Term rewriting plays a crucial role in software verification and compiler optimization. With dozens of highly parameterizable techniques developed to prove various system properties, automatic term rewriting tools work in an extensive parameter space. This complexity exceeds human capacity for parameter selection, motivating an investigation into automated strategy invention. In this paper, we focus on confluence of term rewrite systems, and apply AI techniques to invent strategies for automatic confluence proving. Moreover, we randomly generate a large dataset to analyze confluence for term rewrite systems. We improve the state-of-the-art automatic confluence prover CSI: When equipped with our invented strategies, it surpasses its human-designed strategies both on the augmented dataset and on the original human-created benchmark dataset ARI-COPS, proving/disproving the confluence of several term rewrite systems for which no automated proofs were known before.

Massive multiple-input multiple-output (MIMO) is a key enabling technology for next-generation communication systems. In massive MIMO cellular networks, coordinated beamforming (CBF), which jointly designs the beamformers of multiple base stations (BSs), is an efficient method to enhance the network performance. In this paper, we investigate the sum rate maximization problem in a massive MIMO mobile cellular network, where in each cell a multi-antenna BS serves multiple mobile users simultaneously via downlink beamforming. Although existing optimization-based CBF algorithms can provide near-optimal solutions, they require real-time and global channel state information (CSI), in addition to their high computation complexity. Due to the non-negligible delay of practical backhaul networks and the high-complexity optimization process, it is almost impossible to apply them in mobile cellular networks. Noting that the considered problem under the practical constraints can be modeled as a networked distributed partially observable Markov decision process, we propose a deep reinforcement learning-based distributed dynamic coordinated beamforming (DDCBF) scheme, which enables each BS to determine the beamformers with only local CSI and some historical information from other BSs. Besides, the beamformers can be calculated with a considerably lower computational complexity by exploiting neural networks and expert knowledge, i.e., a solution structure observed from the iterative procedure of the centralized optimization algorithms. Moreover, we provide extensive numerical simulations to validate the effectiveness of the proposed DRL-based approach. With lower computational complexity and less required information, the results show that the proposed approach can achieve comparable performance to the centralized iterative optimization algorithms.

In this paper, we investigate a dynamic coordinated beamforming (CBF) problem to enhance the sum rate of a massive multiple-input multiple-output (MIMO) cellular network. Although existing optimization-based algorithms can provide near-optimal solutions, they require real-time global channel state information (CSI) and have high computational complexity, making them not viable in practical mobile networks. To tackle this issue, we propose a deep reinforcement learning based distributed dynamic CBF framework, which allows each base station (BS) to determine the optimal beamformers with only local CSI and some historical information transferred from other BSs. Besides, the computational complexity is substantially reduced thanks to the exploitation of neural networks and expert knowledge, i.e., a known solution structure that can be observed from a closed-form optimization algorithm. Simulation results demonstrate that the proposed approach can outperform the closed-form optimization methods and achieve comparable performance to the state-of-the-art optimization algorithm.

The explanation for deep neural networks has drawn extensive attention in the deep learning community over the past few years. In this work, we study the visual saliency, a.k.a. visual explanation, to interpret convolutional neural networks. Compared to iteration based saliency methods, single backward pass based saliency methods benefit from faster speed, and they are widely used in downstream visual tasks. Thus, we focus on single backward pass based methods. However, existing methods in this category struggle to successfully produce fine-grained saliency maps concentrating on specific target classes. That said, producing faithful saliency maps satisfying both target-selectiveness and fine-grainedness using a single backward pass is a challenging problem in the field. To mitigate this problem, we revisit the gradient flow inside the network, and find that the entangled semantics and original weights may disturb the propagation of target-relevant saliency. Inspired by those observations, we propose a novel visual saliency method, termed Target-Selective Gradient Backprop (TSGB), which leverages rectification operations to effectively emphasize target classes and further efficiently propagate the saliency to the image space, thereby generating target-selective and fine-grained saliency maps. The proposed TSGB consists of two components, namely, TSGB-Conv and TSGB-FC, which rectify the gradients for convolutional layers and fully-connected layers, respectively. Extensive qualitative and quantitative experiments on the ImageNet and Pascal VOC datasets show that the proposed method achieves more accurate and reliable results than the other competitive methods. Code is available at https://github.com/123fxdx/CNNvisualizationTSGB.

