Pre-trained language models for programming languages have shown a powerful ability on processing many Software Engineering (SE) tasks, e.g., program synthesis, code completion, and code search. However, it remains to be seen what is behind their success. Recent studies have examined how pre-trained models can effectively learn syntax information based on Abstract Syntax Trees. In this paper, we figure out what role the self-attention mechanism plays in understanding code syntax and semantics based on AST and static analysis. We focus on a well-known representative code model, CodeBERT, and study how it can learn code syntax and semantics by the self-attention mechanism and Masked Language Modelling (MLM) at the token level. We propose a group of probing tasks to analyze CodeBERT. Based on AST and static analysis, we establish the relationships among the code tokens. First, Our results show that CodeBERT can acquire syntax and semantics knowledge through self-attention and MLM. Second, we demonstrate that the self-attention mechanism pays more attention to dependence-relationship tokens than to other tokens. Different attention heads play different roles in learning code semantics; we show that some of them are weak at encoding code semantics. Different layers have different competencies to represent different code properties. Deep CodeBERT layers can encode the semantic information that requires some complex inference in the code context. More importantly, we show that our analysis is helpful and leverage our conclusions to improve CodeBERT. We show an alternative approach for pre-training models, which makes fully use of the current pre-training strategy, i.e, MLM, to learn code syntax and semantics, instead of combining features from different code data formats, e.g., data-flow, running-time states, and program outputs.

Dense pose estimation is a dense 3D prediction task for instance-level human analysis, aiming to map human pixels from an RGB image to a 3D surface of the human body. Due to a large amount of surface point regression, the training process appears to be easy to collapse compared to other region-based human instance analyzing tasks. By analyzing the loss formulation of the existing dense pose estimation model, we introduce a novel point regression loss function, named Dense Points} loss to stable the training progress, and a new balanced loss weighting strategy to handle the multi-task losses. With the above novelties, we propose a brand new architecture, named UV R-CNN. Without auxiliary supervision and external knowledge from other tasks, UV R-CNN can handle many complicated issues in dense pose model training progress, achieving 65.0% $AP_{gps}$ and 66.1% $AP_{gpsm}$ on the DensePose-COCO validation subset with ResNet-50-FPN feature extractor, competitive among the state-of-the-art dense human pose estimation methods.

人类垫子是指从具有高质量的自然图像中提取人类部位，包括人类细节信息，例如头发，眼镜，帽子等。这项技术在电影行业的图像合成和视觉效果中起着至关重要的作用。当绿屏不可用时，现有的人类底漆方法需要其他输入（例如Trimap，背景图像等）或具有较高计算成本和复杂网络结构的模型，这给应用程序带来了很大的困难实践中的人类垫子。为了减轻此类问题，大多数现有方法（例如MODNET）使用多分支为通过细分铺平道路，但是这些方法并未充分利用图像功能，并且仅利用网络的预测结果作为指导信息。因此，我们提出了一个模块来生成前景概率图，并将其添加到MODNET中以获得语义引导的Matting Net（SGM-NET）。在只有一个图像的条件下，我们可以实现人类的效果任务。我们在P3M-10K数据集上验证我们的方法。与基准相比，在各种评估指标中，我们的方法显着改善。

Convolutional neural networks (CNNs) have constantly achieved better performance over years by introducing more complex topology, and enlarging the capacity towards deeper and wider CNNs. This makes the manual design of CNNs extremely difficult, so the automated design of CNNs has come into the research spotlight, which has obtained CNNs that outperform manually-designed CNNs. However, the computational cost is still the bottleneck of automatically designing CNNs. In this paper, inspired by transfer learning, a new evolutionary computation based framework is proposed to efficiently evolve CNNs without compromising the classification accuracy. The proposed framework leverages multi-source domains, which are smaller datasets than the target domain datasets, to evolve a generalised CNN block only once. And then, a new stacking method is proposed to both widen and deepen the evolved block, and a grid search method is proposed to find optimal stacking solutions. The experimental results show the proposed method acquires good CNNs faster than 15 peer competitors within less than 40 GPU-hours. Regarding the classification accuracy, the proposed method gains its strong competitiveness against the peer competitors, which achieves the best error rates of 3.46%, 18.36% and 1.76% for the CIFAR-10, CIFAR-100 and SVHN datasets, respectively.

