The impact of gradient noise on training deep models is widely acknowledged but not well understood. In this context, we study the distribution of gradients during training. We introduce a method, Gradient Clustering, to minimize the variance of average mini-batch gradient with stratified sampling. We prove that the variance of average mini-batch gradient is minimized if the elements are sampled from a weighted clustering in the gradient space. We measure the gradient variance on common deep learning benchmarks and observe that, contrary to common assumptions, gradient variance increases during training, and smaller learning rates coincide with higher variance. In addition, we introduce normalized gradient variance as a statistic that better correlates with the speed of convergence compared to gradient variance.

We present the first system that provides real-time probe movement guidance for acquiring standard planes in routine freehand obstetric ultrasound scanning. Such a system can contribute to the worldwide deployment of obstetric ultrasound scanning by lowering the required level of operator expertise. The system employs an artificial neural network that receives the ultrasound video signal and the motion signal of an inertial measurement unit (IMU) that is attached to the probe, and predicts a guidance signal. The network termed US-GuideNet predicts either the movement towards the standard plane position (goal prediction), or the next movement that an expert sonographer would perform (action prediction). While existing models for other ultrasound applications are trained with simulations or phantoms, we train our model with real-world ultrasound video and probe motion data from 464 routine clinical scans by 17 accredited sonographers. Evaluations for 3 standard plane types show that the model provides a useful guidance signal with an accuracy of 88.8 % for goal prediction and 90.9 % for action prediction.

Network security applications, including intrusion detection systems of deep neural networks, are increasing rapidly to make detection task of anomaly activities more accurate and robust. With the rapid increase of using DNN and the volume of data traveling through systems, different growing types of adversarial attacks to defeat them create a severe challenge. In this paper, we focus on investigating the effectiveness of different evasion attacks and how to train a resilience deep learning-based IDS using different Neural networks, e.g., convolutional neural networks (CNN) and recurrent neural networks (RNN). We use the min-max approach to formulate the problem of training robust IDS against adversarial examples using two benchmark datasets. Our experiments on different deep learning algorithms and different benchmark datasets demonstrate that defense using an adversarial training-based min-max approach improves the robustness against the five well-known adversarial attack methods.

While deep learning methods continue to improve This paper describes initial work on URSABench, an open in predictive accuracy on a wide range source suite of benchmarking tools for assessment of approximate of application domains, significant issues remain Bayesian inference methods applied to deep with other aspects of their performance including neural network classification tasks. URSABench includes their ability to quantify uncertainty and their benchmark models, data sets, tasks and evaluation metrics robustness. Recent advances in approximate focused on simultaneously assessing the uncertainty Bayesian inference hold significant promise for quantification performance, robustness, computational scalability addressing these concerns, but the computational and accuracy of learning and inference methods.

In most real world scenarios, a policy trained by reinforcement learning in one environment needs to be deployed in another, potentially quite different environment. However, generalization across different environments is known to be hard. A natural solution would be to keep training after deployment in the new environment, but this cannot be done if the new environment offers no reward signal. Our work explores the use of self-supervision to allow the policy to continue training after deployment without using any rewards. While previous methods explicitly anticipate changes in the new environment, we assume no prior knowledge of those changes yet still obtain significant improvements. Empirical evaluations are performed on diverse environments from DeepMind Control suite and ViZDoom. Our method improves generalization in 25 out of 30 environments across various tasks, and outperforms domain randomization on a majority of environments.

