检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Ghojogh, Benyamin Ghodsi, Ali Karray, Fakhri Crowley, Mark Department of Electrical and Computer Engineering Machine Learning Laboratory University of Waterloo WaterlooON Canada Department of Statistics and Actuarial Science David R. Cheriton School of Computer Science Data Analytics Laboratory University of Waterloo WaterlooON Canada Department of Electrical and Computer Engineering Centre for Pattern Analysis and Machine Intelligence University of Waterloo WaterlooON Canada

This is a tutorial and survey paper on unification of spectral dimensionality reduction methods, kernel learning by Semidefinite Programming (SDP), Maximum Variance Unfolding (MVU) or Semidefinite Embedding (SDE), and its variants. We first explain how the spectral dimensionality reduction methods can be unified as kernel Principal Component Analysis (PCA) with different kernels. This unification can be interpreted as eigenfunction learning or representation of kernel in terms of distance matrix. Then, since the spectral methods are unified as kernel PCA, we say let us learn the best kernel for unfolding the manifold of data to its maximum variance. We first briefly introduce kernel learning by SDP for the transduction task. Then, we explain MVU in detail. Various versions of supervised MVU using nearest neighbors graph, by class-wise unfolding, by Fisher criterion, and by colored MVU are explained. We also explain out-of-sample extension of MVU using eigenfunctions and kernel mapping. Finally, we introduce other variants of MVU including action respecting embedding, relaxed MVU, and landmark MVU for big data. Copyright © 2021, The Authors. All rights reserved.

关键词： Surveys

CLIP: Cheap Lipschitz Training of Neural Networks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Bungert, Leon Raab, René Roith, Tim Schwinn, Leo Tenbrinck, Daniel Department Mathematics Friedrich-Alexander University Erlangen-Nürnberg Cauerstraße 11 Erlangen91058 Germany Machine Learning and Data Analytics Lab Friedrich-Alexander University Erlangen-Nürnberg Carl-Thiersch-Straße 2b Erlangen91052 Germany

Despite the large success of deep neural networks (DNN) in recent years, most neural networks still lack mathematical guarantees in terms of stability. For instance, DNNs are vulnerable to small or even imperceptible input perturbations, so called adversarial examples, that can cause false predictions. This instability can have severe consequences in applications which influence the health and safety of humans, e.g., biomedical imaging or autonomous driving. While bounding the Lipschitz constant of a neural network improves stability, most methods rely on restricting the Lipschitz constants of each layer which gives a poor bound for the actual Lipschitz constant. In this paper we investigate a variational regularization method named CLIP for controlling the Lipschitz constant of a neural network, which can easily be integrated into the training procedure. We mathematically analyze the proposed model, in particular discussing the impact of the chosen regularization parameter on the output of the network. Finally, we numerically evaluate our method on both a nonlinear regression problem and the MNIST and Fashion-MNIST classification databases, and compare our results with a weight regularization *** Codes 65K10, 68T07 Copyright © 2021, The Authors. All rights reserved.

关键词： Stability

Fast emulation of two-point angular statistics for photometric galaxy surveys

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Bonici, Marco Biggio, Luca Carbone, Carmelita Guzzo, Luigi INAF-IASF Milano Via Alfonso Corti 12 MilanoI-20133 Italy Data Analytics Lab Institute of Machine Learning Department of Computer Science ETH Zürich Switzerland Dipartimento di Fisica Aldo Pontremoli Università Degli Studi di Milano INFN Sez. di Milano Via Celoria 16 MilanoI-20133 Italy INAF Osservatorio Astronomico di Brera Milano Italy

We develop a set of machine-learning based cosmological emulators, to obtain fast model predictions for the C() an-gular power spectrum coefficients characterising tomographic observations of galaxy clustering and weak gravitational lensing from multi-band photometric surveys (and their cross-correlation). A set of neural networks are trained to map cosmological parameters into the coefficients, achieving a speed-up O(103) in computing the required statistics for a given set of cosmological parameters, with respect to standard Boltzmann solvers, with an accuracy better than 0.175% ( Copyright © 2022, The Authors. All rights reserved.

