The demand of artificial intelligent adoption for condition-based maintenance strategy is astonishingly increased over the past few years. Intelligent fault diagnosis is one critical topic of maintenance solution for mechanical systems. Deep learning models, such as convolutional neural networks (CNNs), have been successfully applied to fault diagnosis tasks for mechanical systems and achieved promising results. However, for diverse working conditions in the industry, deep learning suffers two difficulties: one is that the well-defined (source domain) and new (target domain) datasets are with different feature distributions; another one is the fact that insufficient or no labelled data in target domain significantly reduce the accuracy of fault diagnosis. As a novel idea, deep transfer learning (DTL) is created to perform learning in the target domain by leveraging information from the relevant source domain. Inspired by Wasserstein distance of optimal transport, in this paper, we propose a novel DTL approach to intelligent fault diagnosis, namely Wasserstein Distance based Deep Transfer Learning (WD-DTL), to learn domain feature representations (generated by a CNN based feature extractor) and to minimize the distributions between the source and target domains through adversarial training. The effectiveness of the proposed WD-DTL is verified through 3 transfer scenarios and 16 transfer fault diagnosis experiments of both unsupervised and supervised (with insufficient labelled data) learning. We also provide a comprehensive analysis of the network visualization of those transfer tasks.

End-to-end visual-based imitation learning has been widely applied in autonomous driving. When deploying the trained visual-based driving policy, a deterministic command is usually directly applied without considering the uncertainty of the input data. Such kind of policies may bring dramatical damage when applied in the real world. In this paper, we follow the recent real-to-sim pipeline by translating the testing world image back to the training domain when using the trained policy. In the translating process, a stochastic generator is used to generate various images stylized under the training domain randomly or directionally. Based on those translated images, the trained uncertainty-aware imitation learning policy would output both the predicted action and the data uncertainty motivated by the aleatoric loss function. Through the uncertainty-aware imitation learning policy, we can easily choose the safest one with the lowest uncertainty among the generated images. Experiments in the Carla navigation benchmark show that our strategy outperforms previous methods, especially in dynamic environments.

In recent years, with the prevalence of social media and smart devices, people causally reveal their locations such as shops, hotels, and restaurants in their tweets. Recognizing and linking such fine-grained location mentions to well-defined location profiles are beneficial for retrieval and recommendation systems. In this paper, we propose DLocRL, a new deep learning pipeline for fine-grained location recognition and linking in tweets, and verify its effectiveness on a real-world Twitter dataset.

We study the calibration of several state of the art neural machine translation(NMT) systems built on attention-based encoder-decoder models. For structured outputs like in NMT, calibration is important not just for reliable confidence with predictions, but also for proper functioning of beam-search inference. We show that most modern NMT models are surprisingly miscalibrated even when conditioned on the true previous tokens. Our investigation leads to two main reasons -- severe miscalibration of EOS (end of sequence marker) and suppression of attention uncertainty. We design recalibration methods based on these signals and demonstrate improved accuracy, better sequence-level calibration, and more intuitive results from beam-search.

Widespread applications of deep learning have led to a plethora of pre-trained neural network models for common tasks. Such models are often adapted from other models via transfer learning. The models may have varying training sets, training algorithms, network architectures, and hyper-parameters. For a given application, what isthe most suitable model in a model repository? This is a critical question for practical deployments but it has not received much attention. This paper introduces the novel problem of searching and ranking models based on suitability relative to a target dataset and proposes a ranking algorithm called \textit{neuralRank}. The key idea behind this algorithm is to base model suitability on the discriminating power of a model, using a novel metric to measure it. With experimental results on the MNIST, Fashion, and CIFAR10 datasets, we demonstrate that (1) neuralRank is independent of the domain, the training set, or the network architecture and (2) that the models ranked highly by neuralRank ranking tend to have higher model accuracy in practice.

