检索结果-内蒙古大学图书馆

Towards gene expression convolutions using gene interaction graphs

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Dutil, Francis Cohen, Joseph Paul Weiss, Martin Derevyanko, Georgy Bengio, Yoshua Montreal Institute for Learning Algorithms Universite of Montreal Concordia University

We study the challenges of applying deep learning to gene expression data. We find experimentally that there exists non-linear signal in the data, however is it not discovered automatically given the noise and low numbers of samples used in most research. We discuss how gene interaction graphs (same pathway, protein-protein, co-expression, or research paper text association) can be used to impose a bias on a deep model similar to the spatial bias imposed by convolutions on an image. We explore the usage of Graph Convolutional Neural Networks coupled with dropout and gene embeddings to utilize the graph information. We find this approach provides an advantage for particular tasks in a low data regime but is very dependent on the quality of the graph used. We conclude that more work should be done in this direction. We design experiments that show why existing methods fail to capture signal that is present in the data when features are added which clearly isolates the problem that needs to be addressed. Copyright © 2018, The Authors. All rights reserved.

关键词： Convolution

Diet networks: Thin parameters for fat genomics 5

学校读者我要写书评

暂无评论

Diet networks: Thin parameters for fat genomics

5th International Conference on learning Representations, ICLR 2017

作者： Romero, Adriana Carrier, Pierre Luc Erraqabi, Akram Sylvain, Tristan Auvolat, Alex Dejoie, Etienne Legault, Marc-André Dubé, Marie-Pierre Hussin, Julie G. Bengio, Yoshua Montreal Institute for Learning Algorithms Montreal QC Canada University of Montreal Faculty of Medicine Canada Montreal Heart Institute Canada Beaulieu-Saucier Pharmacogenomics Centre MontrealQC Canada Wellcome Trust Centre for Human Genetics University of Oxford Oxford United Kingdom

learning tasks such as those involving genomic data often poses a serious challenge: the number of input features can be orders of magnitude larger than the number of training examples, making it difficult to avoid overfitting, even when using the known regularization techniques. We focus here on tasks in which the input is a description of the genetic variation specific to a patient, the single nucleotide polymorphisms (SNPs), yielding millions of ternary inputs. Improving the ability of deep learning to handle such datasets could have an important impact in medical research, more specifically in precision medicine, where high-dimensional data regarding a particular patient is used to make predictions of interest. Even though the amount of data for such tasks is increasing, this mismatch between the number of examples and the number of inputs remains a concern. Naive implementations of classifier neural networks involve a huge number of free parameters in their first layer (number of input features times number of hidden units): each input feature is associated with as many parameters as there are hidden units. We propose a novel neural network parametrization which considerably reduces the number of free parameters. It is based on the idea that we can first learn or provide a distributed representation for each input feature (e.g. for each position in the genome where variations are observed in data), and then learn (with another neural network called the parameter prediction network) how to map a feature's distributed representation (based on the feature's identity not its value) to the vector of parameters specific to that feature in the classifier neural network (the weights which link the value of the feature to each of the hidden units). This approach views the problem of producing the parameters associated with each feature as a multi-task learning problem. We show experimentally on a population stratification task of interest to medical studies that the pro

关键词： Genes

The One Hundred Layers Tiramisu: Fully Convolutional DenseNets for Semantic Segmentation

学校读者我要写书评

暂无评论

The One Hundred Layers Tiramisu: Fully Convolutional DenseNe...

IEEE Conference on Computer Vision and Pattern Recognition Workshops

作者： Simon Jegou Michal Drozdzal David Vazquez Adriana Romero Yoshua Bengio Montreal Institute for Learning Algorithms Ecole Polytechnique de Montreal

ISBN: (纸本)9781538607343

State-of-the-art approaches for semantic image segmentation are built on Convolutional Neural Networks (CNNs). The typical segmentation architecture is composed of (a) a downsampling path responsible for extracting coarse semantic features, followed by (b) an upsampling path trained to recover the input image resolution at the output of the model and, optionally, (c) a post-processing module (e.g. Conditional Random Fields) to refine the model predictions. Recently, a new CNN architecture, Densely Connected Convolutional Networks (DenseNets), has shown excellent results on image classification tasks. The idea of DenseNets is based on the observation that if each layer is directly connected to every other layer in a feed-forward fashion then the network will be more accurate and easier to train. In this paper, we extend DenseNets to deal with the problem of semantic segmentation. We achieve state-of-the-art results on urban scene benchmark datasets such as CamVid and Gatech, without any further post-processing module nor pretraining. Moreover, due to smart construction of the model, our approach has much less parameters than currently published best entries for these datasets. Code to reproduce the experiments is publicly available here: .

