检索结果-内蒙古大学图书馆

39th International Computer Music Conference, ICMC 2013

作者： Deal, Scott Sanchez, Javier Indiana University Purdue University Department of Music and Arts Technology Indianapolis United States

ISBN: (纸本)9780984527427

This paper presents an implementation of a musical interface that utilizes machine learning (ML) attributes in real-time performance. The objective behind the work is to empower performers with an expanded musical palette. This is achieved by employing a variation on a delay effect implemented with neural networks. In this scenario, the delayed signal is an echo of previously performed motifs based on new inputs categorized by an ART (Adaptive Resonance Theory) neural network. An overview of the piece used to test the musical range of the effect will be given, followed by a description of the development rationale for the project. The paper will conclude with a qualitative evaluation of the usability and responsiveness of the effect, as well as its contribution to the aesthetic quality of the composition.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Relevance as a metric for evaluating machine learning algorithms

Relevance as a metric for evaluating machine learning algori...

引用

9th International Conference on International Conference on Machine learning and Data Mining, MLDM 2013

作者： Gopalakrishna, Aravind Kota Ozcelebi, Tanir Liotta, Antonio Lukkien, Johan J. Department of Mathematics and Computer Science Netherlands Electro-Optical Communications Department of Electrical Engineering Eindhoven University of Technology Netherlands

ISBN: (纸本)9783642397110

In machine learning, the choice of a learning algorithm that is suitable for the application domain is critical. The performance metric used to compare different algorithms must also reflect the concerns of users in the application domain under consideration. In this paper, we propose a novel probability-based performance metric called Relevance Score for evaluating supervised learning algorithms. We evaluate the proposed metric through empirical analysis on a dataset gathered from an intelligent lighting pilot installation. In comparison to the commonly used Classification Accuracy metric, the Relevance Score proves to be more appropriate for a certain class of applications. © 2013 Springer-Verlag.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Constructing hard functions using learning algorithms

Constructing hard functions using learning algorithms

引用

2013 IEEE Conference on Computational Complexity, CCC 2013

作者： Klivans, Adam Kothari, Pravesh Oliveira, Igor C. UT Austin United States Columbia University United States

ISBN: (纸本)9780769549972

Fort now and Klivans proved the following relationship between efficient learning algorithms and circuit lower bounds: if a class of boolean circuits C contained in P/poly of Boolean is exactly learnable with membership and equivalence queries in polynomial-time, then EXP^NP is not contained in C (the class EXP^NP was subsequently improved to EXP by Hitchcock and Harkins). In this paper, we improve on these results and show * If C is exactly learnable with membership and equivalence queries in polynomial-time, then DTIME(n^{\omega(1)}) is not contained in C. We obtain even stronger consequences if C is learnable in the mistake-bounded model, in which case we prove an average-case hardness result against C. * If C is learnable in polynomial time in the PAC model then PSPACE is not contained in C, unless PSPACE is contained in BPP. Removing this extra assumption from the statement of the theorem would provide an unconditional separation of PSPACE and BPP. * If C is efficiently learnable in the Correlational Statistical Query (CSQ) model, we show that there exists an explicit function f that is average-case hard for circuits in C. This result provides stronger average-case hardness guarantees than those obtained by SQ-dimension arguments (Blum et al. 1993). We also obtain a non-constructive extension of this result to the stronger Statistical Query (SQ) model. Similar results hold in the case where the learning algorithm runs in sub exponential time. Our proofs regarding exact and mistake-bounded learning are simple and self-contained, yield explicit hard functions, and show how to use mistake-bounded learners to 'diagonalize'' over families of polynomial-size circuits. Our consequences for PAC learning lead to new proofs of Karp-Lipton-style collapse results, and the lower bounds from SQ learning make use of recent work relating combinatorial discrepancy to the existence of hard-on-average functions. © 2013 IEEE.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Stability of the Nash equilibrium under gradient ascent learning algorithms in two-agent two-action games

Stability of the Nash equilibrium under gradient ascent lear...

