The Boston Bruins didn't take long to put the painful memory of the 2010 Stanley Cup Playoffs behind them.

Marcus Sorensen is using his connections in Sweden to stay ready in case the NHL season resumes.

Sabrina Ionescu wins the Wooden Award for the second year in a row, becoming the fifth in the trophy's history to win in back-to-back seasons. With the honor, she completes a complete sweep of the national postseason player of the year awards. As a senior, Ionescu matched her own single-season mark with eight triple-doubles in 2019-20, and she was incredibly efficient from the field with a career-best 51.8 field goal percentage.

We present GluonCV and GluonNLP, the deep learning toolkits for computer vision and natural language processing based on Apache MXNet (incubating). These toolkits provide state-of-the-art pre-trained models, training scripts, and training logs, to facilitate rapid prototyping and promote reproducible research. We also provide modular APIs with flexible building blocks to enable efficient customization. Leveraging the MXNet ecosystem, the deep learning models in GluonCV and GluonNLP can be deployed onto a variety of platforms with different programming languages. The Apache 2.0 license has been adopted by GluonCV and GluonNLP to allow for software distribution, modification, and usage.

Sylvia Frühwirth-Schnatter.

Source: Brazilian Journal of Probability and Statistics, Volume 33, Number 4, 706--733.

Abstract:
Finite mixture models and their extensions to Markov mixture and mixture of experts models are very popular in analysing data of various kind. A challenge for these models is choosing the number of components based on marginal likelihoods. The present paper suggests two innovative, generic bridge sampling estimators of the marginal likelihood that are based on constructing balanced importance densities from the conditional densities arising during Gibbs sampling. The full permutation bridge sampling estimator is derived from considering all possible permutations of the mixture labels for a subset of these densities. For the double random permutation bridge sampling estimator, two levels of random permutations are applied, first to permute the labels of the MCMC draws and second to randomly permute the labels of the conditional densities arising during Gibbs sampling. Various applications show very good performance of these estimators in comparison to importance and to reciprocal importance sampling estimators derived from the same importance densities.

Methods for generating synthetic data have become of increasing importance to build large datasets required for Convolution Neural Networks (CNN) based deep learning techniques for a wide range of computer vision applications. In this work, we extend existing methodologies to show how 2D thermal facial data can be mapped to provide 3D facial models. For the proposed research work we have used tufts datasets for generating 3D varying face poses by using a single frontal face pose. The system works by refining the existing image quality by performing fusion based image preprocessing operations. The refined outputs have better contrast adjustments, decreased noise level and higher exposedness of the dark regions. It makes the facial landmarks and temperature patterns on the human face more discernible and visible when compared to original raw data. Different image quality metrics are used to compare the refined version of images with original images. In the next phase of the proposed study, the refined version of images is used to create 3D facial geometry structures by using Convolution Neural Networks (CNN). The generated outputs are then imported in blender software to finally extract the 3D thermal facial outputs of both males and females. The same technique is also used on our thermal face data acquired using prototype thermal camera (developed under Heliaus EU project) in an indoor lab environment which is then used for generating synthetic 3D face data along with varying yaw face angles and lastly facial depth map is generated.

Datasets in sleep science present challenges for machine learning algorithms due to differences in recording setups across clinics. We investigate two deep transfer learning strategies for overcoming the channel mismatch problem for cases where two datasets do not contain exactly the same setup leading to degraded performance in single-EEG models. Specifically, we train a baseline model on multivariate polysomnography data and subsequently replace the first two layers to prepare the architecture for single-channel electroencephalography data. Using a fine-tuning strategy, our model yields similar performance to the baseline model (F1=0.682 and F1=0.694, respectively), and was significantly better than a comparable single-channel model. Our results are promising for researchers working with small databases who wish to use deep learning models pre-trained on larger databases.

