检索结果-内蒙古大学图书馆

Optical Character Recognition (OCR) in Handwritten Characters Using Convolutional Neural Networks to Assist in Exam Reader System 2

学校读者我要写书评

暂无评论

Optical Character Recognition (OCR) in Handwritten Character...

2nd International Conference on Advancement in Computation and Computer Technologies, InCACCT 2024

作者： Lekshmy, P.L. Velmurugan, S. Kumari, Indra Kayalvili, S. Teja Sree, B. Karthik Kumar, P. LBS Institute of Technology for Women Department of Computer Science and Engineering Kerala India T.J.S. Engineering College Department of Electronics and Communication Engineering Tamil Nadu Chennai India Department of Machine Learning Data Research Applied AI Daejeon Korea Republic of Department of Artificial Intelligence Tamilnadu Erode India S.R.K.R. Engineering College Department of Information Technology Andhra Pradesh Chinaamiram Bhimavaram India Coimbatore India

ISBN: (纸本)9798350371314

This work aimed to develop a character recognition method to facilitate the correction of answer cards in the Multiprova software through the development of a response card analysis flow that would culminate in the recognition of letters written by students and automatic correction of the tests. To isolate and identify the answers written on the answer cards, image segmentation techniques were used based on fixed marks printed on the cards. To recognize the letters and numbers written on the cards, trained three convolutional neural networks (for digits, letters and true or false). The results achieved (98.84% accuracy for digit CNN, 98.38% accuracy for letter CNN and 99.89% accuracy for true or false CNN) point out a great average success rate. © 2024 IEEE.

关键词： Convolutional neural networks

Adaptive Batch Sizes for Active learning: A Probabilistic Numerics Approach

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Adachi, Masaki Hayakawa, Satoshi Jørgensen, Martin Wan, Xingchen Nguyen, Vu Oberhauser, Harald Osborne, Michael A. Machine Learning Research Group University of Oxford United Kingdom Mathematical Institute University of Oxford United Kingdom Toyota Motor Corporation Japan Department of Computer Science University of Helsinki Finland Amazon United States

Active learning parallelization is widely used, but typically relies on fixing the batch size throughout experimentation. This fixed approach is inefficient because of a dynamic trade-off between cost and speed—larger batches are more costly, smaller batches lead to slower wall-clock run-times—and the tradeoff may change over the run (larger batches are often preferable earlier). To address this trade-off, we propose a novel Probabilistic Numerics framework that adaptively changes batch sizes. By framing batch selection as a quadrature task, our integration-error-aware algorithm facilitates the automatic tuning of batch sizes to meet predefined quadrature precision objectives, akin to how typical optimizers terminate based on convergence thresholds. This approach obviates the necessity for exhaustive searches across all potential batch sizes. We also extend this to scenarios with constrained active learning and constrained optimization, interpreting constraint violations as reductions in the precision requirement, to subsequently adapt batch construction. Through extensive experiments, we demonstrate that our approach significantly enhances learning efficiency and flexibility in diverse Bayesian batch active learning and Bayesian optimization *** Codes 62C10, 62F15 © 2023, CC BY-NC-ND.

关键词： Constrained optimization

A duality framework for analyzing random feature and two-layer neural networks

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Chen, Hongrui Long, Jihao Wu, Lei Department of Mathematics Stanford University United States Institute for Advanced Algorithmic Research Shanghai China School of Mathematical Sciences Peking University China Center for Machine Learning Research Peking University China AI for Science Institute Beijing China

We consider the problem of learning functions within the Fp,π and Barron spaces, which play crucial roles in understanding random feature models (RFMs), two-layer neural networks, as well as kernel methods. Leveraging tools from information-based complexity (IBC), we establish a dual equivalence between approximation and estimation, and then apply it to study the learning of the preceding function spaces. The duality allows us to focus on the more tractable problem between approximation and estimation. To showcase the efficacy of our duality framework, we delve into two important but under-explored problems: • Random feature learning beyond kernel regime: We derive sharp bounds for learning Fp,π using RFMs. Notably, the learning is efficient without the curse of dimensionality for p > 1. This underscores the extended applicability of RFMs beyond the traditional kernel regime, since Fp,π with p ∞ learning of RKHS: We establish sharp, spectrum-dependent characterizations for the convergence of L∞ learning error in both noiseless and noisy settings. Surprisingly, we show that popular kernel ridge regression can achieve near-optimal performance in L∞ learning, despite it primarily minimizing square loss. To establish the aforementioned duality, we introduce a type of IBC, termed I-complexity, to measure the size of a function class. Notably, I-complexity offers a tight characterization of learning in noiseless settings, yields lower bounds comparable to Le Cam’s in noisy settings, and is versatile in deriving upper bounds. We believe that our duality framework holds potential for broad application in learning analysis across more scenarios. Copyright © 2023, The Authors. All rights reserved.

