检索结果-内蒙古大学图书馆

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Yo Joong Choe Aditya Gangrade Aaditya Ramdas Data Science Institute University of Chicago Department of EECS University of Michigan Dept. of Statistics and Data Science Machine Learning Department Carnegie Mellon University

Abstaining classifiers have the option to abstain from making predictions on inputs that they are unsure about. These classifiers are becoming increasingly popular in high-stakes decision-making problems, as they can withhold uncertain predictions to improve their reliability and safety. When evaluating black-box abstaining classifier(s), however, we lack a principled approach that accounts for what the classifier would have predicted on its abstentions. These missing predictions matter when they can eventually be utilized, either directly or as a backup option in a failure mode. In this paper, we introduce a novel approach and perspective to the problem of evaluating and comparing abstaining classifiers by treating abstentions as missing data. Our evaluation approach is centered around defining the counterfactual score of an abstaining classifier, defined as the expected performance of the classifier had it not been allowed to abstain. We specify the conditions under which the counterfactual score is identifiable: if the abstentions are stochastic, and if the evaluation data is independent of the training data (ensuring that the predictions are missing at random), then the score is identifiable. Note that, if abstentions are deterministic, then the score is unidentifiable because the classifier can perform arbitrarily poorly on its abstentions. Leveraging tools from observational causal inference, we then develop nonparametric and doubly robust methods to efficiently estimate this quantity under identification. Our approach is examined in both simulated and real data experiments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Next-Gen Dermatology: Revolutionizing Dermatological Diagnostics with AI and Emergency Care Solutions

Next-Gen Dermatology: Revolutionizing Dermatological Diagnos...

引用

Intelligent and Innovative Technologies in Computing, Electrical and Electronics (IITCEE), International Conference

作者： Yashas D M Shivani Kashyap Charan PR Hemanth Kumar GP Abhishek BK Deekshith C Dept of Artificial Intelligence and Machine Learning New Horizon College of Engineering Bengaluru Dept of Information Science and Engineering New Horizon College of Engineering Bengaluru Dept of Artificial Intelligence and Machine Learning BNM Institute of Technology Bengaluru Dept of Artificial Intelligence and Data Science Siddaganga Institute of Technology Tumkur Dept of Computer Science and Engineering Vidyavardhaka College of Engineering Mysore

ISBN: (数字)9798331515911

ISBN: (纸本)9798331515928

Skin health conditions should be diagnosed and treated on time so as to prevent complications and promote better health results. This paper presents an AI-based system that makes use of Convolutional Neural Networks with the InceptionV3 Architecture for predicting skin diseases at higher levels. The model, which is based on the large DermaNet dataset, classifies skin disorders fast and effectively. The system is coupled with a simple Telegram based application for the users to get a complete solution. A user can upload a photo of the affected skin area and get a diagnosis within seconds, an explanation of the disease and how severe it is in percentage. The bot also has a location and contact sharing feature that assists users in finding nearby doctors and clinics that can provide further assistance. It further provides on the spot appropriate cures for the particular condition diagnosed. Moreover, this makes it possible for the customer to fill the healthcare void in particular the neglected ones by making it easy for them to access real time high quality services. By equipping users with relevant information and appropriate actions required at the right time, this project has showcased how AI has the ability to transform the dermatological field.

关键词： Deep learning Dermatology Medical services Transforms Chatbots Skin Real-time systems Convolutional neural networks Artificial intelligence Diseases

来源：评论

学校读者我要写书评

暂无评论

Facial Expression Recognition Using Multi-Block Deep CNN 5

Facial Expression Recognition Using Multi-Block Deep CNN

引用

5th International Conference on Circuits, Control, Communication and Computing, I4C 2024

作者： Priyadarshini, V. Srinivasulu Reddy, U. Reddy Chirra, Venkata Rami Mrudula, M. Suneetha, M. National Institute of Technology Dept. of Computer Science & Engineering Andhra Pradesh India Machine Learning & Data Analytics Lab National Institute of Technology Dept. of Computer Applications Tiruchirappalli India School of Computer Science & Engineering VIT-AP University Amaravathi India Malla Reddy College of Engineering Department of CSE Telangana India Independent Researcher Amaravati India

