We present a novel convex-optimization-based approach to the solutions of a family of problems involving constant modulus signals. The family of problems includes the constant modulus and the constrained constant modulus, as well as the modified constant modulus and the constrained modified constant modulus. These solutions are shown to constitute semidefinite programs (SDP), thus enabling efficient interior-point methods with polynomial time complexity. The performance of the proposed solutions, demonstrated in several simulated experiments for the task of blind beamforming, is shown to be superior to existing methods.

%B Signal Processing %V 160 %P 263 - 270 %8 07/2019 %G eng %U https://linkinghub.elsevier.com/retrieve/pii/S0165168419300568 %! Signal Processing %R 10.1016/j.sigpro.2019.02.007 %0 Conference Paper %B 81st EAGE Conference and Exhibition 2019 %D 2019 %T Deep Recurrent Architectures for Seismic Tomography %A Amir Adler %A Mauricio Araya-Polo %A Tomaso Poggio %XThis paper introduces novel deep recurrent neural network architectures for Velocity Model Building (VMB), which is beyond what Araya-Polo et al 2018 pioneered with the Machine Learning-based seismic tomography built with convolutional non-recurrent neural network. Our investigation includes the utilization of basic recurrent neural network (RNN) cells, as well as Long Short Term Memory (LSTM) and Gated Recurrent Unit (GRU) cells. Performance evaluation reveals that salt bodies are consistently predicted more accurately by GRU and LSTM-based architectures, as compared to non-recurrent architectures. The results take us a step closer to the final goal of a reliable fully Machine Learning-based tomography from pre-stack data, which when achieved will reduce the VMB turnaround from weeks to days.

%B 81st EAGE Conference and Exhibition 2019 %8 06/2019 %G eng %0 Conference Paper %B 27th European Signal Processing Conference, EUSIPCO 2019 %D 2019 %T Direct Localization by Partly Calibrated Arrays: A Relaxed Maximum Likelihood Solution %A Amir Adler %A Mati Wax %XWe present a novel relaxed maximum likelihood solution to the problem of direct localization of multiple narrowband sources by partly calibrated arrays, i.e., arrays composed of fully calibrated subarrays yet lacking inter-array calibration. The proposed solution is based on eliminating analytically all the nuisance parameters in the problem, thus reducing the likelihood function to a maximization problem involving only the location of the sources. The performance of the solution is demonstrated via simulations.

%B 27th European Signal Processing Conference, EUSIPCO 2019 %C A Coruna, Spain %8 07/2019 %G eng %U http://eusipco2019.org/technical-program %0 Book Section %B Deep Learning: Algorithms and Applications %D 2019 %T Fast and Accurate Seismic Tomography via Deep Learning %A Mauricio Araya-Polo %A Amir Adler %A Stuart Farris %A Joseph Jennings %B Deep Learning: Algorithms and Applications %I SPRINGER-VERLAG %G eng %0 Book Section %B Handbook of Numerical Analysis %D 2018 %T Compressed Learning for Image Classification: A Deep Neural Network Approach %A Zisselman, E. %A Amir Adler %A Elad, M. %K Compressed learning %K Compressed sensing %K deep learning %K Neural Networks %K sparse coding %K Sparse representation %XCompressed learning (CL) is a joint signal processing and machine learning framework for inference from a signal, using a small number of measurements obtained by a linear projection. In this chapter, we review this concept of compressed leaning, which suggests that learning directly in the compressed domain is possible, and with good performance. We experimentally show that the classification accuracy, using an efficient classifier in the compressed domain, can be quite close to the accuracy obtained when operating directly on the original data. Using convolutional neural network for the image classification, we examine the performance of different linear sensing schemes for the data acquisition stage, such as random sensing and PCA projection. Then, we present an end-to-end deep learning approach for CL, in which a network composed of fully connected layers followed by convolutional ones, performs the linear sensing and the nonlinear inference stages simultaneously. During the training phase, both the sensing matrix and the nonlinear inference operator are jointly optimized, leading to a suitable sensing matrix and better performance for the overall task of image classification in the compressed domain. The performance of the proposed approach is demonstrated using the MNIST and CIFAR-10 datasets.