Abstract Most convolutional neural network‐based single image super‐resolution (SR) methods do not take full account of the hierarchical features of the original low‐resolution (LR) images, including the intra‐channel spatial feature information and the inter‐channel feature information, which decreases the representational capacity of the network. A deep multi‐level upprojection network (DMUN) is proposed to solve this problem. Local feature up‐projection unit is adopted in DMUN to obtain high‐resolution (HR) feature of different levels and then to reconstruct the SR image. Residual up‐projection group in DMUN mines the hierarchical LR feature information and its corresponding HR residual information recursively. A residual recorrection mechanism is further introduced, which adopts HR residual information to re‐correct HR features and enrich the details of the output image. Finally, the original residual block with spatial‐and‐channel attention mechanism is improved, which adaptively recalibrates features by considering the intra‐channel spatial relationships and the inter‐channel pixel‐wise interdependencies simultaneously. Experiments on benchmark datasets show that DMUN achieves favourable performance against state‐of‐the‐art methods.

In this article, we investigate deep-learning-based omni intrusion detection system (IDS) for supervisory control and data acquisition (SCADA) networks that are capable of detecting both temporally uncorrelated and correlated attacks. Regarding the IDSs developed in this article, a feedforward neural network (FNN) can detect temporally uncorrelated attacks at an F1 of 99.967±0.005% but correlated attacks as low as 58±2%. In contrast, long short-term memory (LSTM) detects correlated attacks at 99.56±0.01% while uncorrelated attacks at 99.3±0.1%. Combining LSTM and FNN through an ensemble approach further improves the IDS performance with F1 of 99.68±0.04% regardless the temporal correlations among the data packets.

Although convolutional neural networks (CNNs) have received great attention in image super-resolution (SR), most SR networks do not take full account of the hierarchical features of the original low-resolution (LR) images, including the spatial feature information and the channel-wise feature information. To solve this problem, we propose a multi-level residual up-projection activation network (MRUAN) consisting of residual up-projection group (RUG), upscale module and residual activation block (RAB). Specifically, RUG uses recursive method to mine hierarchical LR feature information and HR residual information. Subsequently, the upscale module adopts multi-level LR feature information as input to obtain HR features. Furthermore, we improve the original residual block with spatial-and-channel attention mechanism, which adaptively recalibrates features by considering the spatial relationships within channel and the pixel-wise inter-dependencies between channels simultaneously. Experiments on benchmark datasets show that our MRUAN achieves favorable performance against state-of-the-art methods.

Weakly-supervised object detection has recently attracted increasing attention since it only requires image-level annotations. However, the performance obtained by existing methods is still far from being satisfactory compared with fully-supervised object detection methods. To achieve a good trade-off between annotation cost and object detection performance, we propose a simple yet effective method which incorporates CNN visualization with click supervision to generate the pseudo ground-truths (i.e., bounding boxes). These pseudo ground-truths can be used to train a fully-supervised detector. To estimate the object scale, we firstly adopt a proposal selection algorithm to preserve high-quality proposals, and then generate Class Activation Maps (CAMs) for these preserved proposals by the proposed CNN visualization algorithm called Spatial Attention CAM. Finally, we fuse these CAMs together to generate pseudo ground-truths and train a fully-supervised object detector with these ground-truths. Experimental results on the PASCAL VOC 2007 and VOC 2012 datasets show that the proposed method can obtain much higher accuracy for estimating the object scale, compared with the state-of-the-art image-level based methods and the center-click based method.

Advances in machine learning technology have made efficient Super-Resolution Image Reconstruction (SRIR) possible. In this paper, we advance a hierarchical support vector machine (HSVM) to learn representative features of both training and test Low-Resolution (LR) image patches. Then a sparse manifold assumption is cast on training patch features to find local HR neighbors for each test LR input. The reconstructed High-Resolution (HR) patches can then be derived via Neighbors Embedding (NE) technology with the help of the HR neighbors from training HR patches, and compensated for the LR images. Some experiments are taken on realizing a 3X amplification of natural images, the recovered results prove its efficiency and superiority to its counterparts visually and qualitatively.

Neighbors embedding (NE) technology has proved its efficiency in single image super resolution (SISR). However, image patches do not strictly follow the similar structure in the low-resolution and high-resolution spaces, consequently leading to a bias to the image restoration. In this paper, considering that patches are a set of data with multiview characteristics and spatial organization, we advance a dual-geometric neighbor embedding (DGNE) approach for SISR. In DGNE, multiview features and local spatial neighbors of patches are explored to find a feature-spatial manifold embedding for images. We adopt a geometrically motivated assumption that for each patch there exists a small neighborhood in which only the patches that come from the same feature-spatial manifold, will lie approximately in a low-dimensional affine subspace formulated by sparse neighbors. In order to find the sparse neighbors, a tensor-simultaneous orthogonal matching pursuit algorithm is advanced to realize a joint sparse coding of feature-spatial image tensors. Some experiments are performed on realizing a 3X amplification of natural images, and the recovered results prove its efficiency and superiority to its counterparts.