检索结果-内蒙古大学图书馆

Sparse Modeling: Theory, algorithms, and Applications 1

丛书名： Chapman & Hall/CRC Machine learning & Pattern Recognition

2014年

作者： Rish, Irina Grabarnik, Genady

ISBN: (数字)9781439828700

ISBN: (纸本)9781439828694

Sparse models are particularly useful in scientific applications, such as biomarker discovery in genetic or neuroimaging data, where the interpretability of a predictive model is essential. Sparsity can also dramatically improve the cost efficiency of signal *** Modeling: Theory, algorithms, and Applications provides an introduction t

关键词： Computer Science

来源：评论

学校读者我要写书评

暂无评论

Interpreting Black-Box Semantic Segmentation Models in Remote Sensing Applications 2

Interpreting Black-Box Semantic Segmentation Models in Remot...

引用

2nd Workshop on Machine learning Methods in Visualisation for Big Data, MLVis 2019

作者： Janik, A. Sankaran, K. Ortiz, A. Montreal Institute of Learning Algorithms University of Texas - El Paso

ISBN: (纸本)9783038680895

In the interpretability literature, attention is focused on understanding black-box classifiers, but many problems ranging from medicine through agriculture and crisis response in humanitarian aid are tackled by semantic segmentation models. The absence of interpretability for these canonical problems in computer vision motivates this study. In this study we present a usercentric approach that blends techniques from interpretability, representation learning, and interactive visualization. It allows to visualize and link latent representation to real data instances as well as qualitatively assess strength of predictions. We have applied our method to a deep learning model for semantic segmentation, U-Net, in a remote sensing application of building detection. This application is of high interest for humanitarian crisis response teams that rely on satellite images analysis. Preliminary results shows utility in understanding semantic segmentation models, demo presenting the idea is available online. Copyright © 2019 by the Eurographics Association.

关键词： Visualization

来源：评论

学校读者我要写书评

暂无评论

Machine learning and Interpretation in Neuroimaging 2012

引用

丛书名： Lecture Notes in Computer Science

2012年

作者： Georg Langs Irina Rish Moritz Grosse-Wentrup Brian Murphy

ISBN: (数字)9783642347139

ISBN: (纸本)9783642347122

Brain imaging brings together the technology, methodology, research questions and approaches of a wide range of scientific fields including physics, statistics, computer science, neuroscience, biology, and engineering. Thus, methodological and technological advances that enable us to obtain measurements, examine relationships across observations, and link these data to neuroscientific hypotheses happen in a highly interdisciplinary environment. The dynamic field of machine learning with its modern approach to data mining provides many relevant approaches for neuroscience and enables the exploration of open questions. This state-of-the-art survey offers a collection of papers from the Workshop on Machine learning and Interpretation in Neuroimaging, MLINI 2011, held at the 25th Annual Conference on Neural Information Processing, NIPS 2011, in the Sierra Nevada, Spain, in December 2011. Additionally, invited speakers agreed to contribute reviews on various aspects of the field, adding breadth and perspective to the volume. The 32 revised papers were carefully selected from 48 submissions. At the interface between machine learning and neuroimaging the papers aim at shedding some light on the state of the art in this interdisciplinary field. They are organized in topical sections on coding and decoding, neuroscience, dynamcis, connectivity, and probabilistic models and machine learning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine comprehension by text-to-text neural question generation 2

Machine comprehension by text-to-text neural question genera...

引用

2nd Workshop on Representation learning for NLP, Rep4NLP 2017 at the 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017

作者： Yuan, Xingdi Wang, Tong Gulcehre, Caglar Sordoni, Alessandro Bachman, Philip Subramanian, Sandeep Zhang, Saizheng Trischler, Adam Microsoft Maluuba Canada Montreal Institute for Learning Algorithms Université de Montréal Canada

ISBN: (纸本)9781945626623

We propose a recurrent neural model that generates natural-language questions from documents, conditioned on answers. We show how to train the model using a combination of supervised and reinforcement learning. After teacher forcing for standard maximum likelihood training, we fine-tune the model using policy gradient techniques to maximize several rewards that measure question quality. Most notably, one of these rewards is the performance of a question-answering system. We motivate question generation as a means to improve the performance of question answering systems. Our model is trained and evaluated on the recent question-answering dataset SQuAD. © 2017 Association for Computational Linguistics.

关键词： Maximum likelihood

来源：评论

学校读者我要写书评

暂无评论

An evaluation of Fisher approximations beyond Kronecker factorization 6

An evaluation of Fisher approximations beyond Kronecker fact...

引用

6th International Conference on learning Representations, ICLR 2018

作者： Laurent, César George, Thomas Bouthillier, Xavier Ballas, Nicolas Vincent, Pascal Montreal Institute for Learning Algorithms Université de Montréal Canada Facebook AI Research Canada

We study two coarser approximations on top of a Kronecker factorization (K-FAC) of the Fisher Information Matrix, to scale up Natural Gradient to deep and wide Convolutional Neural Networks (CNNs). The first considers the feature maps as spatially uncorrelated while the second considers only correlations among groups of channels. Both variants yield a further block-diagonal approximation tailored for CNNs, which is much more efficient to compute and invert. Experiments on the VGG11 and ResNet50 architectures show the technique can substantially speed up both K-FAC and a baseline with Batch Normalization in wall-clock time, yielding faster convergence to similar or better generalization error. © 6th International Conference on learning Representations, ICLR 2018 - Workshop Track Proceedings. All rights reserved.