ISBN: (纸本)9798331528539

Emotions play a crucial role in decision-making, moral judgments, and other cognitive processes. The goal of this work is to identify people's facial emotions from face images. Facial expression recognition (FER), a highly diverse field with many commonalities between classes, is a challenging problem. The capabilities of current FER systems are limited in this regard. In this work, a multi-block Deep Convolutional Neural Networks (DCNN) model was proposed to identify facial expressions. Five blocks with different computational components were defined in a multi-block DCNN to extract the unique characteristics from input images. The second model (DCNN-SVM) is developed with an ensemble of SVM classifier to improve predictability and stability. The third model (DCNN-MV) is based on the majority voting with 4 classifiers SVM, KNN, Random Forest, and Decision Tree. The CK+ dataset was utilized and expanded via image data augmentation to enhance model performance and generalization. By adjusting hyperparameters, the suggested DCNN model's accuracy was investigated. The DCNN model reports an accuracy score of 97.71%. Both DCNN-SVM and DCNN-MV models achieved 97.79% accuracy. On the CK+ dataset, the proposed models demonstrated good accuracy in identifying facial expressions. When compared to existing models, the proposed model outperformed existing models in terms of accuracy. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

ChatGPT-guided Semantics for Zero-shot learning

ChatGPT-guided Semantics for Zero-shot Learning

引用

2023 International Conference on Digital Image Computing: Techniques and Applications, DICTA 2023

作者： Shubho, Fahimul Hoque Chowdhury, Townim Faisal Cheraghian, Ali Saberi, Morteza Mohammed, Nabeel Rahman, Shafin North South University Dept. of Electrical and Computer Engineering Bangladesh University of Adelaide Australian Institute for Machine Learning Australia Data61 Commonwealth Scientific and Industrial Research Organisation Australia University of Technology Sydney School of Computer Science and Dsi Australia

ISBN: (纸本)9798350382204

Zero-shot learning (ZSL) aims to classify objects that are not observed or seen during training. It relies on class semantic description to transfer knowledge from the seen classes to the unseen classes. Existing methods of obtaining class semantics include manual attributes or automatic word vectors from language models (like word2vec). We know attribute annotation is costly, whereas automatic word vectors are relatively noisy. To address this problem, we explore how ChatGPT, a large language model, can enhance class semantics for ZSL tasks. ChatGPT can be a helpful source to obtain text descriptions for each class containing related attributes and semantics. We use the word2vec model to get a word vector using the texts from ChatGPT. Then, we enrich word vectors by combining the word embeddings from class names and descriptions generated by ChatGPT. More specifically, we leverage ChatGPT to provide extra supervision for the class description, eventually benefiting ZSL models. We evaluate our approach on various 2D image (CUB and AwA) and 3D point cloud (ModelNet10, ModelNet40, and ScanObjectNN) datasets and show that it improves ZSL performance. Our work contributes to the ZSL literature by applying ChatGPT for class semantics enhancement and proposing a novel word vector fusion method. © 2023 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Transforming Text to Video: Leveraging Advanced Generative AI Techniques

Transforming Text to Video: Leveraging Advanced Generative A...

引用

Intelligent Technologies (ACOIT), Asian Conference on

作者： P Indira Priya M Manju R Anitha R Harsavardhini S Sri Harini Dept. of Artificial Intelligence and Data Science Rajalakshmi Engineering College Chennai India Dept. of Artificial Intelligence and Machine Learning Rajalakshmi Engineering College Chennai India