关键词： image segmentation Semantics Dataset segmentation Segmentation Arts

Practical applications of sparse modeling /

学校读者我要写书评

暂无评论

Practical applications of sparse modeling /

丛书名： Neural information processing series

2014年

作者： Irina Rish Guillermo A Cecchi Aurélie Chloe Lozano Alexandru Niculescu-Mizil

ISBN: (纸本)9780262027724

Sparse modeling is a rapidly developing area at the intersection of statistical learning and signal processing, motivated by the age-old statistical problem of selecting a small number of predictive variables in high-dimensional datasets. This collection describes key approaches in sparse modeling, focusing on its applications in fields including neuroscience, computational biology, and computer vision. Sparse modeling methods can improve the interpretability of predictive models and aid efficient recovery of high-dimensional unobserved signals from a limited number of measurements. Yet despite significant advances in the field, a number of open issues remain when sparse modeling meets real-life applications. The book discusses a range of practical applications and state-of-the-art approaches for tackling the challenges presented by these applications. Topics considered include the choice of method in genomics applications; analysis of protein mass-spectrometry data; the stability of sparse models in brain imaging applications; sequential testing approaches; algorithmic aspects of sparse recovery; and learning sparse latent ***. Vania Apkarian, Marwan Baliki, Melissa K. Carroll, Guillermo A. Cecchi, Volkan Cevher, Xi Chen, Nathan W. Churchill, Rmi Emonet, Rahul Garg, Zoubin Ghahramani, Lars Kai Hansen, Matthias Hein, Katherine Heller, Sina Jafarpour, Seyoung Kim, Mladen Kolar, Anastasios Kyrillidis, Aurelie Lozano, Matthew L. Malloy, Pablo Meyer, Shakir Mohamed, Alexandru Niculescu-Mizil, Robert D. Nowak, Jean-Marc Odobez, Peter M. Rasmussen, Irina Rish, Saharon Rosset, Martin Slawski, Stephen C. Strother, Jagannadan Varadarajan, Eric P. Xing

关键词： Mathematical models. Sampling (Statistics) Data reduction. Sparse matrices

MovieGraphs: Towards understanding human-centric situations from videos

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Vicol, Paul Tapaswi, Makarand Castrejón, Lluís Fidler, Sanja University of Toronto Vector Institute Montreal Institute for Learning Algorithms

There is growing interest in artificial intelligence to build socially intelligent robots. This requires machines to have the ability to "read" people's emotions, motivations, and other factors that affect behavior. Towards this goal, we introduce a novel dataset called MovieGraphs which provides detailed, graph-based annotations of social situations depicted in movie clips. Each graph consists of several types of nodes, to capture who is present in the clip, their emotional and physical attributes, their relationships (i.e., parent/child), and the interactions between them. Most interactions are associated with topics that provide additional details, and reasons that give motivations for actions. In addition, most interactions and many attributes are grounded in the video with time stamps. We provide a thorough analysis of our dataset, showing interesting common-sense correlations between different social aspects of scenes, as well as across scenes over time. We propose a method for querying videos and text with graphs, and show that: 1) our graphs contain rich and sufficient information to summarize and localize each scene;and 2) subgraphs allow us to describe situations at an abstract level and retrieve multiple semantically relevant situations. We also propose methods for interaction understanding via ordering, and reason understanding. MovieGraphs is the first benchmark to focus on inferred properties of human-centric situations, and opens up an exciting avenue towards socially-intelligent AI agents. Copyright © 2017, The Authors. All rights reserved.