关键词： Surveys

Fractal Interpolation Densities

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Igudesman, Konstantin Tumakov, Maksim Snegina, Svetlana Tumakov, Dmitrii Department of Data Analysis and Machine Learning Financial University under the Government of Russian Federation 4th Veshnyakovsky pr. 4 Moscow111395 Russia Centre for Econometrics and Business Analytics St. Petersburg State University Uni-versitetskaya nab. 7/9 St. Petersburg199034 Russia Kazan Federal University Institute of Computational Mathematics and Information Technologies Russia Department of Legal Regulation of Economic Operations University under the Government of Russian Federation 4th Veshnyakovsky pr. 4 Moscow111395 Russia

Necessary and sufficient conditions are found under which a continuous fractal interpolation function is the distribution density of a continuous random variable. Examples of fractal interpolation densities are consid... 详细信息

关键词： Interpolation

Deep CNN: A machine learning approach for driver drowsiness detection based on eye state

学校读者我要写书评

暂无评论

Revue d'Intelligence Artificielle 2019年第6期33卷 461-466页

作者： Reddy Chirra, Venkata Rami Uyyala, Srinivasulu Reddy Kishore Kolli, Venkata Krishna Department of Computer Applications National Institute of Technology Tiruchirappalli620015 India Machine Learning and Data Analytics Lab Department of Computer Applications National Institute of Technology Tiruchirappalli620015 India Department of Computer Science and Engineering VFSTR Guntur522213 India

Driver drowsiness is one of the reasons for large number of road accidents these days. With the advancement in Computer Vision technologies, smart/intelligent cameras are developed to identify drowsiness in drivers, thereby alerting drivers which in turn reduce accidents when they are in fatigue. In this work, a new framework is proposed using deep learning to detect driver drowsiness based on Eye state while driving the vehicle. To detect the face and extract the eye region from the face images, Viola-Jones face detection algorithm is used in this work. Stacked deep convolution neural network is developed to extract features from dynamically identified key frames from camera sequences and used for learning phase. A SoftMax layer in CNN classifier is used to classify the driver as sleep or non-sleep. This system alerts driver with an alarm when the driver is in sleepy mood. The proposed work is evaluated on a collected dataset and shows better accuracy with 96.42% when compared with traditional CNN. The limitation of traditional CNN such as pose accuracy in regression is overcome with the proposed Staked Deep CNN. © 2019 Lavoisier. All rights reserved.

关键词： Face recognition

An Image-Based Method for Measuring Strabismus in Virtual Reality

学校读者我要写书评

暂无评论

An Image-Based Method for Measuring Strabismus in Virtual Re...

IEEE International Symposium on Mixed and Augmented Reality Workshops (ISMARW)

作者： Wolfgang A. Mehringer Markus Gerhard Wirth Stefan Gradl Luis S. Durner Matthias Ring Annemarie F Laudanski Bjoern Eskofier Georg Michelson Machine Learning and Data Analytics Lab University of Erlangen-Nürnberg (FAU) University of Waterloo Talkingeyes&More GmbH University of Erlangen-Nürnberg (FAU)

ISBN: (数字)9781728176758

ISBN: (纸本)9781728176765

Strabismus is a visual disorder characterized by eye misalignment. The effect of Panum's Fusional Area (PFA) compensates for small misalignments. However, prominent misalignments affect binocular vision and when present in childhood it may lead to amblyopia, a developmental disorder of the visual system. With the advent of Virtual Reality (VR) technology, possibilities for novel binocular treatments to amblyopia arise in which the measurement of strabismus is crucial to correctly compensate for it. Thus, VR yields great potential due to the ability of displaying content to each eye independently. Major research in VR addresses this topic using eye-tracking while there is a paucity of research on image-based assessment methods. In this work, we propose a VR application for measuring strabismus in nine lines of sight. We conducted a study with 14 healthy participants to evaluate the system under two conditions: no strabismus and an artificial deviation induced by prism lenses. Further, we evaluated the effect of PFA on the system by measuring its extent in horizontal and vertical lines of sight. Results show significant difference between the expected deviation induced by prism lenses and the measured deviation. The existing difference within the measurements can be explained with the recorded extent of the PFA.

