Deep learning is a subset of artificial intelligence, in particular, the field of machine learning. Deep learning uses a multi-layered artificial neural network to carry out a range of tasks, from fraud detection to speech recognition or language translation. Deep learning differs from traditional machine learning systems in that it is capable of self-learning and improving as it analyses large data sets. A highly flexible system it has a number of applications in business. In this article, we explain exactly what deep learning is and explore the ways that it is already transforming businesses. Deep learning is a function of artificial intelligence. It is designed to replicate the way that the human brain processes data. It also re-creates the patterns found in the brain's decision-making process. Sometimes called deep neural networking or neural learning, it is part of the wider field of machine learning. It is powered by networks that can carry out unsupervised learning. This process uses algorithms to analyse raw data, extracting information and presenting it in a structured, useful model. Often it is also used to process unstructured or unlabeled data.

Deep neural networks (DNNs) have been expanded into medical fields and triggered the revolution of some medical applications by extracting complex features and achieving high accuracy and performance, etc. On the contrast, the large-scale network brings high requirements of both memory storage and computation resource, especially for portable medical devices and other embedded systems. In this work, we first train a DNN for pneumonia detection using the dataset provided by RSNA Pneumonia Detection Challenge [4]. To overcome hardware limitation for implementing large-scale networks, we develop a systematic structured weight pruning method with filter sparsity, column sparsity and combined sparsity. Experiments show that we can achieve up to 36x compression ratio compared to the original model with 106 layers, while maintaining no accuracy degradation. We evaluate the proposed methods on an embedded low-power device, Jetson TX2, and achieve low power usage and high energy efficiency. Keywords: Pneumonia detection · YOLO · structured weight pruning.

Despite their tremendous success in a wide range of applications, deep neural network (DNN) models are inherently vulnerable to two types of malicious manipulations: adversarial inputs, which are crafted samples that deceive target DNNs, and backdoored models, which are forged DNNs that misbehave on trigger-embedded inputs. While prior work has intensively studied the two attack vectors in parallel, there is still a lack of understanding about their fundamental connection, which is critical for assessing the holistic vulnerability of DNNs deployed in realistic settings. In this paper, we bridge this gap by conducting the first systematic study of the two attack vectors within a unified framework. More specifically, (i) we develop a new attack model that integrates both adversarial inputs and backdoored models; (ii) with both analytical and empirical evidence, we reveal that there exists an intricate "mutual reinforcement" effect between the two attack vectors; (iii) we demonstrate that this effect enables a large spectrum for the adversary to optimize the attack strategies, such as maximizing attack evasiveness with respect to various defenses and designing trigger patterns satisfying multiple desiderata; (v) finally, we discuss potential countermeasures against this unified attack and their technical challenges, which lead to several promising research directions.

We present the first estimation of the mass and spin of Kerr black holes resulting from the coalescence of binary black holes using a deep neural network. The network is trained on the full publicly available catalog of numerical simulations of gravitational waves emission by binary black hole systems. The network prediction for non-precessing binaries as well as precessing binaries is compared with existing fits in the LIGO-Virgo software package when existing. For the non-precessing case, the absolute error distribution has a root mean square error of $2.6 \cdot 10^{-3}$ for the final mass (twice lower than the existing fits) and $3 \cdot 10^{-3}$ for the final spin (similarly to the existing fits). We also estimate of the final mass in the precessing case, where we obtain a RMSE of $1 \cdot 10^{-3}$ of the absolute error distribution. It is $8 \cdot 10^{-3}$ when predicting the spin of the black hole resulting from a precessing binary, against $1.1 \cdot 10^{-2}$ for the existing fits.

Machine learning techniques have been successfully applied to super-resolution tasks on natural images where visually pleasing results are sufficient. However in many scientific domains this is not adequate and estimations of errors and uncertainties are crucial. To address this issue we propose a Bayesian framework that decomposes uncertainties into epistemic and aleatoric uncertainties. We test the validity of our approach by super-resolving images of the Sun's magnetic field and by generating maps measuring the range of possible high resolution explanations compatible with a given low resolution magnetogram.