引用

2013 IEEE International Conference on Control Applications, CCA 2013

作者： Bhaya, Amit De Macedo, Rodrigo Brandolt Sodré Shigueoka, Lucas Shiguemitsu Department of Electrical Engineering Federal University of Rio de Janeiro Rio de Janeiro Brazil

ISBN: (纸本)9781479915590

This paper provides a unified view and stability analysis of reinforcement learning algorithms for general sum games that have been proposed in the literature. Specifically, the gradient ascent learning algorithms proposed by Singh, Kearns and Mansour, and the variant proposed by Bowling and Veloso are shown to lead to convergence to the Nash equilibrium, using a switching control viewpoint and providing a unified Lyapunov function analysis. Furthermore, a proof of stability of the Nash equilibrium under the weighted policy learning (WPL) algorithm, which was proposed, without formal proof, by Abdallah and Lesser, is also arrived at using a Liapunov function approach and involves the novel feature of an analysis of the virtual equilibrium points. The importance of providing a stability proof for WPL dynamics is that the latter allows agents to reach a Nash equilibrium in two-agent, two-action games in which the only feedback that an agent needs is its own reward, and no agent uses knowledge of the rewards or actions of other agents, or any a priori information on the location of the Nash equilibrium. © 2013 IEEE.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

A deep learning framework for neuroscience

引用

NATURE NEUROSCIENCE 2019年第11期22卷 1761-1770页

作者： Richards, Blake A. Lillicrap, Timothy P. Beaudoin, Philippe Bengio, Yoshua Bogacz, Rafal Christensen, Amelia Clopath, Claudia Costa, Rui Ponte de Berker, Archy Ganguli, Surya Gillon, Colleen J. Hafner, Danijar Kepecs, Adam Kriegeskorte, Nikolaus Latham, Peter Lindsay, Grace W. Miller, Kenneth D. Naud, Richard Pack, Christopher C. Poirazi, Panayiota Roelfsema, Pieter Sacramento, Joao Saxe, Andrew Scellier, Benjamin Schapiro, Anna C. Senn, Walter Wayne, Greg Yamins, Daniel Zenke, Friedemann Zylberberg, Joel Therien, Denis Kording, Konrad P. Mila Montreal PQ Canada McGill Univ Sch Comp Sci Montreal PQ Canada McGill Univ Dept Neurol & Neurosurg Montreal PQ Canada Canadian Inst Adv Res Toronto ON Canada DeepMind Inc London England UCL Ctr Computat Math & Phys Life Sci & Expt Biol London England Element AI Montreal PQ Canada Univ Montreal Montreal PQ Canada Univ Oxford MRC Brain Network Dynam Unit Oxford England Stanford Univ Dept Elect Engn Stanford CA 94305 USA Imperial Coll London Dept Bioengn London England Univ Bristol Sch Comp Sci Elect & Elect Engn Computat Neurosci Unit Bristol Avon England Univ Bristol Engn Maths Bristol Avon England Univ Bern Dept Physiol Bern Switzerland Stanford Univ Dept Appl Phys Stanford CA 94305 USA Google Brain Mountain View CA USA Univ Toronto Scarborough Dept Biol Sci Toronto ON Canada Univ Toronto Dept Cell & Syst Biol Toronto ON Canada Univ Toronto Dept Comp Sci Toronto ON Canada Vector Inst Toronto ON Canada Cold Spring Harbor Lab POB 100 Cold Spring Harbor NY 11724 USA Columbia Univ Dept Psychol & Neurosci New York NY USA Columbia Univ Zuckerman Mind Brain Behav Inst New York NY USA UCL Gatsby Computat Neurosci Unit London England Columbia Univ Ctr Theoret Neurosci New York NY USA Columbia Univ Coll Phys & Surg Dept Neurosci New York NY USA Univ Ottawa Brain & Mind Inst Ottawa ON Canada Univ Ottawa Dept Cellular & Mol Med Ottawa ON Canada Fdn Res & Technol Hellas FORTH IMBB Iraklion Greece Netherlands Inst Neurosci Dept Vis & Cognit Amsterdam Netherlands Swiss Fed Inst Technol Inst Neuroinformat Zurich Switzerland Univ Zurich Zurich Switzerland Univ Oxford Dept Expt Psychol Oxford England Univ Penn Dept Psychol 3815 Walnut St Philadelphia PA 19104 USA Stanford Univ Dept Psychol Stanford CA USA Stanford Univ Dept Comp Sci Stanford CA 94305 USA Stanford Univ Wu Tsai Neurosci Inst Stanford CA 94305 USA Friedrich Miescher Inst Biomed Res Basel Switzerland Univ Oxford Ctr Neural Circuits & Behav O

Systems neuroscience seeks explanations for how the brain implements a wide variety of perceptual, cognitive and motor tasks. Conversely, artificial intelligence attempts to design computational systems based on the tasks they will have to solve. In artificial neural networks, the three components specified by design are the objective functions, the learning rules and the architectures. With the growing success of deep learning, which utilizes brain-inspired architectures, these three designed components have increasingly become central to how we model, engineer and optimize complex artificial learning systems. Here we argue that a greater focus on these components would also benefit systems neuroscience. We give examples of how this optimization-based framework can drive theoretical and experimental progress in neuroscience. We contend that this principled perspective on systems neuroscience will help to generate more rapid progress.

