Low precision operations can provide scalability, memory savings, portability, and energy efficiency. This paper proposes SWALP, an approach to low precision training that averages low-precision SGD iterates with a modified learning rate schedule. SWALP is easy to implement and can match the performance of full-precision SGD even with all numbers quantized down to 8 bits, including the gradient accumulators. Additionally, we show that SWALP converges arbitrarily close to the optimal solution for quadratic objectives, and to a noise ball asymptotically smaller than low precision SGD in strongly convex settings.

Existing methods for CWS usually rely on a large In recent years, neural network based methods have been widely number of labeled sentences to train word segmentation models, used for CWS [1, 17, 23, 26]. Most of these methods model CWS as which are expensive and time-consuming to annotate. Luckily, the a sequence labeling problem [22, 30], and utilize neural networks unlabeled data is usually easy to collect and many high-quality to learn the hidden character features [2, 32]. For example, Chen et Chinese lexicons are off-the-shelf, both of which can provide useful al. [2] used LSTM [8] to learn character features by capturing the information for CWS. In this paper, we propose a neural approach global information of sentence. Peng and Dredze [18] proposed to for Chinese word segmentation which can exploit both lexicon use LSTM for character feature learning and CRF [9] for character and unlabeled data. Our approach is based on a variant of posterior label decoding. However, these methods usually rely on a large regularization algorithm, and the unlabeled data and lexicon number of labeled sentences to train word segmentation models, are incorporated into model training as indirect supervision by which are expensive and time-consuming to annotate.

Time Series Classification (TSC) problems are encountered in many real life data mining tasks ranging from medicine and security to human activity recognition and food safety. With the recent success of deep neural networks in various domains such as computer vision and natural language processing, researchers started adopting these techniques for solving time series data mining problems. However, to the best of our knowledge, no previous work has considered the vulnerability of deep learning models to adversarial time series examples, which could potentially make them unreliable in situations where the decision taken by the classifier is crucial such as in medicine and security. For computer vision problems, such attacks have been shown to be very easy to perform by altering the image and adding an imperceptible amount of noise to trick the network into wrongly classifying the input image. Following this line of work, we propose to leverage existing adversarial attack mechanisms to add a special noise to the input time series in order to decrease the network's confidence when classifying instances at test time. Our results reveal that current state-of-the-art deep learning time series classifiers are vulnerable to adversarial attacks which can have major consequences in multiple domains such as food safety and quality assurance.

Deep neural networks have revolutionized many fields such as computer vision and natural language processing. Inspired by this recent success, deep learning started to show promising results for Time Series Classification (TSC). However, neural networks are still behind the state-of-the-art TSC algorithms, that are currently composed of ensembles of 37 non deep learning based classifiers. We attribute this gap in performance due to the lack of neural network ensembles for TSC. Therefore in this paper, we show how an ensemble of 60 deep learning models can significantly improve upon the current state-of-the-art performance of neural networks for TSC, when evaluated over the UCR/UEA archive: the largest publicly available benchmark for time series analysis. Finally, we show how our proposed Neural Network Ensemble (NNE) is the first time series classifier to outperform COTE while reaching similar performance to the current state-of-the-art ensemble HIVE-COTE.

A long user history inevitably reflects the transitions of personal interests over time. The analyses on the user history require the robust sequential model to anticipate the transitions and the decays of user interests. The user history is often modeled by various RNN structures, but the RNN structures in the recommendation system still suffer from the long-term dependency and the interest drifts. To resolve these challenges, we suggest HCRNN with three hierarchical contexts of the global, the local, and the temporary interests. This structure is designed to withhold the global long-term interest of users, to reflect the local sub-sequence interests, and to attend the temporary interests of each transition. Besides, we propose a hierarchical context-based gate structure to incorporate our \textit{interest drift assumption}. As we suggest a new RNN structure, we support HCRNN with a complementary \textit{bi-channel attention} structure to utilize hierarchical context. We experimented the suggested structure on the sequential recommendation tasks with CiteULike, MovieLens, and LastFM, and our model showed the best performances in the sequential recommendations.

Neural waveform models such as WaveNet have demonstrated better performance than conventional vocoders for statistical parametric speech synthesis. As an autoregressive (AR) model, WaveNet is limited by a slow sequential waveform generation process. Some new models that use the inverse-autoregressive flow (IAF) can generate a whole waveform in a one-shot manner. However, these IAF-based models require sequential transformation during training, which severely slows down the training speed. Other models such as Parallel WaveNet and ClariNet bring together the benefits of AR and IAF-based models and train an IAF model by transferring the knowledge from a pre-trained AR teacher to an IAF student without any sequential transformation. However, both models require additional training criteria, and their implementation is prohibitively complicated. We propose a framework for neural source-filter (NSF) waveform modeling without AR nor IAF-based approaches. This framework requires only three components for waveform generation: a source module that generates a sine-based signal as excitation, a non-AR dilated-convolution-based filter module that transforms the excitation into a waveform, and a conditional module that pre-processes the acoustic features for the source and filer modules. This framework minimizes spectral-amplitude distances for model training, which can be efficiently implemented by using short-time Fourier transform routines. Under this framework, we designed three NSF models and compared them with WaveNet. It was demonstrated that the NSF models generated waveforms at least 100 times faster than WaveNet, and the quality of the synthetic speech from the best NSF model was better than or equally good as that from WaveNet.

