A recent "deep learning" algorithm--despite having no innate knowledge of solar physics--could provide more accurate predictions of how the sun affects our planet than current models based on scientific understanding. For decades, people have tried to predict the impact of the sun on our planet's atmosphere. Up until now, algorithms based on solar physics have been used to predict the shifting density of Earth's atmosphere. But with so many variables affecting the complex and dynamic layers of gases around Earth, artificial intelligence (AI) could provide real improvements in this area because of its ability to handle vastly more complex data, with important implications for how we fly missions in Earth orbit. The conditions in space vary depending on the mood swings of the sun, known as "space weather."

The Livermore Big Artificial Neural Network toolkit (LBANN) is an open-source, HPC-centric, deep learning training framework that is optimized to compose multiple levels of parallelism. LBANN provides model-parallel acceleration through domain decomposition to optimize for strong scaling of network training. It also allows for composition of model-parallelism with both data parallelism and ensemble training methods for training large neural networks with massive amounts of data. LBANN is able to advantage of tightly-coupled accelerators, low-latency high-bandwidth networking, and high-bandwidth parallel file systems. LBANN supports state-of-the-art training algorithms such as unsupervised, self-supervised, and adversarial (GAN) training methods in addition to traditional supervised learning.

Deep learning has vast ranging applications and its application in the healthcare industry always fascinates me. As a keen learner and a Kaggle noob, I decided to work on the Malaria Cells dataset to get some hands-on experience and learn how to work with Convolutional Neural Networks, Keras and images on the Kaggle platform. One of the many things I like about Kaggle is the immense knowledge it holds in the form of Kernels and Discussions. Taking cues and references from various kernels and experts really helped me get better at producing highly accurate results. Do look at other kernels and understand their approach to gain more insights for your own development and knowledge building.

Those concerns spurred research group OpenAI to initially dumb down the public release of one of these models, the text generator GPT-2, when it was unveiled in February. But the creators recently reconsidered and published the full version, satisfied that there was "no strong evidence" of its misuse in the intervening months. With that in mind, we took a look at how these models fare at performing our own jobs here at Adweek--or at least passably imitating our work. We used an online fake news tool called Grover created by the University of Washington's Allen Institute for Artificial Intelligence. It's built on the same framework as GPT-2, but with the added ability to match output to the style of a particular website within the millions on which it was trained--in this case, adweek.com.

Reconstruction of seismic data with missing traces is a long-standing issue in seismic data processing. In recent years, rank reduction operations are being commonly utilized to overcome this problem, which require the rank of seismic data to be a prior. However, the rank of field data is unknown; usually it requires much time to manually adjust the rank and just obtain an approximated rank. Methods based on deep learning require very large datasets for training; however acquiring large datasets is difficult owing to physical or financial constraints in practice. Therefore, in this work, we developed a novel method based on unsupervised learning using the intrinsic properties of a convolutional neural network known as U-net, without training datasets. Only one undersampled seismic data was needed, and the deep seismic prior of input data could be exploited by the network itself, thus making the reconstruction convenient. Furthermore, this method can handle both irregular and regular seismic data. Synthetic and field data were tested to assess the performance of the proposed algorithm (DSPRecon algorithm); the advantages of using our method were evaluated by comparing it with the singular spectrum analysis (SSA) method for irregular data reconstruction and de-aliased Cadzow method for regular data reconstruction. Experimental results showed that our method provided better reconstruction performance than the SSA or Cadzow methods. The recovered signal-to-noise ratios (SNRs) were 32.68 dB and 19.11 dB for the DSPRecon and SSA algorithms, respectively. Those for the DSPRecon and Cadzow methods were 35.91 dB and 15.32 dB, respectively.

DPM: A deep learning PDE augmentation method (with application to large-eddy simulation) Jonathan B. Freund, Jonathan F. MacArt †, and Justin Sirignano ‡§ November 22, 2019 Abstract Machine learning for scientific applications faces the challenge of limited data. We propose a framework that leverages a priori known physics to reduce overfitting when training on relatively small datasets. A deep neural network is embedded in a partial differential equation (PDE) that expresses the known physics and learns to describe the corresponding unknown or unrepresented physics from the data. Crafted as such, the neural network can also provide corrections for erroneously represented physics, such as discretization errors associated with the PDE's numerical solution. Once trained, the deep learning PDE model (DPM) can make out-of-sample predictions for new physical parameters, geometries, and boundary conditions. Estimating the embedded neural network requires optimizing over the entire PDE, which itself is a function of the neural network. Adjoint partial differential equations are used to efficiently calculate the high-dimensional gradient of the objective function with respect to the neural network parameters. A stochastic adjoint method (SAM), similar in spirit to stochastic gradient descent, further accelerates training. The approach is demonstrated and evaluated for turbulence predictions using large-eddy simulation (LES), a filtered version of the Navier-Stokes equation containing unclosed sub-filter-scale terms. High-fidelity direct numerical simulations (DNS) of decaying isotropic turbulence provide the training and testing data. The DPM outperforms the widely-used constant-coefficient and dynamic Smagorinsky models, even for filter sizes so large that these established models become qualitatively incorrect. It also significantly outperforms a priori trained models, which do not account for the full PDE. For comparable accuracy, the overall cost is reduced. Simulations of the DPM are accelerated by efficient GPU implementations of network evaluations. Measures of discretization errors, which are well-known to be consequential in LES, suggest that the ability of the training formulation to correct for these errors Mechanical Science & Engineering and Aerospace Engineering, University of Illinois at Urbana-Champaign, jbfre-und@illinois.edu

