Summary: Performance comparison for the popular Deep Learning frameworks supported by Keras – TensorFlow, CNTK, MXNet and TheanoIf there are any doubts in regards to the popularity of Keras among the Data Scientist/Engineer community and the mindshare it commands, you just need to look at the support it has been receiving from all major AI and Cloud players.

High-dimensional partial differential equations (PDE) appear in a number of models from the financial industry, such as in derivative pricing models, credit valuation adjustment (CVA) models, or portfolio optimization models. The PDEs in such applications are high-dimensional as the dimension corresponds to the number of financial assets in a portfolio. Moreover, such PDEs are often fully nonlinear due to the need to incorporate certain nonlinear phenomena in the model such as default risks, transaction costs, volatility uncertainty (Knightian uncertainty), or trading constraints in the model. Such high-dimensional fully nonlinear PDEs are exceedingly difficult to solve as the computational effort for standard approximation methods grows exponentially with the dimension. In this work we propose a new method for solving high-dimensional fully nonlinear second-order PDEs. Our method can in particular be used to sample from high-dimensional nonlinear expectations. The method is based on (i) a connection between fully nonlinear second-order PDEs and second-order backward stochastic differential equations (2BSDEs), (ii) a merged formulation of the PDE and the 2BSDE problem, (iii) a temporal forward discretization of the 2BSDE and a spatial approximation via deep neural nets, and (iv) a stochastic gradient descent-type optimization procedure. Numerical results obtained using ${\rm T{\small ENSOR}F{\small LOW}}$ in ${\rm P{\small YTHON}}$ illustrate the efficiency and the accuracy of the method in the cases of a $100$-dimensional Black-Scholes-Barenblatt equation, a $100$-dimensional Hamilton-Jacobi-Bellman equation, and a nonlinear expectation of a $ 100 $-dimensional $ G $-Brownian motion.

We consider the problem of active feature acquisition, where we sequentially select the subset of features in order to achieve the maximum prediction performance in the most cost-effective way. In this work, we formulate this active feature acquisition problem as a reinforcement learning problem, and provide a novel framework for jointly learning both the RL agent and the classifier (environment). We also introduce a more systematic way of encoding subsets of features that can properly handle innate challenge with missing entries in active feature acquisition problems, that uses the orderless LSTM-based set encoding mechanism that readily fits in the joint learning framework. We evaluate our model on a carefully designed synthetic dataset for the active feature acquisition as well as several real datasets such as electric health record (EHR) datasets, on which it outperforms all baselines in terms of prediction performance as well feature acquisition cost.

In this paper we introduce ZhuSuan, a python probabilistic programming library for Bayesian deep learning, which conjoins the complimentary advantages of Bayesian methods and deep learning. ZhuSuan is built upon Tensorflow. Unlike existing deep learning libraries, which are mainly designed for deterministic neural networks and supervised tasks, ZhuSuan is featured for its deep root into Bayesian inference, thus supporting various kinds of probabilistic models, including both the traditional hierarchical Bayesian models and recent deep generative models. We use running examples to illustrate the probabilistic programming on ZhuSuan, including Bayesian logistic regression, variational auto-encoders, deep sigmoid belief networks and Bayesian recurrent neural networks.

This study presents a novel end-to-end architecture that learns hierarchical representations from raw EEG data using fully convolutional deep neural networks for the task of neonatal seizure detection. The deep neural network acts as both feature extractor and classifier, allowing for end-to-end optimization of the seizure detector. The designed system is evaluated on a large dataset of continuous unedited multi-channel neonatal EEG totaling 835 hours and comprising of 1389 seizures. The proposed deep architecture, with sample-level filters, achieves an accuracy that is comparable to the state-of-the-art SVM-based neonatal seizure detector, which operates on a set of carefully designed hand-crafted features. The fully convolutional architecture allows for the localization of EEG waveforms and patterns that result in high seizure probabilities for further clinical examination.

