IEEE International Workshop on Machine Learning for Signal Processing : [proceedings]. IEEE International Workshop on Machine Learning for Signal Processing最新文献

DATA-DRIVEN LEARNING OF GEOMETRIC SCATTERING MODULES FOR GNNS. 以数据为驱动学习 gnns 的几何散射模块。

IEEE International Workshop on Machine Learning for Signal Processing : [proceedings]. IEEE International Workshop on Machine Learning for Signal Processing Pub Date : 2021-10-01 Epub Date: 2021-11-15 DOI: 10.1109/mlsp52302.2021.9596169

Alexander Tong, Frederick Wenkel, Kincaid Macdonald, Smita Krishnaswamy, Guy Wolf

引用次数: 0

LEARNING GENERAL TRANSFORMATIONS OF DATA FOR OUT-OF-SAMPLE EXTENSIONS. 学习样本外扩展的一般数据转换。

IEEE International Workshop on Machine Learning for Signal Processing : [proceedings]. IEEE International Workshop on Machine Learning for Signal Processing Pub Date : 2020-09-01 Epub Date: 2020-10-20 DOI: 10.1109/mlsp49062.2020.9231660

Matthew Amodio, David van Dijk, Guy Wolf, Smita Krishnaswamy

{"title":"LEARNING GENERAL TRANSFORMATIONS OF DATA FOR OUT-OF-SAMPLE EXTENSIONS.","authors":"Matthew Amodio, David van Dijk, Guy Wolf, Smita Krishnaswamy","doi":"10.1109/mlsp49062.2020.9231660","DOIUrl":"https://doi.org/10.1109/mlsp49062.2020.9231660","url":null,"abstract":"While generative models such as GANs have been successful at mapping from noise to specific distributions of data, or more generally from one distribution of data to another, they cannot isolate the transformation that is occurring and apply it to a new distribution not seen in training. Thus, they memorize the domain of the transformation, and cannot generalize the transformation out of sample. To address this, we propose a new neural network called a Neuron Transformation Network (NTNet) that isolates the signal representing the transformation itself from the other signals representing internal distribution variation. This signal can then be removed from a new dataset distributed differently from the original one trained on. We demonstrate the effectiveness of our NTNet on more than a dozen synthetic and biomedical single-cell RNA sequencing datasets, where the NTNet is able to learn the data transformation performed by genetic and drug perturbations on one sample of cells and successfully apply it to another sample of cells to predict treatment outcome.","PeriodicalId":73290,"journal":{"name":"IEEE International Workshop on Machine Learning for Signal Processing : [proceedings]. IEEE International Workshop on Machine Learning for Signal Processing","volume":"2020 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/mlsp49062.2020.9231660","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"39446576","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

CONVOLUTIONAL RECURRENT NEURAL NETWORK BASED DIRECTION OF ARRIVAL ESTIMATION METHOD USING TWO MICROPHONES FOR HEARING STUDIES. 基于卷积递归神经网络的双传声器听觉到达方向估计方法研究。

IEEE International Workshop on Machine Learning for Signal Processing : [proceedings]. IEEE International Workshop on Machine Learning for Signal Processing Pub Date : 2020-09-01 Epub Date: 2020-10-20 DOI: 10.1109/mlsp49062.2020.9231693

Abdullah Küçük, Issa M S Panahi

{"title":"CONVOLUTIONAL RECURRENT NEURAL NETWORK BASED DIRECTION OF ARRIVAL ESTIMATION METHOD USING TWO MICROPHONES FOR HEARING STUDIES.","authors":"Abdullah Küçük, Issa M S Panahi","doi":"10.1109/mlsp49062.2020.9231693","DOIUrl":"https://doi.org/10.1109/mlsp49062.2020.9231693","url":null,"abstract":"This work proposes a convolutional recurrent neural network (CRNN) based direction of arrival (DOA) angle estimation method, implemented on the Android smartphone for hearing aid applications. The proposed app provides a 'visual' indication of the direction of a talker on the screen of Android smartphones for improving the hearing of people with hearing disorders. We use real and imaginary parts of short-time Fourier transform (STFT) as a feature set for the proposed CRNN architecture for DOA angle estimation. Real smartphone recordings are utilized for assessing performance of the proposed method. The accuracy of the proposed method reaches 87.33% for unseen (untrained) environments. This work also presents real-time inference of the proposed method, which is done on an Android smartphone using only its two built-in microphones and no additional component or external hardware. The real-time implementation also proves the generalization and robustness of the proposed CRNN based model.","PeriodicalId":73290,"journal":{"name":"IEEE International Workshop on Machine Learning for Signal Processing : [proceedings]. IEEE International Workshop on Machine Learning for Signal Processing","volume":"2020 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2020-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/mlsp49062.2020.9231693","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"38969232","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Nonlinear and non-Gaussian signal processing 非线性和非高斯信号处理