We present an efficient algorithm for maximum likelihood estimation (MLE) of the general exponential family, even in cases when the energy function is represented by a deep neural network. We consider the primal-dual view of the MLE for the kinectics augmented model, which naturally introduces an adversarial dual sampler. The sampler will be represented by a novel neural network architectures, dynamics embeddings, mimicking the dynamical-based samplers, e.g., Hamiltonian Monte-Carlo and its variants. The dynamics embedding parametrization inherits the flexibility from HMC, and provides tractable entropy estimation of the augmented model. Meanwhile, it couples the adversarial dual samplers with the primal model, reducing memory and sample complexity. We further show that several existing estimators, including contrastive divergence (Hinton, 2002), score matching (Hyv\"arinen, 2005), pseudo-likelihood (Besag, 1975), noise-contrastive estimation (Gutmann and Hyv\"arinen, 2010), non-local contrastive objectives (Vickrey et al., 2010), and minimum probability flow (Sohl-Dickstein et al., 2011), can be recast as the special cases of the proposed method with different prefixed dual samplers. Finally, we empirically demonstrate the superiority of the proposed estimator against existing state-of-the-art methods on synthetic and real-world benchmarks.

The abundance of open-source code, coupled with the success of recent advances in deep learning for natural language processing, has given rise to a promising new application of machine learning to source code. In this work, we explore the use of a Siamese recurrent neural network model on Python source code to create vectors which capture the semantics of code. We evaluate the quality of embeddings by identifying which problem from a programming competition the code solves. Our model significantly outperforms a bag-of-tokens embedding, providing promising results for improving code embeddings that can be used in future software engineering tasks.

How well does a classic deep net architecture like AlexNet or VGG19 classify on a standard dataset such as CIFAR-10 when its "width" --- namely, number of channels in convolutional layers, and number of nodes in fully-connected internal layers --- is allowed to increase to infinity? Such questions have come to the forefront in the quest to theoretically understand deep learning and its mysteries about optimization and generalization. They also connect deep learning to notions such as Gaussian processes and kernels. A recent paper [Jacot et al., 2018] introduced the Neural Tangent Kernel (NTK) which captures the behavior of fully-connected deep nets in the infinite width limit trained by gradient descent; this object was implicit in some other recent papers. A subsequent paper [Lee et al., 2019] gave heuristic Monte Carlo methods to estimate the NTK and its extension, Convolutional Neural Tangent Kernel (CNTK) and used this to try to understand the limiting behavior on datasets like CIFAR-10. The current paper gives the first efficient exact algorithm (based upon dynamic programming) for computing CNTK as well as an efficient GPU implementation of this algorithm. This results in a significant new benchmark for performance of a pure kernel-based method on CIFAR-10, being 10% higher than the methods reported in [Novak et al., 2019], and only 5% lower than the performance of the corresponding finite deep net architecture (once batch normalization etc. are turned off). We give the first non-asymptotic proof showing that a fully-trained sufficiently wide net is indeed equivalent to the kernel regression predictor using NTK. Our experiments also demonstrate that earlier Monte Carlo approximation can degrade the performance significantly, thus highlighting the power of our exact kernel computation, which we have applied even to the full CIFAR-10 dataset and 20-layer nets.

Cardiovascular disease (CVD) is considered as one of the main causes of death in the world. Accordingly, scientists look for methods to recognize normal/abnormal heart patterns. Over recent years, researchers have been interested in to investigate CVDs based on heart sounds. The physionet 2016 corpus is presented to provide a standard database for researchers in this field. In this study we proposed an approach for normal/abnormal heart sound detection, based on i-vector features on phiysionet 2016 corpus. In this method, a fixed length vector, namely i-vector, is extracted from each record, and then Principal Component Analysis (PCA) is applied. Then Variational AuotoEncoders (VAE) is used to reduce dimensions of the obtained i-vector. After that, this i-vector and its transmitted version by PCA and VAE are used for training two Gaussian Mixture Models (GMMs). Finally, test set is scored using these trained GMMs. In the next step we applied a simple global threshold to classify the obtained scores. We reported the results based on Equal Error Rate (EER) and Modified Accuracy (MAcc). Experimental results show the obtained Accuracy by our proposed system could improve the results reported on the baseline system by 16%.