关键词： Graphic methods

Discovering Concepts in Learned Representations using Statistical Inference and Interactive Visualization

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Janik, Adrianna Sankaran, Kris Montreal Institute for Learning Algorithms MontréalQC Canada

Concept discovery is one of the open problems in the interpretability literature that is important for bridging the gap between non-deep learning experts and model end-users. Among current formulations, concepts defines them by as a direction in a learned representation space. This definition makes it possible to evaluate whether a particular concept significantly influences classification decisions for classes of interest. However, finding relevant concepts is tedious, as representation spaces are high-dimensional and hard to navigate. Current approaches include hand-crafting concept datasets and then converting them to latent space directions;alternatively, the process can be automated by clustering the latent space. In this study, we offer another two approaches to guide user discovery of meaningful concepts, one based on multiple hypothesis testing, and another on interactive visualization. We explore the potential value and limitations of these approaches through simulation experiments and an demo visual interface to real data. Overall, we find that these techniques offer a promising strategy for discovering relevant concepts in settings where users do not have predefined descriptions of them, but without completely automating the process. Copyright © 2022, The Authors. All rights reserved.

关键词： Visualization

Personalizing dialogue agents: I have a dog, do you have pets too?

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Zhang, Saizheng Dinan, Emily Urbanek, Jack Szlam, Arthur Kiela, Douwe Weston, Jason Montreal Institute for Learning Algorithms MILA Facebook AI Research

Chit-chat models are known to have several problems: they lack specificity, do not display a consistent personality and are often not very captivating. In this work we present the task of making chit-chat more engaging by conditioning on profile information. We collect data and train models to (i) condition on their given profile information;and (ii) information about the person they are talking to, resulting in improved dialogues, as measured by next utterance prediction. Since (ii) is initially unknown, our model is trained to engage its partner with personal topics, and we show the resulting dialogue can be used to predict profile information about the interlocutors. Copyright © 2018, The Authors. All rights reserved.

关键词：

A3T: Adversarially augmented adversarial training

学校读者我要写书评

暂无评论

arXiv 2018年

作者： Erraqabi, Akram Baratin, Aristide Bengio, Yoshua Lacoste-Julien, Simon Montreal Institute of Learning Algorithms Université de Montréal Montreal Canada

Recent research showed that deep neural networks are highly sensitive to so-called adversarial perturbations, which are tiny perturbations of the input data purposely designed to fool a machine learning classifier. In this work, we investigate a procedure to improve adversarial robustness of deep neural networks through enforcing representation invariance. The idea is to train the classifier jointly with a discriminator attached to one of its hidden layer and trained to filter the adversarial noise. We perform preliminary experiments to test the viability of the approach and to compare it to other standard adversarial training methods. Copyright © 2018, The Authors. All rights reserved.

关键词： Deep neural networks

A Risk-Averse Framework for Non-Stationary Stochastic Multi-Armed Bandits

学校读者我要写书评

暂无评论

A Risk-Averse Framework for Non-Stationary Stochastic Multi-...

IEEE International Conference on Data Mining Workshops (ICDM Workshops)

作者： Reda Alami Mohammed Mahfoud Mastane Achab Technology Innovation Institute Masdar City UAE Montreal Institute of Learning Algorithms Montreal Canada

In a typical stochastic multi-armed bandit problem, the objective is often to maximize the expected sum of rewards over some time horizon T. While the choice of a strategy that accomplishes that is optimal with no additional information, it is no longer the case when provided additional environment-specific knowledge. In particular, in areas of high volatility like healthcare or finance, a naive reward maximization approach often does not accurately capture the complexity of the learning problem and results in unreliable solutions. To tackle problems of this nature, we propose a framework of adaptive risk-aware strategies that operate in non-stationary environments. Our framework incorporates various risk measures prevalent in the literature to map multiple families of multi-armed bandit algorithms into a risk-sensitive setting. In addition, we equip the resulting algorithms with the Restarted Bayesian Online Change-Point Detection (R-BOCPD) algorithm and impose a (tunable) forced exploration strategy to detect local (per-arm) switches. We provide finite-time theoretical guarantees and an asymptotic regret bound of $\widetilde {\mathcal{O}}\left( {\sqrt {{K_T}T} } \right)$ up to time horizon T with K T the total number of change-points. In practice, our framework compares favorably to the state-of-the-art in both synthetic and real-world environments and manages to perform efficiently with respect to both risk-sensitivity and non-stationarity.

关键词：