ARXIV 1 Dual-domain Cascade of U-nets for Multi-channel Magnetic Resonance Image Reconstruction Roberto Souza, PhD, Mariana Bento, PhD, Nikita Nogovitsyn, MSc, MD, Kevin J. Chung, BSc, R. Marc Lebel, PhD, and Richard Frayne, PhD Abstract --The U-net is a deep-learning network model that has been used to solve a number of inverse problems. In this work, the concatenation of two-element U-nets, termed the W-net, operating in k-space (K) and image (I) domains, were evaluated for multi-channel magnetic resonance (MR) image reconstruction. The two element network combinations were evaluated for the four possible image-k-space domain configurations: a) W-net II, b) W-net KK, c) W-net IK, and d) W-net KI were evaluated. Selected promising four element networks (WW-nets) were also examined. Two configurations of each network were compared: 1) Each coil channel processed independently, and 2) all channels processed simultaneously. One hundred and eleven volumetric, T1-weighted, 12-channel coil k-space datasets were used in the experiments. Normalized root mean squared error, peak signal to noise ratio, visual information fidelity and visual inspection were used to assess the reconstructed images against the fully sampled reference images. Our results indicated that networks that operate solely in the image domain are better suited when processing individual channels of multi-channel data independently. Dual domain methods are more advantageous when simultaneously reconstructing all channels of multi-channel data. Also, the appropriate cascade of U-nets compared favorably ( p 0 . Index T erms --Magnetic resonance imaging, compressed sensing, multi-channel (coil), image reconstruction, inverse problems, brain, machine learning M AGNETIC RESONANCE (MR) imaging is a sensitive diagnostic modality that allows specific, high-quality investigation of structure and function of the brain and body. One major drawback is the overall acquisition time to complete an MR imaging protocol, which can easily exceed 30 minutes per patient [1]. Lengthy MR examination times are costly ( 300 USD or more per examination); increase susceptibility to patient motion artifacts, which negatively impact image quality; further reduce patient throughput and contribute to repeated studies.

We develop amortized population Gibbs (APG) samplers, a new class of autoencoding variational methods for deep probabilistic models. APG samplers construct high-dimensional proposals by iterating over updates to lower-dimensional blocks of variables. Each conditional update is a neural proposal, which we train by minimizing the inclusive KL divergence relative to the conditional posterior. To appropriately account for the size of the input data, we develop a new parameterization in terms of neural sufficient statistics, resulting in quasi-conjugate variational approximations. Experiments demonstrate that learned proposals converge to the known analytical conditional posterior in conjugate models, and that APG samplers can learn inference networks for highly-structured deep generative models when the conditional posteriors are intractable. Here APG samplers offer a path toward scaling up stochastic variational methods to models in which standard autoencoding architectures fail to produce accurate samples.

In general, image restoration involves mapping from low quality images to their high-quality counterparts. Such optimal mapping is usually non-linear and learnable by machine learning. Recently, deep convolutional neural networks have proven promising for such learning processing. It is desirable for an image processing network to support well with three vital tasks, namely, super-resolution, denoising, and deblocking. It is commonly recognized that these tasks have strong correlations. Therefore, it is imperative to harness the inter-task correlations. To this end, we propose the cross-scale residual network to exploit scale-related features and the inter-task correlations among the three tasks. The proposed network can extract multiple spatial scale features and establish multiple temporal feature reusage. Our experiments show that the proposed approach outperforms state-of-the-art methods in both quantitative and qualitative evaluations for multiple image restoration tasks.

Unsupervised text embedding has shown great power in a wide range of NLP tasks. While text embeddings are typically learned in the Euclidean space, directional similarity is often more effective in tasks such as word similarity and document clustering, which creates a gap between the training stage and usage stage of text embedding. To close this gap, we propose a spherical generative model based on which unsupervised word and paragraph embeddings are jointly learned. To learn text embeddings in the spherical space, we develop an efficient optimization algorithm with convergence guarantee based on Riemannian optimization. Our model enjoys high efficiency and achieves state-of-the-art performances on various text embedding tasks including word similarity and document clustering.

Convolutional neural networks (CNN) have become one of the most popular machine learning tools and are being applied in various tasks, however, CNN models are vulnerable to universal perturbations, which are usually human-imperceptible but can cause natural images to be misclassified with high probability. One of the state-of-the-art algorithms to generate universal perturbations is known as UAP. UAP only aggregates the minimal perturbations in every iteration, which will lead to generated universal perturbation whose magnitude cannot rise up efficiently and cause a slow generation. In this paper, we proposed an optimized algorithm to improve the performance of crafting universal perturbations based on orientation of perturbation vectors. At each iteration, instead of choosing minimal perturbation vector with respect to each image, we aggregate the current instance of universal perturbation with the perturbation which has similar orientation to the former so that the magnitude of the aggregation will rise up as large as possible at every iteration. The experiment results show that we get universal perturbations in a shorter time and with a smaller number of training images. Furthermore, we observe in experiments that universal perturbations generated by our proposed algorithm have an average increment of fooling rate by 8% ~ 9% in white-box attacks and black-box attacks comparing with universal perturbations generated by UAP.