检索结果-内蒙古大学图书馆

EFFICIENT ITERATIVE TECHNIQUES FOR SOLVING TENSOR PROBLEMS WITH THE T-PRODUCT

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Kooshkghazi, Malihe Nobakht Ahmadi-Asl, Salman Afshin, Hamidreza Department of Mathematics Vali-e-Asr University of Rafsanjan Rafsanjan Iran Lab of Machine Learning and Knowledge Representation Innopolis University Innopolis420500 Russia

This paper presents iterative methods for solving tensor equations involving the T-product. The proposed approaches apply tensor computations without matrix construction. For each initial tensor, these algorithms solve related problems in a finite number of iterations, with negligible errors. The theoretical analysis is validated by numerical examples that demonste the practicality and effectiveness of these algorithms. © 2025, CC BY.

关键词： Gradient methods

Building a robust and compact search index

学校读者我要写书评

暂无评论

Building a robust and compact search index

2021 International Conference "Nonlinearity, Information and Robotics", NIR 2021

作者： Savchuk, Vladislav Protasov, Stanislav Innopolis Univesity Machine learning and knowledge representation lab Innopolis Russia

ISBN: (纸本)9781665424066

With exponential data growth search engines require more memory for storage and time for search. The data is indexed to increase search speed, which requires additional memory. In this study we develop a fully functional search engine for Wikipedia articles and compare different indexing techniques. Using vector quantization for compression we fit an index into a single machine's RAM. Moreover, we show that by using metadata and additional search for the out-of-vocabulary words we improve the overall system's quality. © 2021 IEEE.

关键词： Search engines

Domain generalization using ensemble learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Mesbah, Yusuf Ibrahim, Youssef Youssry Khan, Adil Mehood Machine Learning and Knowledge Representation Lab Innopolis University Tatarstan Russia

Domain generalization is a sub-field of transfer learning that aims at bridging the gap between two different domains in the absence of any knowledge about the target domain. Our approach tackles the problem of a model's weak generalization when it is trained on a single source domain. From this perspective, we build an ensemble model on top of base deep learning models trained on a single source to enhance the generalization of their collective prediction. The results achieved thus far have demonstrated promising improvements of the ensemble over any of its base learners. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep learning

Impact of Model Ensemble on the Fairness of Classifiers in machine learning

学校读者我要写书评

暂无评论

Impact of Model Ensemble on the Fairness of Classifiers in M...

2021 International Conference on Applied Artificial Intelligence, ICAPAI 2021

作者： Kenfack, Patrik Joslin Khan, Adil Mehmood Ahsan Kazmi, S.M. Hussain, Rasheed Oracevic, Alma Khattak, Asad Masood Networks and Blockchain Lab Innopolis University Innopolis Russia Machine Learning and Knowledge Representation Lab Innopolis University Innopolis Russia College of Technological Innovation Zayed University Abu Dhabi United Arab Emirates

ISBN: (纸本)9781728159348

machine learning (ML) models are trained using historical data that may contain stereotypes of the society (biases). These biases will be inherently learned by the ML models which might eventually result in discrimination against certain subjects, for instance, people with certain protected characteristics (race, gender, age, religion, etc.). Since the decision provided by ML models might affect people's lives, fairness of these models becomes crucially important. When training a model with fairness constraints, a significant loss in accuracy relative to the unconstrained model may be unavoidable. Reducing the trade-off between fairness and accuracy is an active research question within the fair ML community, i.e., to provide models with high accuracy with as little bias as possible. In this paper, we extensively investigate the fairness metrics over different ML models and study the impact of ensemble models on fairness. To this end, we compare different ensemble strategies and empirically show which strategy is preferable for different fairness metrics. Furthermore, we also propose a novel weighting technique that allows a balance between fairness and accuracy. In essence, we assign weights such that they are proportional to classifiers' performance in term of fairness and accuracy. Our experimental results show that our weighting technique reduces the trade-off between fairness and accuracy in ensemble models. © 2021 IEEE.

关键词： machine learning

Gait Fingerprinting-based User Identification on Smartphones

学校读者我要写书评

暂无评论

Gait Fingerprinting-based User Identification on Smartphones

International Joint Conference on Neural Networks

作者： Muhammad Ahmad Adil Mehmood Khan Joseph Alexander Brown StanislavProtasov Asad Masood Khattak Machine Learning and Knowledge Representation Lab Innopolis University Artificial Intelligence in Game Development Lab Innopolis University Machine Learning and Knowledge Representation Lab Innopolis University College of Technological Innovation Zayed University

ISBN: (纸本)9781509006212

Smartphones have ubiquitously integrated into our home and work environments. It is now a common practice for people to store their sensitive and confidential information on their phones. This has made it extremely important to authenticate legitimate users of a phone and block imposters. In this paper, we demonstrate that the motion dynamics of smartphones, captured using their built in accelerometers, can be used for accurate user identification. We call this mechanism gait fingerprinting. To this end, we first collected the acceleration data from multiple users as they walked with a smartphone placed freely in their pants pockets. Next, we studied the application of different feature extraction, feature selection and classification techniques from the machine learning literature on these data. Through extensive experimentation, demonstrated is that simple time domain features extracted from these data, which are further optimized using stepwise linear discrimination analysis, can be used to train artificial neural networks to identify legitimate user and block imposter with an average accuracy of 95%.

