Depth estimation is an important computer vision task, useful in particular for navigation in autonomous vehicles, or for object manipulation in robotics. Here we solved it using an end-to-end neuromorphic approach, combining two event-based cameras and a Spiking Neural Network (SNN) with a slightly modified U-Net-like encoder-decoder architecture, that we named StereoSpike. More specifically, we used the Multi Vehicle Stereo Event Camera Dataset (MVSEC). It provides a depth ground-truth, which was used to train StereoSpike in a supervised manner, using surrogate gradient descent. We propose a novel readout paradigm to obtain a dense analog prediction -- the depth of each pixel -- from the spikes of the decoder. We demonstrate that this architecture generalizes very well, even better than its non-spiking counterparts, leading to state-of-the-art test accuracy. To the best of our knowledge, it is the first time that such a large-scale regression problem is solved by a fully spiking network. Finally, we show that low firing rates (<10%) can be obtained via regularization, with a minimal cost in accuracy. This means that StereoSpike could be efficiently implemented on neuromorphic chips, opening the door for low power and real time embedded systems.

Face video super-resolution algorithm aims to reconstruct realistic face details through continuous input video sequences. However, existing video processing algorithms usually contain redundant parameters to guarantee different super-resolution scenes. In this work, we focus on super-resolution of face areas in original video scenes, while rest areas are interpolated. This specific super-resolved task makes it possible to cut redundant parameters in general video super-resolution networks. We construct a dataset consisting entirely of face video sequences for network training and evaluation, and conduct hyper-parameter optimization in our experiments. We use three combined strategies to optimize the network parameters with a simultaneous train-evaluation method to accelerate optimization process. Results show that simultaneous train-evaluation method improves the training speed and facilitates the generation of efficient networks. The generated network can reduce at least 52.4% parameters and 20.7% FLOPs, achieve better performance on PSNR, SSIM compared with state-of-art video super-resolution algorithms. When processing 36x36x1x3 input video frame sequences, the efficient network provides 47.62 FPS real-time processing performance. We name our proposal as hyper-parameter optimization for face Video Super-Resolution (HO-FVSR), which is open-sourced at https://github.com/yphone/efficient-network-for-face-VSR.

Glaucoma leads to permanent vision disability by damaging the optical nerve that transmits visual images to the brain. The fact that glaucoma does not show any symptoms as it progresses and cannot be stopped at the later stages, makes it critical to be diagnosed in its early stages. Although various deep learning models have been applied for detecting glaucoma from digital fundus images, due to the scarcity of labeled data, their generalization performance was limited along with high computational complexity and special hardware requirements. In this study, compact Self-Organized Operational Neural Networks (Self- ONNs) are proposed for early detection of glaucoma in fundus images and their performance is compared against the conventional (deep) Convolutional Neural Networks (CNNs) over three benchmark datasets: ACRIMA, RIM-ONE, and ESOGU. The experimental results demonstrate that Self-ONNs not only achieve superior detection performance but can also significantly reduce the computational complexity making it a potentially suitable network model for biomedical datasets especially when the data is scarce.

In collaborative filtering, it is an important way to make full use of social information to improve the recommendation quality, which has been proved to be effective because user behavior will be affected by her friends. However, existing works leverage the social relationship to aggregate user features from friends' historical behavior sequences in a user-level indirect paradigm. A significant defect of the indirect paradigm is that it ignores the temporal relationships between behavior events across users. In this paper, we propose a novel time-aware sequential recommendation framework called Social Temporal Excitation Networks (STEN), which introduces temporal point processes to model the fine-grained impact of friends' behaviors on the user s dynamic interests in an event-level direct paradigm. Moreover, we propose to decompose the temporal effect in sequential recommendation into social mutual temporal effect and ego temporal effect. Specifically, we employ a social heterogeneous graph embedding layer to refine user representation via structural information. To enhance temporal information propagation, STEN directly extracts the fine-grained temporal mutual influence of friends' behaviors through the mutually exciting temporal network. Besides, the user s dynamic interests are captured through the self-exciting temporal network. Extensive experiments on three real-world datasets show that STEN outperforms state-of-the-art baseline methods. Moreover, STEN provides event-level recommendation explainability, which is also illustrated experimentally.

Although deep learning models are powerful among various applications, most deep learning models are still a black box, lacking verifiability and interpretability, which means the decision-making process that human beings cannot understand. Therefore, how to evaluate deep neural networks with explanations is still an urgent task. In this paper, we first propose a multi-semantic image recognition model, which enables human beings to understand the decision-making process of the neural network. Then, we presents a new evaluation index, which can quantitatively assess the model interpretability. We also comprehensively summarize the semantic information that affects the image classification results in the judgment process of neural networks. Finally, this paper also exhibits the relevant baseline performance with current state-of-the-art deep learning models.

Intelligent data-driven fault diagnosis methods have been widely applied, but most of these methods need a large number of high-quality labeled samples. It costs a lot of labor and time to label data in actual industrial processes, which challenges the application of intelligent fault diagnosis methods. To solve this problem, a multi-stage semi-supervised improved deep embedded clustering (MS-SSIDEC) method is proposed for the bearing fault diagnosis under the insufficient labeled samples situation. This method includes three stages: pre-training, deep clustering and enhanced supervised learning. In the first stage, a skip-connection based convolutional auto-encoder (SCCAE) is proposed and pre-trained to automatically learn low-dimensional representations. In the second stage, a semi-supervised improved deep embedded clustering (SSIDEC) model that integrates the pre-trained auto-encoder with a clustering layer is proposed for deep clustering. Additionally, virtual adversarial training (VAT) is introduced as a regularization term to overcome the overfitting in the model's training. In the third stage, high-quality clustering results obtained in the second stage are assigned to unlabeled samples as pseudo labels. The labeled dataset is augmented by those pseudo-labeled samples and used to train a bearing fault discriminative model. The effectiveness of the method is evaluated on the Case Western Reserve University (CWRU) bearing dataset. The results show that the method can not only satisfy the semi-supervised learning under a small number of labeled samples, but also solve the problem of unsupervised learning, and has achieved better results than traditional diagnosis methods. This method provides a new research idea for fault diagnosis with limited labeled samples by effectively using unsupervised data.