关键词： learning algorithms Machine learning Neural circuits

来源：评论

学校读者我要写书评

暂无评论

Thermodynamic non-ideality and disorder heterogeneity in actinide silicate solid solutions

NPJ MATERIALS DEGRADATION

引用

NPJ MATERIALS DEGRADATION 2021年第1期5卷 1-14页

作者： Marcial, J. Zhang, Y. Zhao, X. Xu, H. Mesbah, A. Nienhuis, E. T. Szenknect, S. Neuefeind, J. C. Lin, J. Qi, L. Migdisov, A. A. Ewing, R. C. Dacheux, N. McCloy, J. S. Guo, X. Washington State Univ Sch Mech & Mat Engn Pullman WA 99164 USA Oak Ridge Natl Lab Neutron Scattering Div Oak Ridge TN USA NIST Mat Measurement Sci Div Gaithersburg MD 20899 USA Washington State Univ Dept Chem Pullman WA 99164 USA Washington State Univ Alexandra Navrotsky Inst Expt Thermodynam Pullman WA 99164 USA Washington State Univ Mat Sci & Engn Program Pullman WA 99164 USA Los Alamos Natl Lab Earth & Environm Sci Div Los Alamos NM USA Univ Montpellier ICSM CRNS CEAENSCMSite Marcoule Bagnols Sur Ceze France Chinese Acad Sci Shanghai Inst Appl Phys Shanghai Peoples R China Univ Michigan Dept Mat Sci & Engn Ann Arbor MI 48109 USA Stanford Univ Dept Geol Sci Stanford CA 94305 USA

Non-ideal thermodynamics of solid solutions can greatly impact materials degradation behavior. We have investigated an actinide silicate solid solution system (USiO4-ThSiO4), demonstrating that thermodynamic non-ideality follows a distinctive, atomic-scale disordering process, which is usually considered as a random distribution. Neutron total scattering implemented by pair distribution function analysis confirmed a random distribution model for U and Th in first three coordination shells;however, a machine-learning algorithm suggested heterogeneous U and Th clusters at nanoscale (similar to 2 nm). The local disorder and nanosized heterogeneous is an example of the non-ideality of mixing that has an electronic origin. Partial covalency from the U/Th 5f-O 2p hybridization promotes electron transfer during mixing and leads to local polyhedral distortions. The electronic origin accounts for the strong non-ideality in thermodynamic parameters that extends the stability field of the actinide silicates in nature and under typical nuclear waste repository conditions.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Adaptive scale-invariant online algorithms for learning linear models

arXiv

引用

arXiv 2019年

作者： Kempka, Michal Kotlowski, Wojciech Warmuth, Manfred K. Poznan University of Technology Poznan Poland Google Inc. Zürich UC Santa Cruz

We consider online learning with linear models, where the algorithm predicts on sequentially revealed instances (feature vectors), and is compared against the best linear function (comparator) in hindsight. Popular algorithms in this framework, such as Online Gradient Descent (OGD), have parameters (learning rates), which ideally should be tuned based on the scales of the features and the optimal comparator, but these quantities only become available at the end of the learning process. In this paper, we resolve the tuning problem by proposing online algorithms making predictions which are invariant under arbitrary rescaling of the features. The algorithms have no parameters to tune, do not require any prior knowledge on the scale of the instances or the comparator, and achieve regret bounds matching (up to a logarithmic factor) that of OGD with optimally tuned separate learning rates per dimension, while retaining comparable runtime performance. Copyright © 2019, The Authors. All rights reserved.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

SLIDE: In defense of smart algorithms over hardware acceleration for large-scale deep learning systems

arXiv

引用

arXiv 2019年

作者： Chen, Beidi Medini, Tharun Farwell, James Gobriel, Sameh Tai, Charlie Shrivastava, Anshumali Rice University Intel Corporation