We propose a new model of Bayesian Neural Networks to not only detect the events of compact binary coalescence in the observational data of gravitational waves (GW) but also identify the time periods of the associated GW waveforms before the events. This is achieved by incorporating the Bayesian approach into the CLDNN classifier, which integrates together the Convolutional Neural Network (CNN) and the Long Short-Term Memory Recurrent Neural Network (LSTM). Our model successfully detect all seven BBH events in the LIGO Livingston O2 data, with the periods of their GW waveforms correctly labeled. The ability of a Bayesian approach for uncertainty estimation enables a newly defined `awareness' state for recognizing the possible presence of signals of unknown types, which is otherwise rejected in a non-Bayesian model. Such data chunks labeled with the awareness state can then be further investigated rather than overlooked. Performance tests show that our model recognizes 90% of the events when the optimal signal-to-noise ratio $\rho_\text{opt} >7$ (100% when $\rho_\text{opt} >8.5$) and successfully labels more than 95% of the waveform periods when $\rho_\text{opt} >8$. The latency between the arrival of peak signal and generating an alert with the associated waveform period labeled is only about 20 seconds for an unoptimized code on a moderate GPU-equipped personal computer. This makes our model possible for nearly real-time detection and for forecasting the coalescence events when assisted with deeper training on a larger dataset using the state-of-art HPCs.

Mathematical modelling is ubiquitous in the financial industry and drives key decision processes. Any given model provides only a crude approximation to reality and the risk of using an inadequate model is hard to detect and quantify. By contrast, modern data science techniques are opening the door to more robust and data-driven model selection mechanisms. However, most machine learning models are "black-boxes" as individual parameters do not have meaningful interpretation. The aim of this paper is to combine the above approaches achieving the best of both worlds. Combining neural networks with risk models based on classical stochastic differential equations (SDEs), we find robust bounds for prices of derivatives and the corresponding hedging strategies while incorporating relevant market data. The resulting model called neural SDE is an instantiation of generative models and is closely linked with the theory of causal optimal transport. Neural SDEs allow consistent calibration under both the risk-neutral and the real-world measures. Thus the model can be used to simulate market scenarios needed for assessing risk profiles and hedging strategies. We develop and analyse novel algorithms needed for efficient use of neural SDEs. We validate our approach with numerical experiments using both local and stochastic volatility models.

We investigate two causes for adversarial vulnerability in deep neural networks: bad data and (poorly) trained models. When trained with SGD, deep neural networks essentially achieve zero training error, even in the presence of label noise, while also exhibiting good generalization on natural test data, something referred to as benign overfitting [2, 10]. However, these models are vulnerable to adversarial attacks. We identify label noise as one of the causes for adversarial vulnerability, and provide theoretical and empirical evidence in support of this. Surprisingly, we find several instances of label noise in datasets such as MNIST and CIFAR, and that robustly trained models incur training error on some of these, i.e. they don't fit the noise. However, removing noisy labels alone does not suffice to achieve adversarial robustness. Standard training procedures bias neural networks towards learning "simple" classification boundaries, which may be less robust than more complex ones. We observe that adversarial training does produce more complex decision boundaries. We conjecture that in part the need for complex decision boundaries arises from sub-optimal representation learning. By means of simple toy examples, we show theoretically how the choice of representation can drastically affect adversarial robustness.

Current statistical post-processing methods for probabilistic weather forecasting are not capable of using full spatial patterns from the numerical weather prediction (NWP) model. In this paper we incorporate spatial wind speed information by using convolutional neural networks (CNNs) and obtain probabilistic wind speed forecasts in the Netherlands for 48 hours ahead, based on KNMI's Harmonie-Arome NWP model. The CNNs are shown to have higher Brier skill scores for medium to higher wind speeds, as well as a better continuous ranked probability score (CRPS), than fully connected neural networks and quantile regression forests.

In this work, we propose a simple yet effective meta-learning algorithm in the semi-supervised settings. We notice that existing consistency-based approaches mostly do not consider the essential role of the label information for consistency regularization. To alleviate this issue, we bridge the relationship between the consistency loss and label information by unfolding and differentiating through one optimization step. Specifically, we exploit the pseudo labels of the unlabeled examples which are guided by the meta-gradients of the labeled data loss so that the model can generalize well on the labeled examples. In addition, we introduce a simple first-order approximation to avoid computing higher-order derivatives and guarantee scalability. Extensive evaluations on the SVHN, CIFAR, and ImageNet datasets demonstrate that the proposed algorithm performs favorably against the state-of-the-art methods.