IEEE International Workshop on Machine Learning for Signal Processing : [proceedings]. IEEE International Workshop on Machine Learning for Signal Processing Pub Date : 2019-08-13 DOI: 10.1093/oso/9780198714934.003.0009

Max A. Little

引用次数: 0

Statistical modelling and inference 统计建模与推理

IEEE International Workshop on Machine Learning for Signal Processing : [proceedings]. IEEE International Workshop on Machine Learning for Signal Processing Pub Date : 2019-08-13 DOI: 10.1093/oso/9780198714934.003.0004

Max A. Little

引用次数: 0

Probabilistic graphical models 概率图形模型

IEEE International Workshop on Machine Learning for Signal Processing : [proceedings]. IEEE International Workshop on Machine Learning for Signal Processing Pub Date : 2019-08-13 DOI: 10.1093/oso/9780198714934.003.0005

Max A. Little

引用次数: 0

Nonparametric Bayesian machine learning and signal processing 非参数贝叶斯机器学习与信号处理

IEEE International Workshop on Machine Learning for Signal Processing : [proceedings]. IEEE International Workshop on Machine Learning for Signal Processing Pub Date : 2019-08-13 DOI: 10.1093/oso/9780198714934.003.0010

Max A. Little

{"title":"Nonparametric Bayesian machine learning and signal processing","authors":"Max A. Little","doi":"10.1093/oso/9780198714934.003.0010","DOIUrl":"https://doi.org/10.1093/oso/9780198714934.003.0010","url":null,"abstract":"We have seen that stochastic processes play an important foundational role in a wide range of methods in DSP. For example, we treat a discrete-time signal as a Gaussian process, and thereby obtain many mathematically simplified algorithms, particularly based on the power spectral density. At the same time, in machine learning, it has generally been observed that nonparametric methods outperform parametric methods in terms of predictive accuracy since they can adapt to data with arbitrary complexity. However, these techniques are not Bayesian so we are unable to do important inferential procedures such as draw samples from the underlying probabilistic model or compute posterior confidence intervals. But, Bayesian models are often only mathematically tractable if parametric, with the corresponding loss of predictive accuracy. An alternative, discussed in this section, is to extend the mathematical tractability of stochastic processes to Bayesian methods. This leads to so-called Bayesian nonparametrics exemplified by techniques such as Gaussian process regression and Dirichlet process mixture modelling that have been shown to be extremely useful in practical DSP and machine learning applications.","PeriodicalId":73290,"journal":{"name":"IEEE International Workshop on Machine Learning for Signal Processing : [proceedings]. IEEE International Workshop on Machine Learning for Signal Processing","volume":"46 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80427209","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Mathematical foundations 数学基础

IEEE International Workshop on Machine Learning for Signal Processing : [proceedings]. IEEE International Workshop on Machine Learning for Signal Processing Pub Date : 2019-08-13 DOI: 10.1093/oso/9780198714934.003.0001

Max A. Little

引用次数: 0

Linear-Gaussian systems and signal processing 线性-高斯系统与信号处理

IEEE International Workshop on Machine Learning for Signal Processing : [proceedings]. IEEE International Workshop on Machine Learning for Signal Processing Pub Date : 2019-08-13 DOI: 10.1093/oso/9780198714934.003.0007

Max A. Little

{"title":"Linear-Gaussian systems and signal processing","authors":"Max A. Little","doi":"10.1093/oso/9780198714934.003.0007","DOIUrl":"https://doi.org/10.1093/oso/9780198714934.003.0007","url":null,"abstract":"Linear systems theory, based on the mathematics of vector spaces, is the backbone of all “classical” DSP and a large part of statistical machine learning. The basic idea -- that linear algebra applied to a signal can of substantial practical value -- has counterparts in many areas of science and technology. In other areas of science and engineering, linear algebra is often justified by the fact that it is often an excellent model for real-world systems. For example, in acoustics the theory of (linear) wave propagation emerges from the concept of linearization of small pressure disturbances about the equilibrium pressure in classical fluid dynamics. Similarly, the theory of electromagnetic waves is also linear. Except when a signal emerges from a justifiably linear system, in DSP and machine learning we do not have any particular correspondence to reality to back up the choice of linearity. However, the mathematics of vector spaces, particularly when applied to systems which are time-invariant and jointly Gaussian, is highly tractable, elegant and immensely useful.","PeriodicalId":73290,"journal":{"name":"IEEE International Workshop on Machine Learning for Signal Processing : [proceedings]. IEEE International Workshop on Machine Learning for Signal Processing","volume":"2 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-08-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82901056","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Discrete signals: sampling, quantization and coding 离散信号:采样、量化和编码

IEEE International Workshop on Machine Learning for Signal Processing : [proceedings]. IEEE International Workshop on Machine Learning for Signal Processing Pub Date : 2019-08-13 DOI: 10.1093/oso/9780198714934.003.0008

Max A. Little

引用次数: 0