ISBN: (数字)9798350374957

ISBN: (纸本)9798350374964

This comprehensive evaluation paper delves into the realm of textual content-to-video generation using artificial intelligence. The authors present an inclusive analysis of key reference papers: VGEN - Text to Video Generation Using AI, MAGVIT, STF, DirecT2V, Text2Video-Zero, Tune-A-Video, and four supplementary papers. These manuscripts collectively address various challenges and propose groundbreaking methodologies for producing high-quality videos from textual prompts. VGEN aims to synthesize videos from textual descriptions using pioneering approaches inspired by the strategic tokenization and embedding techniques employed in MAGVIT. STF introduces a cutting-edge 3D generative model specifically designed for text-to-video generation, while DirecT2V focuses on developing lightweight video diffusion models that operate within a low-dimensional latent space. Text2Video-Zero explores zero-shot video generation using diffusion models, and Tune-A-Video introduces a one-shot tuning method that leverages image diffusion models to generate videos. The additional papers contribute to advancements in latent diffusion models, video LDMs, and spatio-temporal attention mechanisms. By incorporating these techniques, the project aims to generate high-fidelity, long-duration videos with content consistency and motion coherence. Code and models are provided for reproducibility, encouraging collaboration in the field. Extensive qualitative and quantitative evaluations demonstrate the effectiveness and versatility of the approaches in producing realistic and diverse videos aligned with textual descriptions. This comprehensive review paper serves as a guide to current strategies in text-to-video technology, offering insights and directions for future research in this exciting field.

关键词： Translation Three-dimensional displays Statistical analysis Streaming media Diffusion models Aerodynamics Reproducibility of results Tokenization Text to video Tuning

来源：评论

学校读者我要写书评

暂无评论

Digital Halftoning via Mixed-Order Weighted Σ∆ Modulation

Digital Halftoning via Mixed-Order Weighted Σ∆ Modulation

引用

International Conference on Sampling Theory and Applications (SampTA)

作者： Felix Krahmer Anna Veselovska Dept. of Mathematics & Munich Data Science Institute Technical University of Munich and Munich Center for Machine Learning Garching/Munich Germany

In this paper, we propose 1-bit weighted Σ∆ quantization schemes of mixed order as a technique for digital halftoning. These schemes combine weighted Σ∆ schemes of different orders for two-dimensional signals so one can profit both from the better stability properties of low order schemes and the better accuracy properties of higher order schemes. We demonstrate that the resulting mixed-order Σ∆ schemes in combination with a padding strategy yield improved representation quality in digital halftoning as measured in the Feature Similarity *** empirical results are complemented by mathematical error bounds for the model of two-dimensional bandlimited signals as motivated by a mathematical model of human visual perception.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Decision-Focused Evaluation of Worst-Case Distribution Shift

arXiv

引用

arXiv 2024年

作者： Ren, Kevin Byun, Yewon Wilder, Bryan Statistics and Data Science Dept. Carnegie Mellon University PittsburghPA United States Machine Learning Dept. Carnegie Mellon University PittsburghPA United States

Distribution shift is a key challenge for predictive models in practice, creating the need to identify potentially harmful shifts in advance of deployment. Existing work typically defines these worst-case shifts as ones that most degrade the individual-level accuracy of the model. However, when models are used to make a downstream population-level decision like the allocation of a scarce resource, individual-level accuracy may be a poor proxy for performance on the task at hand. We introduce a novel framework that employs a hierarchical model structure to identify worst-case distribution shifts in predictive resource allocation settings by capturing shifts both within and across instances of the decision problem. This task is more difficult than in standard distribution shift settings due to combinatorial interactions, where decisions depend on the joint presence of individuals in the allocation task. We show that the problem can be reformulated as a submodular optimization problem, enabling efficient approximations of worst-case loss. Applying our framework to real data, we find empirical evidence that worst-case shifts identified by one metric often significantly diverge from worst-case distributions identified by other metrics. Copyright © 2024, The Authors. All rights reserved.

关键词： Hierarchical systems

来源：评论

学校读者我要写书评

暂无评论

Curriculum learning Effectively Improves Low data VQA 19th

Curriculum Learning Effectively Improves Low Data VQA

引用

19th Workshop of the Australasian Language Technology Association, ALTA 2021

作者： Askarian, Narjes Abbasnejad, Ehsan Zukerman, Ingrid Buntine, Wray Haffari, Gholamreza Dept. of Data Science and AI Monash University Australia Australian Institute for Machine Learning The Univ. of Adelaide Australia