关键词： Ubiquitous Smartphone User identification Imposter Smartphone user id Telephone Confidential Information work environment

Adversarial stacked auto-encoders for fair representation learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Kenfack, Patrik Joslin Khan, Adil Mehmood Hussain, Rasheed Kazmi, S.M. Ahsan Networks and Blockchain Lab Innopolis University Innopolis Russia Machine Learning and Knowledge Representation Lab Innopolis University Innopolis Russia

Training machine learning models with the only accuracy as a final goal may promote prejudices and discriminatory behaviors embedded in the data. One solution is to learn latent representations that fulfill specific fairness metrics. Different types of learning methods are employed to map data into the fair representational space. The main purpose is to learn a latent representation of data that scores well on a fairness metric while maintaining the usability for the downstream task. In this paper, we propose a new fair representation learning approach that leverages different levels of representation of data to tighten the fairness bounds of the learned representation. Our results show that stacking different auto-encoders and enforcing fairness at different latent spaces result in an improvement of fairness compared to other existing approaches. © 2021, CC BY.

关键词： learning systems

RepFair-GAN: Mitigating representation Bias in GANs Using Gradient Clipping

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Kenfack, Patrik Joslin Sabbagh, Kamil Rivera, Adín Ramírez Khan, Adil Machine Learning and Knowledge Representation Lab Innopolis University Innopolis Russia Departments of Informatics University of Oslo Oslo Norway

Fairness has become an essential problem in many domains of machine learning (ML), such as classification, natural language processing, and Generative Adversarial Networks (GANs). In this research effort, we study the unfairness of GANs. We formally define a new fairness notion for generative models in terms of the distribution of generated samples sharing the same protected attributes (gender, race, etc.). The defined fairness notion (representational fairness) requires the distribution of the sensitive attributes at the test time to be uniform, and, in particular for GAN model, we show that this fairness notion is violated even when the dataset contains equally represented groups, i.e., the generator favors generating one group of samples over the others at the test time. In this work, we shed light on the source of this representation bias in GANs along with a straightforward method to overcome this problem. We first show on two widely used datasets (MNIST, SVHN) that when the norm of the gradient of one group is more important than the other during the discriminator’s training, the generator favors sampling data from one group more than the other at test time. We then show that controlling the groups’ gradient norm by performing group-wise gradient norm clipping in the discriminator during the training leads to a more fair data generation in terms of representational fairness compared to existing models while preserving the quality of generated samples. © 2022, CC BY.

关键词： Generative adversarial networks

What augmentations are sensitive to hyper-parameters and why?

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Muhammad, Awais Ch Ibrahim, BEKKOUCH Imad Eddine Machine Learning and Knowledge Representation Lab Innopolis University Innopolis Russia Sorbonne Center for Artificial Intelligence - SCAI Sorbonne University Paris France

We apply augmentations to our dataset to enhance the quality of our predictions and make our final models more resilient to noisy data and domain drifts. Yet the question remains, how are these augmentations going to perform with different hyper-parameters? In this study we evaluate the sensitivity of augmentations with regards to the model’s hyper parameters along with their consistency and influence by performing a Local Surrogate (LIME) interpretation on the impact of hyperparameters when different augmentations are applied to a machine learning model. We have utilized Linear regression coefficients for weighing each augmentation. Our research has proved that there are some augmentations which are highly sensitive to hyper-parameters and others which are more resilient and reliable. Copyright © 2021, The Authors. All rights reserved.

关键词： Lime

VAE-GAN based zero-shot outlier detection 4

学校读者我要写书评

暂无评论

VAE-GAN based zero-shot outlier detection

4th International Symposium on Computer Science and Intelligent Control, ISCSIC 2020

作者： Ibrahim, Bekkouch Imad Nicolae, Dragos Constantin Khan, Adil Ali, Syed Imran Khattak, Asad Machine Learning and Knowledge Representation Lab Institute of Data Science and AI Innopolis Tatarstan Russia Institutul de Cercetari Pentru Inteligenta Artificiala Mihai Draganescu Romania Department of Computer Engineering Kyung Hee University Yongin-si Korea Republic of College of Technological Innovations Zayed University Abu Dhabi United Arab Emirates

ISBN: (纸本)9781450388894

Outlier detection is one of the main fields in machine learning and it has been growing rapidly due to its wide range of applications. In the last few years, deep learning-based methods have outperformed machine learning and handcrafted outlier detection techniques, and our method is no different. We present a new twist to generative models which leverages variational autoencoders as a source for uniform distributions which can be used to separate the inliers from the outliers. Both the generative and adversarial parts of the model are used to obtain three main losses (Reconstruction loss, KL-divergence, Discriminative loss) which in return are wrapped with a one-class SVM which is used to make the predictions. We evaluated our method against several datasets both for images and tabular data and it has shown great results for the zero-shot outlier detection problem and was able to easily generalize it for supervised outlier detection tasks on which the performance has increased. For comparison, we evaluated our method against several of the common outlier detection techniques such as DBSCAN-based outlier detection, GMM, K-means and one class SVM directly, and we have outperformed all of them on all datasets. © 2020 ACM.

关键词： Anomaly detection