ECENTLY, Vapnik and Vashist [1] provided a new learning paradigm termed learning using privileged information (LUPI), which is aimed at enhancing the generalization performance of learning algorithms. Generally speaking, in classical supervised learning paradigm, the training data and test data must come from the same distribution. Although in this new learning paradigm the training data is also considered an unbiased representation for the test data, the LUPI provides a set of additional information for the training data during the training stage, which is called privileged information. In the LUPI paradigm, we use the new training set containing privileged information to train a learning algorithm, while the privileged information is not available in the test stage. We note that the new learning paradigm is analogous to human learning process. In class, a teacher can provide some important and helpful information about this course for students, and these information provided by the teacher can help students acquire knowledge better. Therefore, a teacher plays an essential role in human leaning process. The LUPI paradigm resembling the classroom teaching model can achieve better generalization performance than the traditional learning paradigm. The author is with Department of Industrial Engineering and Logistics Management, School of Engineering, Hong Kong University of Science and Technology, Hong Kong 999077, China.(Email:

We present a probabilistic framework for nonlinearities, based on doubly truncated Gaussian distributions. By setting the truncation points appropriately, we are able to generate various types of nonlinearities within a unified framework, including sigmoid, tanh and ReLU, the most commonly used nonlinearities in neural networks. The framework readily integrates into existing stochastic neural networks (with hidden units characterized as random variables), allowing one for the first time to learn the nonlinearities alongside model weights in these networks. Extensive experiments demonstrate the performance improvements brought about by the proposed framework when integrated with the restricted Boltzmann machine (RBM), temporal RBM and the truncated Gaussian graphical model (TGGM).

We investigate in this paper the architecture of deep convolutional networks. Building on existing state of the art models, we propose a reconfiguration of the model parameters into several parallel branches at the global network level, with each branch being a standalone CNN. We show that this arrangement is an efficient way to significantly reduce the number of parameters without losing performance or to significantly improve the performance with the same level of performance. The use of branches brings an additional form of regularization. In addition to the split into parallel branches, we propose a tighter coupling of these branches by placing the "fuse (averaging) layer" before the Log-Likelihood and SoftMax layers during training. This gives another significant performance improvement, the tighter coupling favouring the learning of better representations, even at the level of the individual branches. We refer to this branched architecture as "coupled ensembles". The approach is very generic and can be applied with almost any DCNN architecture. With coupled ensembles of DenseNet-BC and parameter budget of 25M, we obtain error rates of 2.92%, 15.68% and 1.50% respectively on CIFAR-10, CIFAR-100 and SVHN tasks. For the same budget, DenseNet-BC has error rate of 3.46%, 17.18%, and 1.8% respectively. With ensembles of coupled ensembles, of DenseNet-BC networks, with 50M total parameters, we obtain error rates of 2.72%, 15.13% and 1.42% respectively on these tasks.

We present an approach to adaptively utilize deep neural networks in order to reduce the evaluation time on new examples without loss of accuracy. Rather than attempting to redesign or approximate existing networks, we propose two schemes that adaptively utilize networks. We first pose an adaptive network evaluation scheme, where we learn a system to adaptively choose the components of a deep network to be evaluated for each example. By allowing examples correctly classified using early layers of the system to exit, we avoid the computational time associated with full evaluation of the network. We extend this to learn a network selection system that adaptively selects the network to be evaluated for each example. We show that computational time can be dramatically reduced by exploiting the fact that many examples can be correctly classified using relatively efficient networks and that complex, computationally costly networks are only necessary for a small fraction of examples. We pose a global objective for learning an adaptive early exit or network selection policy and solve it by reducing the policy learning problem to a layer-by-layer weighted binary classification problem. Empirically, these approaches yield dramatic reductions in computational cost, with up to a 2.8x speedup on state-of-the-art networks from the ImageNet image recognition challenge with minimal (<1%) loss of top5 accuracy.

As traditional neural network consumes a significant amount of computing resources during back propagation, \citet{Sun2017mePropSB} propose a simple yet effective technique to alleviate this problem. In this technique, only a small subset of the full gradients are computed to update the model parameters. In this paper we extend this technique into the Convolutional Neural Network(CNN) to reduce calculation in back propagation, and the surprising results verify its validity in CNN: only 5\% of the gradients are passed back but the model still achieves the same effect as the traditional CNN, or even better. We also show that the top-$k$ selection of gradients leads to a sparse calculation in back propagation, which may bring significant computational benefits for high computational complexity of convolution operation in CNN.