-- Despite the superiority of convolutional neural networks demonstrated in time series modeling and forecasting, it has not been fully explored on the design of the neural network architecture as well as the tuning of the hyper-parameters. Inspired by the iterative construction strategy for building a random multilayer perceptron, we propose a novel Error-feedback Stochastic Configuration (ESC) strategy to construct a random Convolutional Neural Network (ESC-CNN) for time series forecasting task, which builds the network architecture adaptively. The ESC strategy suggests that random filters and neurons of the error-feedback fully connected layer are incre-mentally added in a manner that they can steadily compensate the prediction error during the construction process, and a filter selection strategy is introduced to secure that ESC-CNN holds the universal approximation property, providing helpful information at each iterative process for the prediction. The performance of ESC-CNN is justified on its prediction accuracy for one-step- ahead and multi-step-ahead forecasting tasks. Comprehensive experiments on a synthetic dataset and two real-world datasets show that the proposed ESC-CNN not only outperforms the state-of-art random neural networks, but also exhibits strong predictive power in comparison to trained Convolution Neural Networks and Long Short-T erm Memory models, demonstrating the effectiveness of ESC-CNN in time series forecasting. Time series forecasting, especially computational intelligence enabled time series forecasting, is of great importance for a learning system in dynamic environments, and plays a vital role in applications such as in finance [1]-[3], energy [4]- [6], traffic [7]-[9], and electric load [10]-[12], etc. Recently, convolutional neural networks (CNNs) have been successfully implemented for time series forecasting tasks, benefiting from its strength in extracting local features via multiple convolu-tional filters and learning representation by fully connected layers [13]-[16].

We propose a deep learning strategy to compute the mean curvature of an implicit level-set representation of an interface. Our approach is based on fitting neural networks to synthetic datasets of pairs of nodal $\phi$ values and curvatures obtained from circular interfaces immersed in different uniform resolutions. These neural networks are multilayer perceptrons that ingest sample level-set values of grid points along a free boundary and output the dimensionless curvature at the center vertices of each sampled neighborhood. Evaluations with irregular (smooth and sharp) interfaces, in both uniform and adaptive meshes, show that our deep learning approach is systematically superior to conventional numerical approximation in the $L^2$ and $L^\infty$ norms. Our methodology is also less sensitive to steep curvatures and approximates them well with samples collected with fewer iterations of the reinitialization equation, often needed to regularize the underlying implicit function. Additionally, we show that an application-dependent map of local resolutions to neural networks can be constructed and employed to estimate interface curvatures more efficiently than using typically expensive numerical schemes while still attaining comparable or higher precision.

The ultimate aim of artificial intelligence research is to develop agents with truly intelligent behaviors, akin to those found in humans and animals. To this end, a number of tools and techniques have been developed. In recent years, two approaches in particular - deep learning (DL) and reinforcement learning (RL), seem to have made considerable progress towards this goal. Both these fields have been widely studied, with numerous successful examples [22, 29, 42, 25, 40] reported, particularly in recent years. However, even with the unprecedented success of recent approaches such as deep RL [28, 27, 36], poor sample efficiency and limited generalization remain major concerns to be addressed, keeping in view the ultimate goal of developing general purpose agents. The poor generalization capability of DL is exposed by its liability to deception when presented with adversarial examples [30, 39]. Recent work [38], showed that it was possible to hurt the performance of DLbased image recognition systems by carefully altering just a single pixel.

Decentralized Parallel SGD (D-PSGD) and its asynchronous variant Asynchronous Parallel SGD (AD-PSGD) is a family of distributed learning algorithms that have been demonstrated to perform well for large-scale deep learning tasks. One drawback of (A)D-PSGD is that the spectral gap of the mixing matrix decreases when the number of learners in the system increases, which hampers convergence. In this paper, we investigate techniques to accelerate (A)D-PSGD based training by improving the spectral gap while minimizing the communication cost. We demonstrate the effectiveness of our proposed techniques by running experiments on the 2000-hour Switchboard speech recognition task and the ImageNet computer vision task. On an IBM P9 supercomputer, our system is able to train an LSTM acoustic model in 2.28 hours with 7.5% WER on the Hub5-2000 Switchboard (SWB) test set and 13.3% WER on the CallHome (CH) test set using 64 V100 GPUs and in 1.98 hours with 7.7% WER on SWB and 13.3% WER on CH using 128 V100 GPUs, the fastest training time reported to date. Index T erms -- distributed training, decentralized SGD, parallel computing, automatic speech recognition, image recognition.

