel Gold Futures Price Prediction Model based on PCA-AGRU 29

学校读者我要写书评

暂无评论

A Novel Gold Futures Price Prediction Model based on PCA-AGR...

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Wang, Jingyang Lu, Tong Liu, Jindian Sun, Qiuhong Qi, Lianyong Zhou, Xiaokang Hebei University of Science and Technology School of Information Science and Engineering Shijiazhuang China Shiga University Faculty of Data Science Hikone522-8522 Japan Qingdao China RIKEN Center for Advanced Intelligence Project RIKEN Tokyo103-0027 Japan

ISBN: (纸本)9798350330717

As an important financial investment commodity, the price fluctuations of gold significantly impact the global economy and the stability of the financial market. Therefore, it is of great significance to accurately predict the price of gold futures. This paper presents a novel gold futures price prediction model, PCA-AGRU, based on Principal Component Analysis (PCA) and Adaptive Gated Recurrent Unit (AGRU). PCA is utilized for the dimensionality reduction of data while extracting essential features. AGRU bases on Gated Recurrent Unit (GRU), embeds Self-Attention (SA), and adds an adaptive adjustment mechanism, making the model more effective in capturing long-term dependencies within time series data. This paper uses the international gold futures market data as the experimental dataset, and uses Maximal Information Coefficient (MIC) to analyze the correlation of the influencing factors. The PCA-AGRU model is compared with five prediction models of GRU, SA-GRU, AGRU, PCA-GRU, and PCA-SA-GRU. The experimental results show that the PCA-AGRU model performs best in forecasting gold futures prices. © 2023 IEEE.

关键词： AGRU deep learning Gold Futures PCA Price Prediction SA