In recent years, multi-access edge computing (MEC) is a key enabler for handling the massive expansion of Internet of Things (IoT) applications and services. However, energy consumption of a MEC network depends on volatile tasks that induces risk for energy demand estimations. As an energy supplier, a microgrid can facilitate seamless energy supply. However, the risk associated with energy supply is also increased due to unpredictable energy generation from renewable and non-renewable sources. Especially, the risk of energy shortfall is involved with uncertainties in both energy consumption and generation. In this paper, we study a risk-aware energy scheduling problem for a microgrid-powered MEC network. First, we formulate an optimization problem considering the conditional value-at-risk (CVaR) measurement for both energy consumption and generation, where the objective is to minimize the loss of energy shortfall of the MEC networks and we show this problem is an NP-hard problem. Second, we analyze our formulated problem using a multi-agent stochastic game that ensures the joint policy Nash equilibrium, and show the convergence of the proposed model. Third, we derive the solution by applying a multi-agent deep reinforcement learning (MADRL)-based asynchronous advantage actor-critic (A3C) algorithm with shared neural networks. This method mitigates the curse of dimensionality of the state space and chooses the best policy among the agents for the proposed problem. Finally, the experimental results establish a significant performance gain by considering CVaR for high accuracy energy scheduling of the proposed model than both the single and random agent models.

Beginning from a basic neural-network architecture, we test the potential benefits offered by a range of advanced techniques for machine learning, in particular deep learning, in the context of a typical classification problem encountered in the domain of high-energy physics, using a well-studied dataset: the 2014 Higgs ML Kaggle dataset. The advantages are evaluated in terms of both performance metrics and the time required to train and apply the resulting models. Techniques examined include domain-specific data-augmentation, learning rate and momentum scheduling, (advanced) ensembling in both model-space and weight-space, and alternative architectures and connection methods.

Following the investigation, we arrive at a model which achieves equal performance to the winning solution of the original Kaggle challenge, whilst being significantly quicker to train and apply, and being suitable for use with both GPU and CPU hardware setups. These reductions in timing and hardware requirements potentially allow the use of more powerful algorithms in HEP analyses, where models must be retrained frequently, sometimes at short notice, by small groups of researchers with limited hardware resources. Additionally, a new wrapper library for PyTorch called LUMINis presented, which incorporates all of the techniques studied.

A deep neural network has relieved the burden of feature engineering by human experts, but comparable efforts are instead required to determine an effective architecture. On the other hands, as the size of a network has over-grown, a lot of resources are also invested to reduce its size. These problems can be addressed by sparsification of an over-complete model, which removes redundant parameters or connections by pruning them away after training or encouraging them to become zero during training. In general, however, these approaches are not fully differentiable and interrupt an end-to-end training process with the stochastic gradient descent in that they require either a parameter selection or a soft-thresholding step. In this paper, we propose a fully differentiable sparsification method for deep neural networks, which allows parameters to be exactly zero during training, and thus can learn the sparsified structure and the weights of networks simultaneously using the stochastic gradient descent. We apply the proposed method to various popular models in order to show its effectiveness.

The paper focuses on a novel approach for false-positive reduction (FPR) of nodule candidates in Computer-aided detection (CADe) system after suspicious lesions proposing stage. Unlike common decisions in medical image analysis, the proposed approach considers input data not as 2d or 3d image, but as a point cloud and uses deep learning models for point clouds. We found out that models for point clouds require less memory and are faster on both training and inference than traditional CNN 3D, achieves better performance and does not impose restrictions on the size of the input image, thereby the size of the nodule candidate. We propose an algorithm for transforming 3d CT scan data to point cloud. In some cases, the volume of the nodule candidate can be much smaller than the surrounding context, for example, in the case of subpleural localization of the nodule. Therefore, we developed an algorithm for sampling points from a point cloud constructed from a 3D image of the candidate region. The algorithm guarantees to capture both context and candidate information as part of the point cloud of the nodule candidate. An experiment with creating a dataset from an open LIDC-IDRI database for a feature of the FPR task was accurately designed, set up and described in detail. The data augmentation technique was applied to avoid overfitting and as an upsampling method. Experiments are conducted with PointNet, PointNet++ and DGCNN. We show that the proposed approach outperforms baseline CNN 3D models and demonstrates 85.98 FROC versus 77.26 FROC for baseline models.

Recent advancements in diagnostic learning and development of gesture-based human machine interfaces have driven surface electromyography (sEMG) towards significant importance. Analysis of hand gestures requires an accurate assessment of sEMG signals. The proposed work presents a novel sequential master-slave architecture consisting of deep neural networks (DNNs) for classification of signs from the Indian sign language using signals recorded from multiple sEMG channels. The performance of the master-slave network is augmented by leveraging additional synthetic feature data generated by long short term memory networks. Performance of the proposed network is compared to that of a conventional DNN prior to and after the addition of synthetic data. Up to 14% improvement is observed in the conventional DNN and up to 9% improvement in master-slave network on addition of synthetic data with an average accuracy value of 93.5% asserting the suitability of the proposed approach.

