In computational fluid dynamics, it often takes days or weeks to simulate the aerodynamic behavior of designs such as jets, spacecraft, or gas turbine engines. One of the biggest open problems in the field is how to simulate such systems much more quickly with sufficient accuracy. Many approaches have been tried; some involve models of the underlying physics, while others are model-free and make predictions based only on existing simulation data. However, all previous approaches have severe shortcomings or limitations. We present a novel approach: we reformulate the prediction problem to effectively increase the size of the otherwise tiny datasets, and we introduce a new neural network architecture (called a cluster network) with an inductive bias well-suited to fluid dynamics problems. Compared to state-of-the-art model-based approximations, we show that our approach is nearly as accurate, an order of magnitude faster and vastly easier to apply. Moreover, our method outperforms previous model-free approaches.

Generative Adversarial Networks (GAN) have gained a lot of popularity from their introduction in 2014 till present. Research on GAN is rapidly growing and there are many variants of the original GAN focusing on various aspects of deep learning. GAN are perceived as the most impactful direction of machine learning in the last decade. This paper focuses on the application of GAN in autonomous driving including topics such as advanced data augmentation, loss function learning, semi-supervised learning, etc. We formalize and review key applications of adversarial techniques and discuss challenges and open problems to be addressed.

An active area of research is to increase the safety of self-driving vehicles. Although safety cannot be guarenteed completely, the capability of a vehicle to predict the future trajectories of its surrounding vehicles could help ensure this notion of safety to a greater deal. We cast the trajectory forecast problem in a multi-time step forecasting problem and develop a Convolutional Neural Network based approach to learn from trajectory sequences generated from completely raw dataset in real-time. Results show improvement over baselines.

The robustness of deep models to adversarial attacks has gained significant attention in recent years, so has the model compactness and efficiency: yet the two have been mostly studied separately, with few relationships drawn between each other. This paper is concerned with: how can we combine the best of both worlds, obtaining a robust and compact network? The answer is not as straightforward as it may seem, since the two goals of model robustness and compactness may contradict from time to time. We formally study this new question, by proposing a novel Adversarially Trained Model Compression (ATMC) framework. A unified constrained optimization formulation is designed, with an efficient algorithm developed. An extensive group of experiments are then carefully designed and presented, demonstrating that ATMC obtains remarkably more favorable trade-off among model size, accuracy and robustness, over currently available alternatives in various settings.

Blind image deblurring remains a topic of enduring interest. Learning based approaches, especially those that employ neural networks have emerged to complement traditional model based methods and in many cases achieve vastly enhanced performance. That said, neural network approaches are generally empirically designed and the underlying structures are difficult to interpret. In recent years, a promising technique called algorithm unrolling has been developed that has helped connect iterative algorithms such as those for sparse coding to neural network architectures. However, such connections have not been made yet for blind image deblurring. In this paper, we propose a neural network architecture based on this idea. We first present an iterative algorithm that may be considered as a generalization of the traditional total-variation regularization method in the gradient domain. We then unroll the algorithm to construct a neural network for image deblurring which we refer to as Deep Unrolling for Blind Deblurring (DUBLID). Key algorithm parameters are learned with the help of training images. Our proposed deep network DUBLID achieves significant practical performance gains while enjoying interpretability at the same time. Extensive experimental results show that DUBLID outperforms many state-of-the-art methods and in addition is computationally faster.

A novel hierarchical Deep Neural Network (DNN) model is presented to address the task of end-to-end driving. The model consists of a master classifier network which determines the driving task required from an input stereo image and directs said image to one of a set of subservient network regression models that perform inference and output a steering command. These subservient networks are designed and trained for a specific driving task: straightaway, swerve maneuver, tight turn, gradual turn, and chicane. Using this modular network strategy allows for two primary advantages: an overall reduction in the amount of data required to train the complete system, and for model tailoring where more complex models can be used for more challenging tasks while simplified networks can handle more mundane tasks. It is this latter facet of the model that makes the approach attractive to a number of applications beyond the current vehicle steering strategy.

Despite the fact that deep neural networks are powerful models and achieve appealing results on many tasks, they are too gigantic to be deployed on edge devices like smart-phones or embedded sensor nodes. There has been efforts to compress these networks, and a popular method is knowledge distillation, where a large (a.k.a. teacher) pre-trained network is used to train a smaller (a.k.a. student) network. However, in this paper, we show that the student network performance degrades when the gap between student and teacher is large. Given a fixed student network, one cannot employ an arbitrarily large teacher, or in other words, a teacher can effectively transfer its knowledge to students up to a certain size, not smaller. To alleviate this shortcoming, we introduce multi-step knowledge distillation which employs an intermediate-sized network (a.k.a. teacher assistant) to bridge the gap between the student and the teacher. We study the effect of teacher assistant size and extend the framework to multi-step distillation. Moreover, empirical and theoretical analysis are conducted to analyze the teacher assistant knowledge distillation framework. Extensive experiments on CIFAR-10 and CIFAR-100 datasets and plain CNN and ResNet architectures substantiate the effectiveness of our proposed approach.

Evaluating the clinical similarities between pairwise patients is a fundamental problem in healthcare informatics. A proper patient similarity measure enables various downstream applications, such as cohort study and treatment comparative effectiveness research. One major carrier for conducting patient similarity research is Electronic Health Records(EHRs), which are usually heterogeneous, longitudinal, and sparse. Though existing studies on learning patient similarity from EHRs have shown being useful in solving real clinical problems, their applicability is limited due to the lack of medical interpretations. Moreover, most previous methods assume a vector-based representation for patients, which typically requires aggregation of medical events over a certain time period. As a consequence, temporal information will be lost. In this paper, we propose a patient similarity evaluation framework based on the temporal matching of longitudinal patient EHRs. Two efficient methods are presented, unsupervised and supervised, both of which preserve the temporal properties in EHRs. The supervised scheme takes a convolutional neural network architecture and learns an optimal representation of patient clinical records with medical concept embedding. The empirical results on real-world clinical data demonstrate substantial improvement over the baselines. We make our code and sample data available for further study.

Creativity, a process that generates novel and valuable ideas, involves increased association between task-positive (control) and task-negative (default) networks in brain. Inspired by this seminal finding, in this study we propose a creative decoder that directly modulates the neuronal activation pattern, while sampling from the learned latent space. The proposed approach is fully unsupervised and can be used as off-the-shelf. Our experiments on three different image datasets (MNIST, FMNIST, CELEBA) reveal that the co-activation between task-positive and task-negative neurons during decoding in a deep neural net enables generation of novel artifacts. We further identify sufficient conditions on several novelty metrics towards measuring the creativity of generated samples.

An artificial neural network architecture, parameterization networks, is proposed for simulating extrapolated dynamics beyond observed data in dynamical systems. Parameterization networks are used to ensure the long term integrity of extrapolated dynamics, while careful tuning of model hyperparameters against validation errors controls overfitting. A parameterization network is demonstrated on the logistic map, where chaos and other nonlinear phenomena consistent with the underlying model can be extrapolated from non-chaotic training time series with good fidelity. The stated results are a lot less fantastical than they appear to be because the neural network is only extrapolating between quadratic return maps. Nonetheless, the results do suggest that successful extrapolation of qualitatively different behaviors requires learning to occur on a level of abstraction where the corresponding behaviors are more similar in nature.