Generative models have been successfully used for generating realistic signals. Because the likelihood function is typically intractable in most of these models, the common practice is to use "implicit" models that avoid likelihood calculation. However, it is hard to obtain theoretical guarantees for such models. In particular, it is not understood when they can globally optimize their non-convex objectives. Here we provide such an analysis for the case of Maximum Mean Discrepancy (MMD) learning of generative models. We prove several optimality results, including for a Gaussian distribution with low rank covariance (where likelihood is inapplicable) and a mixture of Gaussians. Our analysis shows that that the MMD optimization landscape is benign in these cases, and therefore gradient based methods will globally minimize the MMD objective.

Time series forecasting use cases are certainly the most common time series use cases, as they can be found in all types of industries and in various contexts.

"CNNs are a special kind of multi-layer neural networks. Like almost every other neural network they are trained with a version of the back-propagation algorithm. Where they differ is in the architecture.

DL is an advanced technology based on neural networks that try to imitate the way the human cortex works. Today, we want to get deeper into this subject. You have to know that neural networks are by no means homogenous. In fact, we can indicate at least six types of neural networks and deep learning architectures that are built on them. In this article, we are going to show you the most popular and versatile types of deep learning architecture.

To develop and evaluate an automated segmentation method for accurate quantification of abdominal adipose tissue (AAT) depots (superficial subcutaneous adipose tissue [SSAT], deep subcutaneous adipose tissue [DSAT], and visceral adipose tissue [VAT]) in neonates and young children. This was a secondary analysis of prospectively collected data, which used abdominal MRI data from Growing Up in Singapore Towards healthy Outcomes, or GUSTO, a longitudinal mother–offspring cohort, to train and evaluate a convolutional neural network for volumetric AAT segmentation. The data comprised imaging volumes of 333 neonates obtained at early infancy (age 2 weeks, 180 male neonates) and 755 children aged either 4.5 years (n 316, 150 male children) or 6 years (n 439, 219 male children). The network was trained on images of 761 randomly selected volumes (neonates and children combined) and evaluated on 100 neonatal volumes and 227 child volumes by using 10-fold validation. Automated segmentations were compared with expert-generated manual segmentation.

Deep Learning, particularly Natural Language Processing (NLP), has been gathering a huge interest nowadays. Some time ago, there was an NLP competition on Kaggle called Quora Question insincerity challenge. The competition is a text classification problem and it becomes easier to understand after working through the competition, as well as by going through the invaluable kernels put up by the Kaggle experts. First, let's start by explaining a little more about the text classification problem in the competition. Text classification is a common task in natural language processing, which transforms a sequence of a text of indefinite length into a category of text.

All local retailers in India can create a video of Shahrukh Khan (one of the largest celebrities in the world) endorsing their local stores! An initiative by Cadbury, conceptualized by Ogilvy, powered by Rephrase.ai's

PyTorch is a widely used, open source deep learning platform used for easily writing neural network layers in Python enabling a seamless workflow from research to production. Based on Torch, PyTorch has become a powerful machine learning framework favored by esteemed researchers around the world, and now adopted fully by Facebook. The new PyTorch 1.10.0 release is composed of over 3,400 commits since 1.9, made by 426 contributors. PyTorch 1.10 updates are focused on improving training and performance of PyTorch, and developer usability. You can check the blogpost that shows the new features here.

Scientific communities are increasingly adopting machine learning and deep learning models in their applications to accelerate scientific insights. High performance computing systems are pushing the frontiers of performance with a rich diversity of hardware resources and massive scale-out capabilities. There is a critical need to understand fair and effective benchmarking of machine learning applications that are representative of real-world scientific use cases. MLPerfTM is a community-driven standard to benchmark machine learning workloads, focusing on end-to-end performance metrics. In this paper, we introduce MLPerf HPC, a benchmark suite of largescale scientific machine learning training applications, driven by the MLCommonsTM Association.

Coronaviruses can be isolated from bats, civets, pangolins, birds and other wild animals. As an animal-origin pathogen, coronavirus can cross species barrier and cause pandemic in humans. In this study, a deep learning model for early prediction of pandemic risk was proposed based on the sequences of viral genomes. A total of 3257 genomes were downloaded from the Coronavirus Genome Resource Library. We present a deep learning model of cross-species coronavirus infection that combines a bidirectional gated recurrent unit network with a one-dimensional convolution. The genome sequence of animal-origin coronavirus was directly input to extract features and predict pandemic risk. The best performances were explored with the use of pre-trained DNA vector and attention mechanism. The area under the receiver operating characteristic curve (AUROC) and the area under precision-recall curve (AUPR) were used to evaluate the predictive models. The six specific models achieved good performances for the corresponding virus groups (1 for AUROC and 1 for AUPR). The general model with pre-training vector and attention mechanism provided excellent predictions for all virus groups (1 for AUROC and 1 for AUPR) while those without pre-training vector or attention mechanism had obviously reduction of performance (about 5–25%). Re-training experiments showed that the general model has good capabilities of transfer learning (average for six groups: 0.968 for AUROC and 0.942 for AUPR) and should give reasonable prediction for potential pathogen of next pandemic. The artificial negative data with the replacement of the coding region of the spike protein were also predicted correctly (100% accuracy). With the application of the Python programming language, an easy-to-use tool was created to implements our predictor. Robust deep learning model with pre-training vector and attention mechanism mastered the features from the whole genomes of animal-origin coronaviruses and could predict the risk of cross-species infection for early warning of next pandemic.