Program optimization is the process of modifying software to execute more efficiently. Because finding the optimal program is generally undecidable, modern compilers usually resort to expert-written heuristic optimizations. In contrast, superoptimizers attempt to find the optimal program by employing significantly more expensive search and constraint solving techniques. Generally, these methods do not scale well to programs in real development scenarios, and as a result superoptimization has largely been confined to small-scale, domain-specific, and/or synthetic program benchmarks. In this paper, we propose a framework to learn to superoptimize real-world programs by using neural sequence-to-sequence models. We introduce the Big Assembly benchmark, a dataset consisting of over 25K real-world functions mined from open-source projects in x86-64 assembly, which enables experimentation on large-scale optimization of real-world programs. We propose an approach, Self Imitation Learning for Optimization (SILO) that is easy to implement and outperforms a standard policy gradient learning approach on our Big Assembly benchmark. Our method, SILO, superoptimizes programs an expected 6.2% of our test set when compared with the gcc version 10.3 compiler's aggressive optimization level -O3. We also report that SILO's rate of superoptimization on our test set is over five times that of a standard policy gradient approach and a model pre-trained on compiler optimization demonstration.

The performance of a deep neural network (DNN) for fault diagnosis is very much dependent on the network architecture. Also, the diagnostic performance is reduced if the model trained on a laboratory case machine is used on a test dataset from an industrial machine running under variable operating conditions. Thus there are two challenges for the intelligent fault diagnosis of industrial machines: (i) selection of suitable DNN architecture and (ii) domain adaptation for the change in operating conditions. Therefore, we propose an evolutionary Net2Net transformation (EvoNet2Net) that finds the best suitable DNN architecture for the given dataset. Nondominated sorting genetic algorithm II has been used to optimize the depth and width of the DNN architecture. We have formulated a transfer learning-based fitness evaluation scheme for faster evolution. It uses the concept of domain adaptation for quick learning of the data pattern in the target domain. Also, we have introduced a hybrid crossover technique for optimization of the depth and width of the deep neural network encoded in a chromosome. We have used the Case Western Reserve University dataset and Paderborn university dataset to demonstrate the effectiveness of the proposed framework for the selection of the best suitable architecture capable of excellent diagnostic performance, classification accuracy almost up to 100\%.

Recurrent Neural Network (RNN) is a fundamental structure in deep learning. Recently, some works study the training process of over-parameterized neural networks, and show that over-parameterized networks can learn functions in some notable concept classes with a provable generalization error bound. In this paper, we analyze the training and generalization for RNNs with random initialization, and provide the following improvements over recent works: 1) For a RNN with input sequence $x=(X_1,X_2,...,X_L)$, previous works study to learn functions that are summation of $f(\beta^T_lX_l)$ and require normalized conditions that $||X_l||\leq\epsilon$ with some very small $\epsilon$ depending on the complexity of $f$. In this paper, using detailed analysis about the neural tangent kernel matrix, we prove a generalization error bound to learn such functions without normalized conditions and show that some notable concept classes are learnable with the numbers of iterations and samples scaling almost-polynomially in the input length $L$. 2) Moreover, we prove a novel result to learn N-variables functions of input sequence with the form $f(\beta^T[X_{l_1},...,X_{l_N}])$, which do not belong to the ``additive'' concept class, i,e., the summation of function $f(X_l)$. And we show that when either $N$ or $l_0=\max(l_1,..,l_N)-\min(l_1,..,l_N)$ is small, $f(\beta^T[X_{l_1},...,X_{l_N}])$ will be learnable with the number iterations and samples scaling almost-polynomially in the input length $L$.

Deep neural networks (DNNs) have shown their success as high-dimensional function approximators in many applications; however, training DNNs can be challenging in general. DNN training is commonly phrased as a stochastic optimization problem whose challenges include non-convexity, non-smoothness, insufficient regularization, and complicated data distributions. Hence, the performance of DNNs on a given task depends crucially on tuning hyperparameters, especially learning rates and regularization parameters. In the absence of theoretical guidelines or prior experience on similar tasks, this requires solving many training problems, which can be time-consuming and demanding on computational resources. This can limit the applicability of DNNs to problems with non-standard, complex, and scarce datasets, e.g., those arising in many scientific applications. To remedy the challenges of DNN training, we propose slimTrain, a stochastic optimization method for training DNNs with reduced sensitivity to the choice hyperparameters and fast initial convergence. The central idea of slimTrain is to exploit the separability inherent in many DNN architectures; that is, we separate the DNN into a nonlinear feature extractor followed by a linear model. This separability allows us to leverage recent advances made for solving large-scale, linear, ill-posed inverse problems. Crucially, for the linear weights, slimTrain does not require a learning rate and automatically adapts the regularization parameter. Since our method operates on mini-batches, its computational overhead per iteration is modest. In our numerical experiments, slimTrain outperforms existing DNN training methods with the recommended hyperparameter settings and reduces the sensitivity of DNN training to the remaining hyperparameters.