Harnessing data to discover the underlying governing laws or equations that describe the behavior of complex physical systems can significantly advance our modeling, simulation and understanding of such systems in various science and engineering disciplines. Recent advances in sparse identification show encouraging success in distilling closed-form governing equations from data for a wide range of nonlinear dynamical systems. However, the fundamental bottleneck of this approach lies in the robustness and scalability with respect to data scarcity and noise. This work introduces a novel physics-informed deep learning framework to discover governing partial differential equations (PDEs) from scarce and noisy data for nonlinear spatiotemporal systems. In particular, this approach seamlessly integrates the strengths of deep neural networks for rich representation learning, automatic differentiation and sparse regression to approximate the solution of system variables, compute essential derivatives, as well as identify the key derivative terms and parameters that form the structure and explicit expression of the PDEs. The efficacy and robustness of this method are demonstrated on discovering a variety of PDE systems with different levels of data scarcity and noise. The resulting computational framework shows the potential for closed-form model discovery in practical applications where large and accurate datasets are intractable to capture.

Identification of input data points relevant for the classifier (i.e. serve as the support vector) has recently spurred the interest of researchers for both interpretability as well as dataset debugging. This paper presents an in-depth analysis of the methods which attempt to identify the influence of these data points on the resulting classifier. To quantify the quality of the influence, we curated a set of experiments where we debugged and pruned the dataset based on the influence information obtained from different methods. To do so, we provided the classifier with mislabeled examples that hampered the overall performance. Since the classifier is a combination of both the data and the model, therefore, it is essential to also analyze these influences for the interpretability of deep learning models. Analysis of the results shows that some interpretability methods can detect mislabels better than using a random approach, however, contrary to the claim of these methods, the sample selection based on the training loss showed a superior performance.

The large volumes of Sentinel-1 data produced over Europe are being used to develop pan-national ground motion services. However, simple analysis techniques like thresholding cannot detect and classify complex deformation signals reliably making providing usable information to a broad range of non-expert stakeholders a challenge. Here we explore the applicability of deep learning approaches by adapting a pre-trained convolutional neural network (CNN) to detect deformation in a national-scale velocity field. For our proof-of-concept, we focus on the UK where previously identified deformation is associated with coal-mining, ground water withdrawal, landslides and tunnelling. The sparsity of measurement points and the presence of spike noise make this a challenging application for deep learning networks, which involve calculations of the spatial convolution between images. Moreover, insufficient ground truth data exists to construct a balanced training data set, and the deformation signals are slower and more localised than in previous applications. We propose three enhancement methods to tackle these problems: i) spatial interpolation with modified matrix completion, ii) a synthetic training dataset based on the characteristics of real UK velocity map, and iii) enhanced over-wrapping techniques. Using velocity maps spanning 2015-2019, our framework detects several areas of coal mining subsidence, uplift due to dewatering, slate quarries, landslides and tunnel engineering works. The results demonstrate the potential applicability of the proposed framework to the development of automated ground motion analysis systems.

Benedikt Bauer, Michael Kohler.

Source: The Annals of Statistics, Volume 47, Number 4, 2261--2285.

Abstract:
Assuming that a smoothness condition and a suitable restriction on the structure of the regression function hold, it is shown that least squares estimates based on multilayer feedforward neural networks are able to circumvent the curse of dimensionality in nonparametric regression. The proof is based on new approximation results concerning multilayer feedforward neural networks with bounded weights and a bounded number of hidden neurons. The estimates are compared with various other approaches by using simulated data.

Ningshan Zhang, Kyle Schmaus, Patrick O. Perry.

Source: The Annals of Applied Statistics, Volume 13, Number 4, 2260--2288.

Abstract:
We consider a particular instance of a common problem in recommender systems, using a database of book reviews to inform user-targeted recommendations. In our dataset, books are categorized into genres and subgenres. To exploit this nested taxonomy, we use a hierarchical model that enables information pooling across across similar items at many levels within the genre hierarchy. The main challenge in deploying this model is computational. The data sizes are large and fitting the model at scale using off-the-shelf maximum likelihood procedures is prohibitive. To get around this computational bottleneck, we extend a moment-based fitting procedure proposed for fitting single-level hierarchical models to the general case of arbitrarily deep hierarchies. This extension is an order of magnitude faster than standard maximum likelihood procedures. The fitting method can be deployed beyond recommender systems to general contexts with deeply nested hierarchical generalized linear mixed models.

