Match!
arXiv: Learning
Papers
8733
Papers 14206
1 page of 1,421 pages (14.2k results)
Newest
Published on Jan 1, 2018in arXiv: Learning
Prasad Cheema3
Estimated H-index: 3
,
Mehrisadat Makki Alamdari8
Estimated H-index: 8
,
Gareth A. Vio10
Estimated H-index: 10
In many contexts the modal properties of a structure change, either due to the impact of a changing environment, fatigue, or due to the presence of structural damage. For example during flight, an aircraft’s modal properties are known to change with both altitude and velocity. It is thus important to quantify these changes given only a truncated set of modal data, which is usually the case experimentally. This procedure is formally known as the generalised inverse eigenvalue problem. In this pap...
Published on 2020in arXiv: Learning
Rahul Vashisht (IIST: Indian Institute of Space Science and Technology), H. Viji (VSSC: Vikram Sarabhai Space Centre)+ 2 AuthorsS. Sumitra (IIST: Indian Institute of Space Science and Technology)
The advancement of machine learning algorithms has opened a wide scope for vibration-based Structural Health Monitoring (SHM). Vibration-based SHM is based on the fact that damage will alter the dynamic properties, viz., structural response, frequencies, mode shapes, etc. of the structure. The responses measured using sensors, which are high dimensional in nature, can be intelligently analysed using machine learning techniques for damage assessment. Neural networks employing multilayer architect...
Published on Jul 23, 2019in arXiv: Learning
Angelica I. Aviles-Rivero1
Estimated H-index: 1
(University of Cambridge),
Nicolas Papadakis (University of Cambridge)+ 4 AuthorsCarola-Bibiane Schönlieb (Yale University)
The task of classifying X-ray data is a problem of both theoretical and clinical interest. Whilst supervised deep learning methods rely upon huge amounts of labelled data, the critical problem of achieving a good classification accuracy when an extremely small amount of labelled data is available has yet to be tackled. In this work, we introduce a novel semi-supervised framework for X-ray classification which is based on a graph-based optimisation model. To the best of our knowledge, this is the...
Published on 2019in arXiv: Learning
Andrey Sapegin4
Estimated H-index: 4
,
Christoph Meinel36
Estimated H-index: 36
Nowadays processing of Big Security Data, such as log messages, is commonly used for intrusion detection purposed. Its heterogeneous nature, as well as combination of numerical and categorical attributes does not allow to apply the existing data mining methods directly on the data without feature preprocessing. Therefore, a rather computationally expensive conversion of categorical attributes into vector space should be utilised for analysis of such data. However, a well-known k-modes algorithm ...
Published on 2019in arXiv: Learning
Thodoris Lykouris7
Estimated H-index: 7
(Cornell University),
Éva Tardos59
Estimated H-index: 59
(Cornell University),
Drishti Wali (Cornell University)
We study the stochastic multi-armed bandit problem with the graph-based feedback structure introduced by Mannor and Shamir. We analyze the performance of the two most prominent stochastic bandit algorithms, Thompson Sampling and Upper Confidence Bound (UCB), in the graph-based feedback setting. We show that these algorithms achieve regret guarantees that combine the graph structure and the gaps between the means of the arm distributions. Surprisingly this holds despite the fact that these algori...
Published on 2019in arXiv: Learning
Laura Rieger1
Estimated H-index: 1
(DTU: Technical University of Denmark),
Chandan Singh12
Estimated H-index: 12
(University of California, Berkeley)
+ 1 AuthorsBin Yu49
Estimated H-index: 49
(University of California, Berkeley)
For an explanation of a deep learning model to be effective, it must provide both insight into a model and suggest a corresponding action in order to achieve some objective. Too often, the litany of proposed explainable deep learning methods stop at the first step, providing practitioners with insight into a model, but no way to act on it. In this paper, we propose contextual decomposition explanation penalization (CDEP), a method which enables practitioners to leverage existing explanation meth...
Published on 2019in arXiv: Learning
Ben Mussay , Margarita Osadchy10
Estimated H-index: 10
+ 2 AuthorsDan Feldman15
Estimated H-index: 15
Previous work showed empirically that large neural networks can be significantly reduced in size while preserving their accuracy. Model compression became a central research topic, as it is crucial for deployment of neural networks on devices with limited computational and memory resources. The majority of the compression methods are based on heuristics and offer no worst-case guarantees on the trade-off between the compression rate and the approximation error for an arbitrarily new sample. We p...
Published on 2019in arXiv: Learning
Juho Lee4
Estimated H-index: 4
,
Yoonho Lee2
Estimated H-index: 2
,
Yee Whye Teh44
Estimated H-index: 44
(University of Oxford)
We propose a deep amortized clustering (DAC), a neural architecture which learns to cluster datasets efficiently using a few forward passes. DAC implicitly learns what makes a cluster, how to group data points into clusters, and how to count the number of clusters in datasets. DAC is meta-learned using labelled datasets for training, a process distinct from traditional clustering algorithms which usually require hand-specified prior knowledge about cluster shapes/structures. We empirically show,...
Published on 2019in arXiv: Learning
Linxi Fan3
Estimated H-index: 3
,
Yuke Zhu14
Estimated H-index: 14
+ 6 AuthorsFei-Fei Li
We present an overview of SURREAL-System, a reproducible, flexible, and scalable framework for distributed reinforcement learning (RL). The framework consists of a stack of four layers: Provisioner, Orchestrator, Protocol, and Algorithms. The Provisioner abstracts away the machine hardware and node pools across different cloud providers. The Orchestrator provides a unified interface for scheduling and deploying distributed algorithms by high-level description, which is capable of deploying to a ...
Published on 2019in arXiv: Learning
Rohan Chitnis1
Estimated H-index: 1
,
Tomás Lozano-Pérez42
Estimated H-index: 42
(MIT: Massachusetts Institute of Technology)
We address the problem of approximate model minimization for MDPs in which the state is partitioned into endogenous and (much larger) exogenous components. An exogenous state variable is one whose dynamics are independent of the agent's actions. We formalize the mask-learning problem, in which the agent must choose a subset of exogenous state variables to reason about when planning; doing planning in such a reduced state space can often be significantly more efficient than planning in the full m...
12345678910