Based on interviews with 28 organizations, we found that industry practitioners are not equipped with tactical and strategic tools to protect, detect and respond to attacks on their Machine Learning (ML) systems. We leverage the insights from the interviews and we enumerate the gaps in perspective in securing machine learning systems when viewed in the context of traditional software security development. We write this paper from the perspective of two personas: developers/ML engineers and security incident responders who are tasked with securing ML systems as they are designed, developed and deployed ML systems. The goal of this paper is to engage researchers to revise and amend the Security Development Lifecycle for industrial-grade software in the adversarial ML era.

Purpose: To construct a neural network model that can learn the different diagnosing strategies of radiologists to better classify aneurysm status in magnetic resonance angiography images. Materials and methods: This retrospective study included 3423 time-of-flight brain magnetic resonance angiography image series (subjects: male 1843 [mean age, 50.2 +/- 11.7 years], female 1580 [50.8 +/- 11.3 years]) recorded from November 2017 through January 2019. The image series were read independently for aneurysm status by one of four board-certified radiologists, who were assisted by an established deep learning-based computer-assisted diagnosis (CAD) system. The constructed neural networks were trained to classify the aneurysm status of zero to five aneurysm-suspicious areas suggested by the CAD system for each image series, and any additional aneurysm areas added by the radiologists, and this classification was compared with the judgment of the annotating radiologist. Image series were randomly allocated to training and testing data in an 8:2 ratio. The accuracy of the classification was compared by receiver operating characteristic analysis between the control model that accepted only image data as input and the proposed model that additionally accepted the information of who the annotating radiologist was. The DeLong test was used to compare areas under the curves (P < 0.05 was considered significant). Results: The area under the curve was larger in the proposed model (0.845) than in the control model (0.793), and the difference was significant (P < 0.0001). Conclusion: The proposed model improved classification accuracy by learning the diagnosis strategies of individual annotating radiologists.

AI algorithms, and machine learning (ML) techniques in particular, are increasingly important to individuals' lives, but have caused a range of privacy concerns addressed by, e.g., the European GDPR. Using cryptographic techniques, it is possible to perform inference tasks remotely on sensitive client data in a privacy-preserving way: the server learns nothing about the input data and the model predictions, while the client learns nothing about the ML model (which is often considered intellectual property and might contain traces of sensitive data). While such privacy-preserving solutions are relatively efficient, they are mostly targeted at neural networks, can degrade the predictive accuracy, and usually reveal the network's topology. Furthermore, existing solutions are not readily accessible to ML experts, as prototype implementations are not well-integrated into ML frameworks and require extensive cryptographic knowledge. In this paper, we present CryptoSPN, a framework for privacy-preserving inference of sum-product networks (SPNs). SPNs are a tractable probabilistic graphical model that allows a range of exact inference queries in linear time. Specifically, we show how to efficiently perform SPN inference via secure multi-party computation (SMPC) without accuracy degradation while hiding sensitive client and training information with provable security guarantees. Next to foundations, CryptoSPN encompasses tools to easily transform existing SPNs into privacy-preserving executables. Our empirical results demonstrate that CryptoSPN achieves highly efficient and accurate inference in the order of seconds for medium-sized SPNs.

Recently semantic parsing in context has received a considerable attention, which is challenging since there are complex contextual phenomena. Previous works verified their proposed methods in limited scenarios, which motivates us to conduct an exploratory study on context modeling methods under real-world semantic parsing in context. We present a grammar-based decoding semantic parser and adapt typical context modeling methods on top of it. We evaluate 13 context modeling methods on two large complex cross-domain datasets, and our best model achieves state-of-the-art performances on both datasets with significant improvements. Furthermore, we summarize the most frequent contextual phenomena, with a fine-grained analysis on representative models, which may shed light on potential research directions.

Beginning from a basic neural-network architecture, we test the potential benefits offered by a range of advanced techniques for machine learning and 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 requiring about 1% of the training time and less than 5% of the inference time using much less specialised hardware. Additionally, a new wrapper library for PyTorch called LUMIN is presented, which incorporates all of the techniques studied.

Strictly enforcing orthonormality constraints on parameter matrices has been shown advantageous in deep learning. This amounts to Riemannian optimization on the Stiefel manifold, which, however, is computationally expensive. To address this challenge, we present two main contributions: (1) A new efficient retraction map based on an iterative Cayley transform for optimization updates, and (2) An implicit vector transport mechanism based on the combination of a projection of the momentum and the Cayley transform on the Stiefel manifold. We specify two new optimization algorithms: Cayley SGD with momentum, and Cayley ADAM on the Stiefel manifold. Convergence of Cayley SGD is theoretically analyzed. Our experiments for CNN training demonstrate that both algorithms: (a) Use less running time per iteration relative to existing approaches that enforce orthonormality of CNN parameters; and (b) Achieve faster convergence rates than the baseline SGD and ADAM algorithms without compromising the performance of the CNN. Cayley SGD and Cayley ADAM are also shown to reduce the training time for optimizing the unitary transition matrices in RNNs.