Vinod Venkatraman
Mar 9, 2011; 31:3712-3718
BehavioralSystemsCognitive

Adam J. Krause
Mar 20, 2019; 39:2291-2300
BehavioralSystemsCognitive

Michele Bellesi
May 24, 2017; 37:5263-5273
Cellular

With measures to stem the spread of COVID-19 putting a chokehold on their filming capabilities, advertising agencies are enhancing old content with new tech, including deepfakes. Deepfakes typically blend one person's likeness, or parts thereof, with the image of another person. Ad agencies are so restricted in how they can generate content, they'll explore anything that can be computer-generated.

People have been giving presentations for thousands of years, from Moses with his stone tablets to Elon Musk revealing his grand plans to colonize Mars. While the elements of a great pitchman generally have remained the same over the past 5,000 years -- conviction, charisma, credibility -- today's successful presenters do more than just get in front of an audience and talk.

We took a look around and put together a list of  Twitter accounts to keep you informed about what is happening in the world of soils.  Here are, in alphabetical order, ten voices on twitter you should follow for the latest on soils: @agriculturesnet The AgriCultures Network shares knowledge on small-scale family farming and agroecology. With agroecology we can build soils for life! http://t.co/pN62odtLt9 [...]

Peste des petits ruminants (PPR) or sheep and goat plague is a highly contagious animal disease affecting small ruminants. An estimated 300 million families who rely on small ruminants, such as sheep and goats, as a source of food and income are at risk of losing their livelihoods and may be forced to migrate, particularly in areas where food insecurity, other resource shortages [...]

We often talk about the future of food, but what about its history? In our day to day lives, we might not realize that some of our staple foods have come from extraordinary agricultural traditions that are deeply rooted in our cultures and identity.

Where would you find the world’s largest recreation center and the most natural supermarket? Forests wouldn’t have been your first answer, would it? That’s the thing about forests. They keep secrets.

What does William Shakespeare have in common with Mexican beekeeper Francisco Lenin Bartolo Reyes? Both men understand the importance of the honey bee, a small but invaluable ally of the human race.

Pizza and pasta are pretty obviously out, but what are the other no-nos?

‘What on earth were they doing there?’ one researcher asks

The vineyard deploys a daily bird-based battalion to pluck snails and insects off their plants

Starved of resources, these hardy bacteria still eke out a living, suggesting life forms could survive in the harsh habitats on other planets

Blending marshmallows with scientific rigor, the contest offers levity during a difficult time

We’re really, really sorry

After missing years of shears, the voluminous creature had ballooned to about five times the size of a typical sheep

A study of microbial communities at the site of a 1989 deep-sea mining test suggests the fragile ecosystem may take half a century to fully recover

When Elizabeth May, parliamentary leader of the federal Green Party, proclaimed on Tuesday that "oil is dead," she was correct in a philosophical sense. But not in a practical, real world sense.

Tensions are rising on Manitoulin Island because a First Nation is stopping travellers on provincial highways that go through the community. But opinions on M'Chigeeng's attempt to protect its people from COVID-19 are not divided along racial lines. 

Tampa Bay Rays' Blake Snell claimed champion status after defeating Lucas Giolito of the Chicago White Sox in the inaugural MLB The Show player league on Sunday.

A former groundskeeper for the Expos recently told the Montreal Gazette that Pete Rose, who played less than a full season with the team, routinely had an Olympic Stadium staffer cork his bats in 1984.

Sign makers in P.E.I. have been busy since the province announced its plans to ease back COVID-19 restrictions, as businesses are ordering signs and decals ahead of reopening.

OK, you’re gonna hear a lot about Joementum.

Karina LeBlanc was returning home from her second hospital visit after giving birth to her first child, only this time she would have to spend 14 days in self-isolation after doctors feared she contracted COVID-19 during her stay.

More than a dozen First Nations in northeastern Ontario have closed their borders to outsiders during the pandemic. It's creating some friction, but in the long-run could help to better define what Indigenous self-government really means. 

It's not often people want to hang onto winter, but a Summerside, P.E.I. woman has kept a piece of it in her freezer for over a decade: a snowball in a ziplock bag.

Hamilton Conservation Authority is re-opening the Hamilton-to-Branford Rail Trail, while the city announced the reopening of the Hamilton Waterfront Trail, between Confederation Park and the Burlington Lift Bridge.