Visual question answering (VQA) models, in particular modular ones, are commonly trained on large-scale datasets to achieve state of the art performance. However, such datasets are sometimes not available. Further, it has been shown that training these models on small datasets significantly reduces their accuracy. In this paper, we propose a curriculum-based learning (CL) regime to increase the accuracy of VQA models trained on small datasets. Specifically, we offer three criteria to rank the samples in these datasets, and propose a training strategy for each criterion. Our results show that, for small datasets, our CL approach yields more accurate results than those obtained when training with no curriculum. © ALTA 2021. All rights reserved.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Decomposed Linear Dynamical Systems for Robust Discovery of Latent Neural Dynamics 38

Probabilistic Decomposed Linear Dynamical Systems for Robust...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Chen, Yenho Mudrik, Noga Johnsen, Kyle A. Alagapan, Sankaraleengam Charles, Adam S. Rozell, Christopher J. Machine Learning Center Georgia Institute of Technology United States School of Electrical and Computer Engineering Georgia Institute of Technology United States Coulter Dept. of Biomedical Engineering Emory University Georgia Institute of Technology United States Department of Biomedical Engineering Mathematical Institute for Data Science Center for Imaging Science Kavli Neuroscience Discovery Institute Johns Hopkins University United States

Time-varying linear state-space models are powerful tools for obtaining mathematically interpretable representations of neural signals. For example, switching and decomposed models describe complex systems using latent variables that evolve according to simple locally linear dynamics. However, existing methods for latent variable estimation are not robust to dynamical noise and system nonlinearity due to noise-sensitive inference procedures and limited model formulations. This can lead to inconsistent results on signals with similar dynamics, limiting the model's ability to provide scientific insight. In this work, we address these limitations and propose a probabilistic approach to latent variable estimation in decomposed models that improves robustness against dynamical noise. Additionally, we introduce an extended latent dynamics model to improve robustness against system nonlinearities. We evaluate our approach on several synthetic dynamical systems, including an empirically-derived brain-computer interface experiment, and demonstrate more accurate latent variable inference in nonlinear systems with diverse noise conditions. Furthermore, we apply our method to a real-world clinical neurophysiology dataset, illustrating the ability to identify interpretable and coherent structure where previous models cannot. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A $4\times 4$ Millimeter-Wave Antenna Based on a Higher Order Mode in a Sub-mode Microwave SIW Strucutre for Recent 5G Applications

A $4\times 4$ Millimeter-Wave Antenna Based on a Higher Orde...

引用

European Conference on Antennas and Propagation, EuCAP

作者： Amjaad T. Altakhaineh Saqer S. Alja'afreh Chaoyun Song Data Science and Machine Learning Dept Pioneers International Academy Amman Jordan Dept of Electrical Engineering Mutah University Alkarak Jordan Department of Engineering King's College London London United Kingdom

ISBN: (数字)9788831299107

ISBN: (纸本)9798350366327

This paper presents a single structure, multi-port antenna for 5G millimeter wave (mmWave) applications. The proposed antenna is constructed by exploiting the higher-order modes of a fraction-mode microwave substrate-integrated waveguide (SIW) cavity at 28 GHz (quadrature mode substrate-integrated waveguide (QMSIW)). Such properties exhibit spatial multiplexing capabilities, giving the single cavity a MIMO capability. Firstly, two perpendicular T-shaped microstrip ports (Port 1 and Port 2) are installed to excite TE205 higher-order mode of the QMSIW cavity at 28 GHz. To extend the MIMO capability, a 4×4 MIMO QMSIW antenna is created by adding two extra coaxial feeding ports (Port 3 and Port 4), the higher-order modes of the cavity are reused by leveraging two orthogonal inverted L-shaped slots, in which each slot is excited using coaxial cables at 28 GHz. The proposed antenna exhibited a wide -10 dB impedance and > 11 dB isolation based on the simulation environment without using decoupling structures. Finally, we believe this work offers a promising contribution to present and future multi-port single antenna, MIMO, and polarization applications.

关键词： Phased arrays Microwave antennas Slot antennas 5G mobile communication Simulation Microwave communication Millimeter wave propagation Space division multiplexing Millimeter wave communication Substrates

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：