Procedurally generating cohesive and interesting game environments is challenging and time-consuming. In order for the relationships between the game elements to be natural, common-sense has to be encoded into arrangement of the elements. In this work, we investigate a machine learning approach for world creation using content from the multi-player text adventure game environment LIGHT. We introduce neural network based models to compositionally arrange locations, characters, and objects into a coherent whole. In addition to creating worlds based on existing elements, our models can generate new game content. Humans can also leverage our models to interactively aid in worldbuilding. We show that the game environments created with our approach are cohesive, diverse, and preferred by human evaluators compared to other machine learning based world construction algorithms.

Overparameterized neural networks can be highly accurate on average on an i.i.d. test set yet consistently fail on atypical groups of the data (e.g., by learning spurious correlations that hold on average but not in such groups). Distributionally robust optimization (DRO) allows us to learn models that instead minimize the worst-case training loss over a set of pre-defined groups. However, we find that naively applying group DRO to overparameterized neural networks fails: these models can perfectly fit the training data, and any model with vanishing average training loss also already has vanishing worst-case training loss. Instead, their poor worst-case performance arises from poor generalization on some groups. By coupling group DRO models with increased regularization---stronger-than-typical $\ell_2$ regularization or early stopping---we achieve substantially higher worst-group accuracies, with 10-40 percentage point improvements on a natural language inference task and two image tasks, while maintaining high average accuracies. Our results suggest that regularization is critical for worst-group generalization in the overparameterized regime, even if it is not needed for average generalization. Finally, we introduce and give convergence guarantees for a stochastic optimizer for the group DRO setting, underpinning the empirical study above.

Deep learning methods, which have found successful applications in fields like image classification and natural language processing, have recently been applied to source code analysis too, due to the enormous amount of freely available source code (e.g., from open-source software repositories). In this work, we elaborate upon a state-of-the-art approach to the representation of source code that uses information about its syntactic structure, and we adapt it to represent source changes (i.e., commits). We use this representation to classify security-relevant commits. Because our method uses transfer learning (that is, we train a network on a "pretext task" for which abundant labeled data is available, and then we use such network for the target task of commit classification, for which fewer labeled instances are available), we studied the impact of pre-training the network using two different pretext tasks versus a randomly initialized model. Our results indicate that representations that leverage the structural information obtained through code syntax outperform token-based representations. Furthermore, the performance metrics obtained when pre-training on a loosely related pretext task with a very large dataset ($>10^6$ samples) were surpassed when pretraining on a smaller dataset ($>10^4$ samples) but for a pretext task that is more closely related to the target task.

Recently, artificial neural networks (ANNs) in conjunction with stochastic gradient descent optimization methods have been employed to approximately compute solutions of possibly rather high-dimensional partial differential equations (PDEs). Very recently, there have also been a number of rigorous mathematical results in the scientific literature which examine the approximation capabilities of such deep learning based approximation algorithms for PDEs. These mathematical results from the scientific literature prove in part that algorithms based on ANNs are capable of overcoming the curse of dimensionality in the numerical approximation of high-dimensional PDEs. In these mathematical results from the scientific literature usually the error between the solution of the PDE and the approximating ANN is measured in the $L^p$-sense with respect to some $p \in [1,\infty)$ and some probability measure. In many applications it is, however, also important to control the error in a uniform $L^\infty$-sense. The key contribution of the main result of this article is to develop the techniques to obtain error estimates between solutions of PDEs and approximating ANNs in the uniform $L^\infty$-sense. In particular, we prove that the number of parameters of an ANN to uniformly approximate the classical solution of the heat equation in a region $ [a,b]^d $ for a fixed time point $ T \in (0,\infty) $ grows at most polynomially in the dimension $ d \in \mathbb{N} $ and the reciprocal of the approximation precision $ \varepsilon > 0 $. This shows that ANNs can overcome the curse of dimensionality in the numerical approximation of the heat equation when the error is measured in the uniform $L^\infty$-norm.