关键词： Multilayer neural networks

Genetic prediction of quantitative traits: a machine learner’s guide focused on height

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Bourguignon, Lucie Weis, Caroline Jutzeler, Catherine R. Adamer, Michael Biomedical Data Science Lab D-HEST ETH Zurich Switzerland Schulthess Klinik Switzerland Swiss Institute of Bioinformatics Switzerland Machine Learning and Computational Biology Lab D-BSSE ETH Zurich Switzerland

machine learning and deep learning have been celebrating many successes in the application to biological problems, especially in the domain of protein folding. Another equally complex and important question has received relatively little attention by the machine learning community, namely the one of prediction of complex traits from genetics. Tackling this problem requires in-depth knowledge of the related genetics literature and awareness of various subtleties associated with genetic data. In this guide, we provide an overview for the machine learning community on current state of the art models and associated subtleties which need to be taken into consideration when developing new models for phenotype prediction. We use height as an example of a continuous-valued phenotype and provide an introduction to benchmark datasets, confounders, feature selection, and common metrics. © 2023, CC BY-NC-ND.

关键词： Forecasting

Quantization of Bandlimited Graph Signals

学校读者我要写书评

暂无评论

Quantization of Bandlimited Graph Signals

International Conference on Sampling Theory and Applications (SampTA)

作者： Felix Krahmer He Lyu Rayan Saab Anna Veselovska Rongrong Wang Department of Mathematics & Munich Data Science Institute Technical University of Munich and Munich Center for Machine Learning Garching/Munich Germany Department of Mathematics & Halicioglu Data Science Institute University of California San Diego San Diego USA Department of Computational Mathematics Science and Engineering & Department of Mathematics Michigan State University East Lansing USA

Graph models and graph-based signals are becoming increasingly important in machine learning, natural sciences, and modern signal processing. In this paper, we address the problem of quantizing bandlimited graph signals. We introduce two classes of noise-shaping algorithms for graph signals that differ in their sampling methodologies. We demonstrate that these algorithms can be efficiently used to construct quantized representatives of bandlimited graph-based signals with bounded amplitude. Moreover, for one of the algorithms, we provide theoretical guarantees on the relative error between the quantized representative and the true signal.

关键词：

An Enhanced Product Quality Evaluation using Hybrid LSTM-FCNN Model and GWO Algorithm for Social Media Sentiment Analysis

学校读者我要写书评

暂无评论

An Enhanced Product Quality Evaluation using Hybrid LSTM-FCN...

International conference of Electronics, Communication and Aerospace Technology (ICECA)

作者： V. S. Raj Kumar T. Kumaresan P. Rajesh Kanna S. Jagadeesan P. Showmiya P. Nithin Department of Artificial Intelligence and Data Science Bannari Amman Institute of Technology Erode India Department of Computer Science and Engineering Bannari Amman Institute of Technology Erode India Department of Computer Science and Engineering Nandha Engineering College Erode India Department of Computer Science – Cyber Security Nehru Institute of Technology Coimbatore India Department of Artificial Intelligence and Machine Learning Bannari Amman Institute of Technology Erode India

ISBN: (数字)9798350367904

ISBN: (纸本)9798350367911

Sentiment analysis is still in its developing era, and sometimes, struggles are faced in evaluating user sentiment due to the use of traditional models to analyze the relationship structures in social media interactions. To tackle the issue, we proposed an innovative approach Hybrid LSTM neural network and a fully connected neural network (FCNN) integrated with the Grey Wolf Optimization (GWO) algorithm. The objective of this proposed method is to improve sentiment analysis by employing the LSTM to capture the sequence of data and improve the ability of FCNNs to improve feature extraction and the analysis process. The proposed system process initiated with the data preprocessing of input Twitter sentiment dataset transformed into a suitable input to the Hybrid LSTM-FCNN neural network. Then, temporal dependency of the data captured by LSTM and FCNN is used to extract the features. The GWO method mimics the grey wolf hunting behaviour, for optimizing the proposed Hybrid LSTM-FCNN model’s parameters to enhance the classification accuracy. The system models start with the initialization of the model, parameters, and training the models using the dataset to reduce the cross-entropy loss, estimating the testing dataset from unseen data and fine-tuning using GWO as necessary. Results demonstrate significant improvements in sentiment categorization compared to traditional methods. The Hybrid LSTM-FCNN model, enhanced with GWO, effectively captures nuanced sentiment patterns, leading to more accurate classification. Additionally, GWO’s computational efficiency contributes to scalability. In conclusion, our proposed approach offers a promising solution for enhancing product quality evaluation through advanced neural network architectures and optimization algorithms applied to social media sentiment analysis.