Deep learning (DL) algorithms are the central focus of modern machine learning systems. As data volumes keep growing, it has become customary to train large neural networks with hundreds of millions of parameters to maintain enough capacity to memorize these volumes and obtain state-of-the-art accuracy. To get around the costly computations associated with large models and data, the community is increasingly investing in specialized hardware for model training. However, specialized hardware is expensive and hard to generalize to a multitude of tasks. The progress on the algorithmic front has failed to demonstrate a direct advantage over powerful hardware such as NVIDIA-V100 GPUs. This paper provides an exception. We propose SLIDE (Sub-LInear Deep learning Engine) that uniquely blends smart randomized algorithms, with multi-core parallelism and workload optimization. Using just a CPU, SLIDE drastically reduces the computations during both training and inference outperforming an optimized implementation of Tensorflow (TF) on the best available GPU. Our evaluations on industry-scale recommendation datasets, with large fully connected architectures, show that training with SLIDE on a 44 core CPU is more than 3.5 times (1 hour vs. 3.5 hours) faster than the same network trained using TF on Tesla V100 at any given accuracy level. On the same CPU hardware, SLIDE is over 10x faster than TF. We provide codes and scripts for reproducibility. Copyright © 2019, The Authors. All rights reserved.

关键词： learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Practical reinforcement learning - Experiences in lot scheduling application

引用

IFAC-PapersOnLine 2019年第13期52卷 1415-1420页

作者： Rummukainen, Hannu Nurminen, Jukka K. VTT Technical Research Centre of Finland P.O. Box 1000 VTTFI-02044 Finland

With recent advances in deep reinforcement learning, it is time to take another look at reinforcement learning as an approach for discrete production control. We applied proximal policy optimization (PPO), a recently developed algorithm for deep reinforcement learning, to the stochastic economic lot scheduling problem. The problem involves scheduling manufacturing decisions on a single machine under stochastic demand, and despite its simplicity remains computationally challenging. We implemented two parameterized models for the control policy and value approximation, a linear model and a neural network, and used a modified PPO algorithm to seek the optimal parameter values. Benchmarking against the best known control policy for the test case, in which Paternina-Arboleda and Das (2005) combined a base-stock policy and an older reinforcement learning algorithm, we improved the average cost rate by 2 %. Our approach is more general, as we do not require a priori policy parameters such as base-stock levels, and the entire policy is learned. © 2019, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.

关键词： learning algorithms Approximation algorithms Deep learning learning systems Manufacture Monte Carlo methods Neural networks Production control Reinforcement learning Scheduling Stochastic control systems Stochastic systems Discrete production Economic lot scheduling Economic lot scheduling problems learning control Parameterized model Policy optimization Stochastic control Value approximation

来源：评论

学校读者我要写书评

暂无评论

ADES: A New Ensemble Diversity-Based Approach for Handling Concept Drift

引用

MOBILE INFORMATION SYSTEMS 2021年第1期2021卷

作者： Museba, Tinofirei Nelwamondo, Fulufhelo Ouahada, Khmaies Univ Johannesburg Dept Appl Informat Syst Johannesburg South Africa Univ Johannesburg Dept Elect & Elect Engn Sci Johannesburg South Africa

Beyond applying machine learning predictive models to static tasks, a significant corpus of research exists that applies machine learning predictive models to streaming environments that incur concept drift. With the prevalence of streaming real-world applications that are associated with changes in the underlying data distribution, the need for applications that are capable of adapting to evolving and time-varying dynamic environments can be hardly overstated. Dynamic environments are nonstationary and change with time and the target variables to be predicted by the learning algorithm and often evolve with time, a phenomenon known as concept drift. Most work in handling concept drift focuses on updating the prediction model so that it can recover from concept drift while little effort has been dedicated to the formulation of a learning system that is capable of learning different types of drifting concepts at any time with minimum overheads. This work proposes a novel and evolving data stream classifier called Adaptive Diversified Ensemble Selection Classifier (ADES) that significantly optimizes adaptation to different types of concept drifts at any time and improves convergence to new concepts by exploiting different amounts of ensemble diversity. The ADES algorithm generates diverse base classifiers, thereby optimizing the margin distribution to exploit ensemble diversity to formulate an ensemble classifier that generalizes well to unseen instances and provides fast recovery from different types of concept drift. Empirical experiments conducted on both artificial and real-world data streams demonstrate that ADES can adapt to different types of drifts at any given time. The prediction performance of ADES is compared to three other ensemble classifiers designed to handle concept drift using both artificial and real-world data streams. The comparative evaluation performed demonstrated the ability of ADES to handle different types of concept drifts. The experimental

关键词： learning algorithms

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：