In this paper we study the problem of convergence and generalization error bound of stochastic momentum for deep learning from the perspective of regularization. To do so, we first interpret momentum as solving an $\ell_2$-regularized minimization problem to learn the offsets between arbitrary two successive model parameters. We call this {\em time-delay momentum} because the model parameter is updated after a few iterations towards finding the minimizer. We then propose our learning algorithm, \ie stochastic gradient descent (SGD) with time-delay momentum. We show that our algorithm can be interpreted as solving a sequence of strongly convex optimization problems using SGD. We prove that under mild conditions our algorithm can converge to a stationary point with rate of $O(\frac{1}{\sqrt{K}})$ and generalization error bound of $O(\frac{1}{\sqrt{n\delta}})$ with probability at least $1-\delta$, where $K,n$ are the numbers of model updates and training samples, respectively. We demonstrate the empirical superiority of our algorithm in deep learning in comparison with the state-of-the-art deep learning solvers.

Learning continuous representations of nodes is attracting growing interest in both academia and industry recently, due to their simplicity and effectiveness in a variety of applications. Most of existing node embedding algorithms and systems are capable of processing networks with hundreds of thousands or a few millions of nodes. However, how to scale them to networks that have tens of millions or even hundreds of millions of nodes remains a challenging problem. In this paper, we propose GraphVite, a high-performance CPU-GPU hybrid system for training node embeddings, by co-optimizing the algorithm and the system. On the CPU end, augmented edge samples are parallelly generated by random walks in an online fashion on the network, and serve as the training data. On the GPU end, a novel parallel negative sampling is proposed to leverage multiple GPUs to train node embeddings simultaneously, without much data transfer and synchronization. Moreover, an efficient collaboration strategy is proposed to further reduce the synchronization cost between CPUs and GPUs. Experiments on multiple real-world networks show that GraphVite is super efficient. It takes only about one minute for a network with 1 million nodes and 5 million edges on a single machine with 4 GPUs, and takes around 20 hours for a network with 66 million nodes and 1.8 billion edges. Compared to the current fastest system, GraphVite is about 50 times faster without any sacrifice on performance.

We propose a novel {\it Equilibrated Recurrent Neural Network} (ERNN) to combat the issues of inaccuracy and instability in conventional RNNs. Drawing upon the concept of autapse in neuroscience, we propose augmenting an RNN with a time-delayed self-feedback loop. Our sole purpose is to modify the dynamics of each internal RNN state and, at any time, enforce it to evolve close to the equilibrium point associated with the input signal at that time. We show that such self-feedback helps stabilize the hidden state transitions leading to fast convergence during training while efficiently learning discriminative latent features that result in state-of-the-art results on several benchmark datasets at test-time. We propose a novel inexact Newton method to solve fixed-point conditions given model parameters for generating the latent features at each hidden state. We prove that our inexact Newton method converges locally with linear rate (under mild conditions). We leverage this result for efficient training of ERNNs based on backpropagation.

The performance of automatic speech recognition systems(ASR) degrades in the presence of noisy speech. This paper demonstrates that using electroencephalography (EEG) can help automatic speech recognition systems overcome performance loss in the presence of noise. The paper also shows that distillation training of automatic speech recognition systems using EEG features will increase their performance. Finally, we demonstrate the ability to recognize words from EEG with no speech signal on a limited English vocabulary with high accuracy.

When We identify a phenomenon, which we refer to dealing with many large models, a common strategy to keep as multi-model forgetting, that occurs when sequentially training tractable is to share a subset of the weights across training multiple deep networks with the multiple models and to train them sequentially (Pham partially-shared parameters; the performance of et al., 2018; Xie & Yuille, 2017; Liu et al., 2018a). This previously-trained models degrades as one optimizes strategy has a major drawback. Figure 1 shows that for two a subsequent one, due to the overwriting models, A and B, the larger the number of shared weights, of shared parameters. To overcome this, we introduce the more the accuracy of A drops when training B; B overwrites a statistically-justified weight plasticity loss some of the weights of A and this damages the performance that regularizes the learning of a model's shared of A. We call this multi-model forgetting. The parameters according to their importance for the benefits of weight-sharing have been emphasized in tasks previous models, and demonstrate its effectiveness like neural architecture search, where the associated speed when training two models sequentially and gains have been key in making the process practical (Pham for neural architecture search. Adding weight et al., 2018; Liu et al., 2018b), but its downsides remain plasticity in neural architecture search preserves virtually unexplored.