Full text available online - https://books.google.com/books?hl=en&lr=&id=zDx4DwAAQBAJ&oi=fnd&pg=PA3&ots=vxCX2Ddl0f&sig=RNZB40wA-2EFLjOpkazg8cnWyYo#v=onepage&q&f=false

%B Handbook of Numerical Analysis %I Elsevier %V 19 %P 3 - 17 %8 10/2018 %@ 9780444642059 %G eng %U https://linkinghub.elsevier.com/retrieve/pii/S1570865918300024 %R 10.1016/bs.hna.2018.08.002 %0 Generic %D 2018 %T Constant Modulus Algorithms via Low-Rank Approximation %A Amir Adler %A Mati Wax %K Constant modulus %K convex optimization %K trace norm %XWe present a novel convex-optimization-based approach to the solutions of a family of problems involving constant modulus signals. The family of problems includes the constant modulus and the constrained constant modulus, as well as the modified constant modulus and the constrained modified constant modulus. The usefulness of the proposed solutions is demonstrated for the tasks of blind beamforming and blind multiuser detection. The performance of these solutions, as we demonstrate by simulated data, is superior to existing methods.

%8 04/2018 %2http://hdl.handle.net/1721.1/114672

%0 Conference Paper %B 2018 IEEE Statistical Signal Processing Workshop (SSP) %D 2018 %T Constant Modulus Beamforming Via Low-Rank Approximation %A Amir Adler %A Mati Wax %XWe present novel convex-optimization-based solutions to the problem of blind beamforming of constant modulus signals, and to the related problem of linearly constrained blind beamforming of constant modulus signals. These solutions are based on a low-rank approximation, ensure global optimality and are parameter free, namely, do not contain any tuneable parameters and do not require any a-priori parameter settings. The proposed approach outperforms state-of-the-art both in terms of the number of required samples for convergence, and in terms of the beamformer output SINR.

%B 2018 IEEE Statistical Signal Processing Workshop (SSP) %C Freiburg im Breisgau, Germany %@ 978-1-5386-1571-3 %G eng %U https://ieeexplore.ieee.org/document/8450799/ %R 10.1109/SSP.2018.8450799 %0 Journal Article %J The Leading Edge %D 2018 %T Deep-learning tomography %A Mauricio Araya-Polo %A Joseph Jennings %A Amir Adler %A Dahlke, Taylor %K algorithm %K full waveform inversion %K Neural Networks %K NMO %K tomography Read More: https://library.seg.org/doi/abs/10.1190/tle37010058.1 %XVelocity model building (VMB) is a key step in hydrocarbon exploration; The VMB main product is an initial model of the subsurface that is subsequently used in seismic imaging and interpretation workflows. Reflection or refraction Tomography and full waveform inversion (FWI) are the most commonly used techniques in VMB. On one hand, Tomography is a time-consuming activity that relies on successive updates of highly human-curated analysis of gathers. On the other hand, FWI is very computationally demanding with no guarantees of global convergence.

We propose and implement a novel concept that bypasses these demanding steps, directly producing an accurate gridding or layered velocity model from shot gathers. Our approach relies on training deep neural networks; the resulting predictive model maps relationships between the data space and the final output (particularly, the presence of high velocity segments that might indicate salt formations). In term of time, the training task takes a few hours for 2D data, but the inference step (predicting a model from previously unseen data) takes only seconds.

The promising results shown here for synthetic 2D data demonstrate a new way of using seismic data and suggests fast turnaround of workflows that now make use of machine learning approaches to identify key structures in the subsurface.

%B The Leading Edge %V 37 %P 58 - 66 %8 01/2018 %G eng %U https://library.seg.org/doi/10.1190/tle37010058.1 %N 1 %R 10.1190/tle37010058.1