关键词： Visualization Atmospheric measurements Particle measurements Vision defects Augmented reality Lenses

Automatic Diagnosis of Myocarditis Disease in Cardiac MRI Modality using Deep Transformers and Explainable Artificial Intelligence

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Jafari, Mahboobeh Shoeibi, Afshin Ghassemi, Navid Heras, Jonathan Ling, Sai Ho Beheshti, Amin Zhang, Yu-Dong Wang, Shui-Hua Alizadehsani, Roohallah Gorriz, Juan M. Acharya, U. Rajendra Rokny, Hamid Alinejad Internship in BioMedical Machine Learning Lab The Graduate School of Biomedical Engineering UNSW Sydney SydneyNSW2052 Australia Data Science and Computational Intelligence Institute University of Granada Spain Department of Mathematics and Computer Science University of La Rioja La Rioja Spain Australia Data Analytics Lab Department of Computing Macquarie University SydneyNSW2109 Australia School of Computing and Mathematical Sciences University of Leicester Leicester United Kingdom Deakin University VIC3217 Australia Department of Psychiatry University of Cambridge United Kingdom School of Mathematics Physics and Computing University of Southern Queensland Springfield Australia BioMedical Machine Learning Lab The Graduate School of Biomedical Engineering UNSW Sydney SydneyNSW2052 Australia UNSW Data Science Hub The University of New South Wales SydneyNSW2052 Australia Research Centre Macquarie University Sydney2109 Australia

Myocarditis is a significant cardiovascular disease (CVD) that poses a threat to the health of many individuals by causing damage to the myocardium. The occurrence of microbes and viruses, including the likes of HIV, plays a crucial role in the development of myocarditis disease (MCD). The images produced during cardiac magnetic resonance imaging (CMRI) scans are low contrast, which can make it challenging to diagnose cardiovascular diseases. In other hand, checking numerous CMRI slices for each CVD patient can be a challenging task for medical doctors. To overcome the existing challenges, researchers have suggested the use of artificial intelligence (AI)-based computer-aided diagnosis systems (CADS). The presented paper outlines a CADS for the detection of MCD from CMR images, utilizing deep learning (DL) methods. The proposed CADS consists of several steps, including dataset, preprocessing, feature extraction, classification, and post-processing. First, the Z-Alizadeh dataset was selected for the experiments. Subsequently, the CMR images underwent various preprocessing steps, including denoising, resizing, as well as data augmentation (DA) via CutMix and MixUp techniques. In the following, the most current deep pre-trained and transformer models are used for feature extraction and classification on the CMR images. The findings of our study reveal that transformer models exhibit superior performance in detecting MCD as opposed to pre-trained architectures. In terms of DL architectures, the Turbulence Neural Transformer (TNT) model exhibited impressive accuracy, reaching 99.73% utilizing a 10-fold cross-validation approach. Additionally, to pinpoint areas of suspicion for MCD in CMRI images, the Explainable-based Grad Cam method was employed. © 2022, CC BY-NC-ND.

