检索结果-内蒙古大学图书馆

A Neuro-Symbolic Approach for Marine Vessels Power Prediction Under Distribution Shifts

学校读者我要写书评

暂无评论

A Neuro-Symbolic Approach for Marine Vessels Power Predictio...

2023 IEEE Jordan International Joint Conference on Electrical Engineering and Information Technology, JEEIT 2023

作者： Hammoudeh, Ahmad Ghannam, Ibrahim Mubarak, Hamza Jean, Emmanuael Vandenbulcke, Virginie Dupont, Stephane MAiA Lab ISlA Lab Umons Trail Belgium RWTH Aachen University Electrical Engineering Germany Griffith University Engineering and Built Environment Australia Machine Learning & Signal Processing Multitel Trail Belgium Umons Isia Lab Belgium Umons Maia Lab Belgium

ISBN: (纸本)9798350324051

This paper proposes a neuro-symbolic approach to predict the power of marine cargo vessels. The neuro-symbolic approach combines two parts. The first is a neural networks part, and the second is a symbolic part that relies on physics-based formulae. The Shifts-power dataset was used for evaluation. The experimental results showed that a combination of a physics-based module (symbolic part) with a neural networks model (namely ensemble Monte Carlo dropout) superseded the state-of-the-art results by 2.3% in terms of uncertainty estimation measured using R-AUC, and by 3.4% in terms of power prediction for out-of-distribution (OOD) examples measured using RMSE. It also superseded the symbolic approach by 6.3% in terms of uncertainty and 17.7% in terms of OOD power prediction. © 2023 IEEE.

关键词： Neural network models

Revealing Emotional Clusters in Speaker Embeddings: A Contrastive learning Strategy for Speech Emotion Recognition

学校读者我要写书评

暂无评论

Revealing Emotional Clusters in Speaker Embeddings: A Contra...

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Ismail Rasim Ulgen Zongyang Du Carlos Busso Berrak Sisman Speech & Machine Learning (SML) Lab The University of Texas at Dallas USA Multimodal Signal Processing (MSP) Lab The University of Texas at Dallas USA

Speaker embeddings carry valuable emotion-related information, which makes them a promising resource for enhancing speech emotion recognition (SER), especially with limited lab.led data. Traditionally, it has been assumed that emotion information is indirectly embedded within speaker embeddings, leading to their under-utilization. Our study reveals a direct and useful link between emotion and state-of-the-art speaker embeddings in the form of intra-speaker clusters. By conducting a thorough clustering analysis, we demonstrate that emotion information can be readily extracted from speaker embeddings. In order to leverage this information, we introduce a novel contrastive pretraining approach applied to emotion-unlab.led data for speech emotion recognition. The proposed approach involves the sampling of positive and the negative examples based on the intra-speaker clusters of speaker embeddings. The proposed strategy, which leverages extensive emotion-unlab.led data, leads to a significant improvement in SER performance, whether employed as a standalone pretraining task or integrated into a multi-task pretraining setting.

关键词：

TurkishMMLU: Measuring Massive Multitask Language Understanding in Turkish

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Yüksel, Arda Köksal, Abdullatif Senel, Lütfi Kerem Korhonen, Anna Schütze, Hinrich Technical University of Munich Germany Center for Information and Language Processing LMU Munich Germany Munich Center for Machine Learning Germany Language Technology Lab. University of Cambridge United Kingdom

Multiple choice question answering tasks evaluate the reasoning, comprehension, and mathematical abilities of Large Language Models (LLMs). While existing benchmarks employ automatic translation for multilingual evaluation, this approach is error-prone and potentially introduces culturally biased questions, especially in social sciences. We introduce the first multitask, multiple-choice Turkish QA benchmark, TurkishMMLU, to evaluate LLMs’ understanding of the Turkish language. TurkishMMLU includes over 10,000 questions, covering 9 different subjects from Turkish high-school education curricula. These questions are written by curriculum experts, suitable for the high-school curricula in Turkey, covering subjects ranging from natural sciences and math questions to more culturally representative topics such as Turkish Literature and the history of the Turkish Republic. We evaluate over 20 LLMs, including multilingual open-source (e.g., Gemma, Llama, MT5), closed-source (GPT 4o, Claude, Gemini), and Turkish-adapted (e.g., Trendyol) models. We provide an extensive evaluation, including zero-shot and few-shot evaluation of LLMs, chain-of-thought reasoning, and question difficulty analysis along with model performance. We provide an in-depth analysis of the Turkish capabilities and limitations of current LLMs to provide insights for future LLMs for the Turkish language. We publicly release our code for the dataset and evaluation: https://***/ArdaYueksel/TurkishMMLU. Copyright © 2024, The Authors. All rights reserved.