关键词： Factorization

来源：评论

学校读者我要写书评

暂无评论

Improving generative adversarial networks with denoising feature matching 5

Improving generative adversarial networks with denoising fea...

引用

5th International Conference on learning Representations, ICLR 2017

作者： Warde-Farley, David Bengio, Yoshua Montreal Institute for Learning Algorithms Université de Montréal MontrealQC Canada CIFAR Université de Montréal MontrealQC Canada

We propose an augmented training procedure for generative adversarial networks designed to address shortcomings of the original by directing the generator towards probable configurations of abstract discriminator features. We estimate and track the distribution of these features, as computed from data, with a denoising auto-encoder, and use it to propose high-level targets for the generator. We combine this new loss with the original and evaluate the hybrid criterion on the task of unsupervised image synthesis from datasets comprising a diverse set of visual categories, noting a qualitative and quantitative improvement in the "objectness" of the resulting samples. © ICLR 2019 - Conference Track Proceedings. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Improved training of wasserstein GANs 17

Improved training of wasserstein GANs

引用

Proceedings of the 31st International Conference on Neural Information Processing Systems

作者： Ishaan Gulrajani Faruk Ahmed Martin Arjovsky Vincent Dumoulin Aaron Courville Montreal Institute for Learning Algorithms and Google Brain Montreal Institute for Learning Algorithms Courant Institute of Mathematical Sciences Montreal Institute for Learning Algorithms and CIFAR Fellow

ISBN: (纸本)9781510860964

Generative Adversarial Networks (GANs) are powerful generative models, but suffer from training instability. The recently proposed Wasserstein GAN (WGAN) makes progress toward stable training of GANs, but sometimes can still generate only poor samples or fail to converge. We find that these problems are often due to the use of weight clipping in WGAN to enforce a Lipschitz constraint on the critic, which can lead to undesired behavior. We propose an alternative to clipping weights: penalize the norm of gradient of the critic with respect to its input. Our proposed method performs better than standard WGAN and enables stable training of a wide variety of GAN architectures with almost no hyperparameter tuning, including 101-layer ResNets and language models with continuous generators. We also achieve high quality generations on CIFAR-10 and LSUN bedrooms.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Density estimation using real NVP 5

Density estimation using real NVP

引用

5th International Conference on learning Representations, ICLR 2017

作者： Dinh, Laurent Sohl-Dickstein, Jascha Bengio, Samy Montreal Institute for Learning Algorithms University of Montreal MontrealQCH3T1J4 Canada Google Brain United States

Unsupervised learning of probabilistic models is a central yet challenging problem in machine learning. Specifically, designing models with tractable learning, sampling, inference and evaluation is crucial in solving this task. We extend the space of such models using real-valued non-volume preserving (real NVP) transformations, a set of powerful, stably invertible, and learnable transformations, resulting in an unsupervised learning algorithm with exact log-likelihood computation, exact and efficient sampling, exact and efficient inference of latent variables, and an interpretable latent space. We demonstrate its ability to model natural images on four datasets through sampling, log-likelihood evaluation, and latent variable manipulations. © ICLR 2019 - Conference Track Proceedings. All rights reserved.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Towards an automatic turing test: learning to evaluate dialogue responses 5

Towards an automatic turing test: Learning to evaluate dialo...

引用

5th International Conference on learning Representations, ICLR 2017

作者： Lowe, Ryan Noseworthy, Michael Serban, Iulian V. Angelard-Gontier, Nicolas Bengio, Yoshua Pineau, Joelle Reasoning and Learning Lab School of Computer Science McGill University Canada Montreal Institute for Learning Algorithms Université de Montréal Canada CIFAR

Automatically evaluating the quality of dialogue responses for unstructured domains is a challenging problem. Unfortunately, existing automatic evaluation metrics are biased and correlate very poorly with human judgements of response quality (Liu et al., 2016). Yet having an accurate automatic evaluation procedure is crucial for dialogue research, as it allows rapid prototyping and testing of new models with fewer expensive human evaluations. In response to this challenge, we formulate automatic dialogue evaluation as a learning problem. We present an evaluation model (ADEM) that learns to predict human-like scores to input responses, using a new dataset of human response scores. We show that the ADEM model's predictions correlate significantly, and at level much higher than word-overlap metrics such as BLEU, with human judgements at both the utterance and system-level. We also show that ADEM can generalize to evaluating dialogue models unseen during training, an important step for automatic dialogue evaluation. © 5th International Conference on learning Representations, ICLR 2017 - Workshop Track Proceedings. All Rights Reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Distribution matching losses can hallucinate features in medical image translation

arXiv

引用

arXiv 2018年

作者： Cohen, Joseph Paul Luck, Margaux Honari, Sina Montreal Institute for Learning Algorithms University of Montreal

This paper discusses how distribution matching losses, such as those used in CycleGAN, when used to synthesize medical images can lead to mis-diagnosis of medical conditions. It seems appealing to use these new image synthesis methods for translating images from a source to a target domain because they can produce high quality images and some even do not require paired data. However, the basis of how these image translation models work is through matching the translation out-put to the distribution of the target domain. This can cause an issue when the data provided in the target domain has an over or under rep-resentation of some classes (e.g. healthy or sick). When the output of an algorithm is a transformed image there are uncertainties whether all known and unknown class labels have been preserved or changed. There-fore, we recommend that these translated images should not be used for direct interpretation (e.g. by doctors) because they may lead to misdiag-nosis of patients based on hallucinated image features by an algorithm that matches a distribution. However there are many recent papers that seem as though this is the goal. Copyright © 2018, The Authors. All rights reserved.

关键词： Diagnosis

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：