关键词： Diseases

T-Cell Receptor Optimization with Reinforcement learning and Mutation Policies for Precision Immunotherapy

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Chen, Ziqi Min, Martin Renqiang Guo, Hongyu Cheng, Chao Clancy, Trevor Ning, Xia Computer Science and Engineering The Ohio State University ColumbusOH43210 United States Machine Learning Department NEC Labs PrincetonNJ08540 United States Digital Technologies Research Centre National Research Council Canada ON Canada Department of Medicine Baylor College of Medicine HoustonTX77030 United States NEC Oncolmmunity AS Oslo Cancer Cluster Innovation Park Ullernchausséen 64 Oslo0379 Norway Biomedical Informatics The Ohio State University ColumbusOH43210 United States Translational Data Analytics Institute The Ohio State University ColumbusOH43210 United States

T cells monitor the health status of cells by identifying foreign peptides displayed on their surface. T-cell receptors (TCRs), which are protein complexes found on the surface of T cells, are able to bind to these peptides. This process is known as TCR recognition and constitutes a key step for immune response. Optimizing TCR sequences for TCR recognition represents a fundamental step towards the development of personalized treatments to trigger immune responses killing cancerous or virus-infected cells. In this paper, we formulated the search for these optimized TCRs as a reinforcement learning (RL) problem, and presented a framework TCRPPO with a mutation policy using proximal policy optimization. TCRPPO mutates TCRs into effective ones that can recognize given peptides. TCRPPO leverages a reward function that combines the likelihoods of mutated sequences being valid TCRs measured by a new scoring function based on deep autoencoders, with the probabilities of mutated sequences recognizing peptides from a peptide-TCR interaction predictor. We compared TCRPPO with multiple baseline methods and demonstrated that TCRPPO significantly outperforms all the baseline methods to generate positive binding and valid TCRs. These results demonstrate the potential of TCRPPO for both precision immunotherapy and peptide-recognizing TCR motif discovery. © 2023, CC BY.

关键词： Reinforcement learning

A Bidirectional LSTM Model for Classifying Chatbot Messages

学校读者我要写书评

暂无评论

A Bidirectional LSTM Model for Classifying Chatbot Messages

International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP)

作者： Nunthawat Lhasiw Nuttapong Sanglerdsinlapachai Tanatorn Tanantong Faculty of Science and Technology Thammasat University Pathum Thani Thailand Strategic Analytics Networks With Machine Learning and AI Research Team National Electronics and Computer Technology Center Pathum Thani Thailand Thammasat Research Unit in Data Innovation and Artificial Intelligence Faculty of Science and Technology Thammasat University Pathum Thani Thailand

ISBN: (纸本)9781665409483

Online channels, e.g., Facebook Messenger and Line, are widely used especially in COVID-19 pandemic. To quickly respond to their customer, chatbot system are implemented in many companies or organizations, connected to those channels. The Office of Registrar, Thammasat University also implements a chatbot to answer questions from students. An important step in the chatbot system is to know an intention of a question message. A bidirectional LSTM model is employed to classify a question message from the chatbot system into five intention classes. The experimental results shows that the obtained model yields an accuracy of 0.80 on our validation dataset.

关键词： Training COVID-19 Social networking (online) Pandemics data integrity Memory management Companies

Superposition as data Augmentation Using Lstm and Hmm in Small Training Sets

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Sivaswamy, Akilesh Pavlovskiy, Evgeniy Stream Data Analytics and Machine Learning lab Novosibirsk State University

Considering audio and image data as having quantum nature (data are represented by density matrices), we achieved better results on training architectures such as 3-layer stacked LSTM and HMM by mixing training samples using superposition augmentation and compared with plain default training and mix-up augmentation. This augmentation technique originates from the mix-up approach but provides more solid theoretical reasoning based on quantum properties. We achieved 3% improvement (from 68% to 71%) by using 38% lesser number of training samples in Russian audio-digits recognition task and 7,16% better accuracy than mix-up augmentation by training only 500 samples using HMM on the same task. Also, we achieved 1.1% better accuracy than mix-up on first 900 samples in MNIST using 3-layer stacked LSTM. Copyright © 2019, The Authors. All rights reserved.

关键词： Quantum theory