关键词： Curricula

On the Robustness of Out-of-Distribution Detection Methods for Camera-based Systems

学校读者我要写书评

暂无评论

On the Robustness of Out-of-Distribution Detection Methods f...

Asilomar Conference on signals, Systems & Computers

作者： Christian Huber Bernhard Lehner Claus Hofmann Bernhard Moser Reinhard Feger Silicon Austria Labs GmbH JKU LIT SAL eSPML Lab Austria JKU LIT SAL eSPML Lab Johannes Kepler University Linz Austria Institute for Machine Learning Institute of Signal Processing Institute for Communications Engineering and RF-Systems

ISBN: (数字)9798350354058

ISBN: (纸本)9798350354065

关键词： Image sensors Degradation Training Sensitivity Prevention and mitigation machine learning Benchmark testing Robustness Safety Autonomous vehicles

A Neuro-Symbolic Approach for Marine Vessels Power Prediction Under Distribution Shifts

学校读者我要写书评

暂无评论

A Neuro-Symbolic Approach for Marine Vessels Power Predictio...

IEEE Jordan International Joint Conference on Electrical Engineering and Information Technology (JEEIT)

作者： Ahmad Hammoudeh Ibrahim Ghannam Hamza Mubarak Emmanuael Jean Virginie Vandenbulcke Stephane Dupont MAiA Lab ISlA Lab UMONS TRAIL Belgium Electrical Engineering RWTH Aachen University Germany Engineering and Built Environment Griffith University Australia Machine Learning & Signal Processing Multitel TRAIL Belgium ISIA Lab UMONS Belgium MAIA Lab UMONS Belgium

关键词：

learning Fair Representations through Uniformly Distributed Sensitive Attributes

学校读者我要写书评

暂无评论

Learning Fair Representations through Uniformly Distributed ...

Secure and Trustworthy machine learning (SaTML), IEEE Conference on

作者： Patrik Joslin Kenfack Adín Ramírez Rivera Adil Mehmood Khan Manuel Mazzara Machine Learning and Knowledge Representation Lab Innopolis University Innopolis Russia Department of Informatics Digital Signal Processing and Image Analysis (DSB) group University of Oslo Oslo Norway School of Computer Science University of Hull Hull UK Institute of Software Development and Engineering Innopolis University Innopolis Russia

machine learning (ML) models trained on biased data can reproduce and even amplify these biases. Since such models are deployed to make decisions that can affect people's lives, ensuring their fairness is critical. One approach to mitigate possible unfairness of ML models is to map the input data into a less-biased new space by means of training the model on fair representations. Several methods based on adversarial learning have been proposed to learn fair representation by fooling an adversary in predicting the sensitive attribute (e.g., gender or race). However, adversarial-based learning can be too difficult to optimize in practice; besides, it penalizes the utility of the representation. Hence, in this research effort we train bias-free representations from the input data by inducing a uniform distribution over the sensitive attributes in the latent space. In particular, we propose a probabilistic framework that learns these representations by enforcing the correct reconstruction of the original data, plus the prediction of the attributes of interest while eliminating the possibility of predicting the sensitive ones. Our method leverages the inability of Deep Neural Networks (DNNs) to generalize when trained on a noisy lab.l space to regularize the latent space. We use a network head that predicts a noisy version of the sensitive attributes in order to increase the uncertainty of their predictions at test time. Our experiments in two datasets demonstrated that the proposed model significantly improves fairness while maintaining the prediction accuracy of downstream tasks.

关键词：

Unsupervised Anomaly Detection in Medical Images with a Memory-augmented Multi-level Cross-attentional Masked Autoencoder

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Tian, Yu Pang, Guansong Liu, Yuyuan Wang, Chong Chen, Yuanhong Liu, Fengbei Singh, Rajvinder Verjans, Johan W. Wang, Mengyu Carneiro, Gustavo Harvard Ophthalmology AI Lab Harvard University United States Australian Institute for Machine Learning University of Adelaide Australia Faculty of Health and Medical Sciences University of Adelaide Australia South Australian Health and Medical Research Institute Australia Singapore Management University Singapore Centre for Vision Speech and Signal Processing University of Surrey United Kingdom