关键词： Sentiment analysis Analytical models Accuracy Social networking (online) Neural networks Blogs Feature extraction data models Optimization Long short term memory

Enhancing the Prediction Accuracy of Brain Tumor Detection by using Fuzzy C-Means Segmentation and Support Vector machine

学校读者我要写书评

暂无评论

Enhancing the Prediction Accuracy of Brain Tumor Detection b...

IoT Based Control Networks and Intelligent Systems (ICICNIS), International Conference on

作者： M Revathi P Kalaiarasi S Jeevitha G Akilandasowmya Artificial Intelligence & Data Science St. Joseph's Institute of Technology Chennai India Department of Machine Learning Kalasalingam University Krishnankoil India Information Technology Jerusalem College of Engineering Chennai India Computer and Communication Engineering Sri Sairam Institute of Technology Chennai India

ISBN: (数字)9798331518097

ISBN: (纸本)9798331518103

Brain is an important organ of the human body that helps in the proper functioning of the all the organs. Without brain, the functions of other organs will not happen since they cannot run without the commands of brain. Brain tumor refers to a situation where an abnormal group of cells are found in some part of the brain. There are many types of brain tumor that are identified. The tumors in brain is independent of age and it can grow at anytime. The symptoms that is exhibited by the brain tumor depends on the size of the tumor cell as well as its location. machine learning algorithms helps in the earlier identification of the disease which can be used to give proper treatment. In this paper, a fuzzy c means based segmentation of image is done. Then classification of the segmented image is done by using Support Vector machine. The results shows 98% percentage of accuracy.

关键词： Support vector machines Image segmentation Accuracy machine learning algorithms Brain tumors Biological systems Intelligent systems Diseases

Prediction of Heart Failure by using machine learning and Feature Selection

学校读者我要写书评

暂无评论

Prediction of Heart Failure by using Machine Learning and Fe...

International Conference on Emerging Technologies, ICET

作者： Muhammad Haseeb Aslam Syed Fawad Hussain Machine Learning and Data Science (MDS) Lab Faculty of Computer Science & Engg. GIK Institute of Engg. Sciences & Tech. Khyber Pakhtunkhwa Pakistan

ISBN: (纸本)9781665459938

Heart attacks are one of the foremost causes of death in the world. While doctors can carry out multiple tests to diagnose it, it may go undetected for a long time which can prove fatal. However, it is possible to predict the potential risk of a heart attack using machine learning (ML) algorithms. This is done using patients' historical data and has found some success in the literature. However, not all features are equally important in such data which may result in low accuracy of prediction. In this study, we use feature selection techniques to select a subset of features with contribution to improve upon the prediction accuracy of ML models. Inforation theory based models are used for feature selection in combination with popular ML classifiers including Random forest (RF), Decision Trees (DTs), Logistic Regression (LR), k-nearest neighbors (kNN), Gradient Boosting, Bagging, Ensemble, Neural Network (NN) and Support Vector machines (SVM). The model is tested the real-world and publicly available Framingham dataset. Results show that the proposed approach improves the prediction of heart disease compared to baseline models.

关键词： Support vector machines Heart machine learning algorithms Predictive models Feature extraction Regression tree analysis Random forests

A Quadrature Approach for General-Purpose Batch Bayesian Optimization via Probabilistic Lifting

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Adachi, Masaki Hayakawa, Satoshi Jørgensen, Martin Hamid, Saad Oberhauser, Harald Osborne, Michael A. Machine Learning Research Group University of Oxford United Kingdom Mathematical Institute University of Oxford United Kingdom Department of Computer Science University of Helsinki Finland Aioi R&D Lab Oxford United Kingdom Mind Foundry Oxford United Kingdom

Parallelisation in Bayesian optimisation is a common strategy but faces several challenges: the need for flexibility in acquisition functions and kernel choices, flexibility dealing with discrete and continuous variables simultaneously, model misspecification, and lastly fast massive parallelisation. To address these challenges, we introduce a versatile and modular framework for batch Bayesian optimisation via probabilistic lifting with kernel quadrature, called SOBER, which we present as a Python library based on GPyTorch/BoTorch. Our framework offers the following unique benefits: (1) Versatility in downstream tasks under a unified approach. (2) A gradient-free sampler, which does not require the gradient of acquisition functions, offering domain-agnostic sampling (e.g., discrete and mixed variables, non-Euclidean space). (3) Flexibility in domain prior distribution. (4) Adaptive batch size (autonomous determination of the optimal batch size). (5) Robustness against a misspecified reproducing kernel Hilbert space. (6) Natural stopping *** Codes 62C10, 62F15 © 2024, CC BY-NC-SA.

关键词： Python