Unsupervised anomaly detection (UAD) aims to find anomalous images by optimising a detector using a training set that contains only normal images. UAD approaches can be based on reconstruction methods, self-supervised approaches, and Imagenet pre-trained models. Reconstruction methods, which detect anomalies from image reconstruction errors, are advantageous because they do not rely on the design of problem-specific pretext tasks needed by self-supervised approaches, and on the unreliable translation of models pre-trained from non-medical datasets. However, reconstruction methods may fail because they can have low reconstruction errors even for anomalous images. In this paper, we introduce a new reconstruction-based UAD approach that addresses this low-reconstruction error issue for anomalous images. Our UAD approach, the memory-augmented multi-level cross-attentional masked autoencoder (MemMC-MAE), is a transformer-based approach, consisting of a novel memory-augmented self-attention operator for the encoder and a new multi-level cross-attention operator for the decoder. MemMC-MAE masks large parts of the input image during its reconstruction, reducing the risk that it will produce low reconstruction errors because anomalies are likely to be masked and cannot be reconstructed. However, when the anomaly is not masked, then the normal patterns stored in the encoder's memory combined with the decoder's multi-level cross-attention will constrain the accurate reconstruction of the anomaly. We show that our method achieves SOTA anomaly detection and localisation on colonoscopy, pneumonia, and covid-19 chest x-ray datasets. Copyright © 2022, The Authors. All rights reserved.

关键词： Anomaly detection

Adversarial learning with Cost-Sensitive Classes

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Shen, Haojing Chen, Sihong Wang, Ran Wang, Xizhao Big Data Institute College of Computer Science and Software Engineering Guangdong Key Lab. of Intelligent Information Processing Shenzhen University Guangdong Shenzhen518060 China The College of Mathematics and Statistics Shenzhen University Shenzhen518060 China The Shenzhen Key Laboratory of Advanced Machine Learning and Applications Shenzhen University Shenzhen518060 China

It is necessary to improve the performance of some special classes or to particularly protect them from attacks in adversarial learning. This paper proposes a framework combining cost-sensitive classification and adversarial learning together to train a model that can distinguish between protected and unprotected classes, such that the protected classes are less vulnerable to adversarial examples. We find in this framework an interesting phenomenon during the training of deep neural networks, called Min-Max property, that is, the absolute values of most parameters in the convolutional layer approach zero while the absolute values of a few parameters are significantly larger becoming bigger. Based on this Min-Max property which is formulated and analyzed in a view of random distribution, we further build a new defense model against adversarial examples for adversarial robustness improvement. An advantage of the built model is that it performs better than the standard one and can combine with adversarial training to achieve an improved performance. It is experimentally confirmed that, regarding the average accuracy of all classes, our model is almost as same as the existing models when an attack does not occur and is better than the existing models when an attack occurs. Specifically, regarding the accuracy of protected classes, the proposed model is much better than the existing models when an attack occurs. © 2021, CC BY.

关键词： Deep neural networks

ScanMix: learning from Severe lab.l Noise via Semantic Clustering and Semi-Supervised learning

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Sachdeva, Ragav Cordeiro, Filipe Rolim Belagiannis, Vasileios Reid, Ian Carneiro, Gustavo Visual Geometry Group Department of Engineering Science University of Oxford United Kingdom School of Computer Science Australian Institute for Machine Learning Australia Visual Computing Lab Department of Computing Universidade Federal Rural de Pernambuco Brazil Otto-von-Guericke-Universität Magdeburg Germany Centre for Vision Speech and Signal Processing University of Surrey United Kingdom

We propose a new training algorithm, ScanMix, that explores semantic clustering and semi-supervised learning (SSL) to allow superior robustness to severe lab.l noise and competitive robustness to non-severe lab.l noise problems, in comparison to the state of the art (SOTA) methods. ScanMix is based on the expectation maximisation framework, where the E-step estimates the latent variable to cluster the training images based on their appearance and classification results, and the M-step optimises the SSL classification and learns effective feature representations via semantic clustering. We present a theoretical result that shows the correctness and convergence of ScanMix, and an empirical result that shows that ScanMix has SOTA results on CIFAR-10/-100 (with symmetric, asymmetric and semantic lab.l noise), Red Mini-ImageNet (from the Controlled Noisy Web lab.ls), Clothing1M and WebVision. In all benchmarks with severe lab.l noise, our results are competitive to the current SOTA. © 2021, CC BY.

关键词： Semantics