Deep convolutional neural networks have proven their effectiveness, and have been acknowledged as the most dominant method for image classification. However, a severe drawback of deep convolutional neural networks is poor explainability. Unfortunately, in many real-world applications, users need to understand the rationale behind the predictions of deep convolutional neural networks when determining whether they should trust the predictions or not. To resolve this issue, a novel genetic algorithm-based method is proposed for the first time to automatically evolve local explanations that can assist users to assess the rationality of the predictions. Furthermore, the proposed method is model-agnostic, i.e., it can be utilised to explain any deep convolutional neural network models. In the experiments, ResNet is used as an example model to be explained, and the ImageNet dataset is selected as the benchmark dataset. DenseNet and MobileNet are further explained to demonstrate the model-agnostic characteristic of the proposed method. The evolved local explanations on four images, randomly selected from ImageNet, are presented, which show that the evolved local explanations are straightforward to be recognised by humans. Moreover, the evolved explanations can explain the predictions of deep convolutional neural networks on all four images very well by successfully capturing meaningful interpretable features of the sample images. Further analysis based on the 30 runs of the experiments exhibits that the evolved local explanations can also improve the probabilities/confidences of the deep convolutional neural network models in making the predictions. The proposed method can obtain local explanations within one minute, which is more than ten times faster than LIME (the state-of-the-art method).

数据有效的图像分类是一项具有挑战性的任务，旨在使用小型培训数据来解决图像分类。基于神经网络的深度学习方法对于图像分类很有效，但是它们通常需要大规模的培训数据，并且具有重大局限性，例如需要专业知识来设计网络架构和具有差的可解释性。进化深度学习是一个最近的热门话题，将进化计算与深度学习结合在一起。但是，大多数进化的深度学习方法都集中在神经网络的架构上，这些方法仍然遭受诸如不良解释性之类的局限性。为了解决这个问题，本文提出了一种新的基于基因编程的进化深度学习方法，以进行数据有效的图像分类。新方法可以使用来自图像和分类域的许多重要运算符自动发展可变长度模型。它可以从颜色或灰度图像中学习不同类型的图像特征，并构建有效而多样的合奏以进行图像分类。灵活的多层表示可以使新方法自动构建浅层或深模型/树以进行不同的任务，并通过多个内部节点对输入数据进行有效的转换。新方法用于解决具有不同训练集大小的五个图像分类任务。结果表明，在大多数情况下，它比深度学习方法的图像分类更好。深入的分析表明，新方法具有良好的收敛性，并演变具有高解释性，不同长度/尺寸/形状以及良好可传递性的模型。

在本文中，我们开发了损失功能学习的新兴主题，该主题旨在学习损失功能，从而显着提高在其下方训练的模型的性能。具体而言，我们提出了一个新的元学习框架，用于通过混合神经符号搜索方法来学习模型 - 不足的损失函数。该框架首先使用基于进化的方法来搜索原始数学操作的空间，以找到一组符号损耗函数。其次，随后通过基于端梯度的训练程序对学习的损失功能集进行了参数化和优化。拟议框架的多功能性在经验上得到了各种监督的学习任务的经验验证。结果表明，通过新提出的方法发现的元学习损失函数在各种神经网络体系结构和数据集上都超过了交叉渗透丢失和最新的损失函数学习方法。

计算机视觉（CV）是涵盖广泛应用的人工智能中的一个重要领域。图像分析是CV的主要任务，目的是提取，分析和理解图像的视觉内容。但是，由于许多因素，图像之间的较高变化，高维度，域专业知识要求和图像扭曲，因此与图像相关的任务非常具有挑战性。进化计算方法（EC）方法已被广泛用于图像分析，并取得了重大成就。但是，没有对现有的EC方法进行图像分析的全面调查。为了填补这一空白，本文提供了一项全面的调查，涵盖了重要的图像分析任务的所有基本EC方法，包括边缘检测，图像分割，图像特征分析，图像分类，对象检测等。这项调查旨在通过讨论不同方法的贡献并探讨如何以及为什么将EC用于简历和图像分析，以更好地了解进化计算机视觉（ECV）。还讨论并总结了与该研究领域相关的应用，挑战，问题和趋势，以提供进一步的指南和未来研究的机会。

近年来，行业和学术界的深度学习（DL）迅速发展。但是，找到DL模型的最佳超参数通常需要高计算成本和人类专业知识。为了减轻上述问题，进化计算（EC）作为一种强大的启发式搜索方法显示出在DL模型的自动设计中，所谓的进化深度学习（EDL）具有重要优势。本文旨在从自动化机器学习（AUTOML）的角度分析EDL。具体来说，我们首先从机器学习和EC阐明EDL，并将EDL视为优化问题。根据DL管道的说法，我们系统地介绍了EDL方法，从功能工程，模型生成到具有新的分类法的模型部署（即，什么以及如何发展/优化），专注于解决方案表示和搜索范式的讨论通过EC处理优化问题。最后，提出了关键的应用程序，开放问题以及可能有希望的未来研究线。这项调查回顾了EDL的最新发展，并为EDL的开发提供了有见地的指南。

神经体系结构搜索（NAS）可以自动为深神经网络（DNN）设计架构，并已成为当前机器学习社区中最热门的研究主题之一。但是，NAS通常在计算上很昂贵，因为在搜索过程中需要培训大量DNN。绩效预测因素可以通过直接预测DNN的性能来大大减轻NAS的过失成本。但是，构建令人满意的性能预测能力很大程度上取决于足够的训练有素的DNN体系结构，在大多数情况下很难获得。为了解决这个关键问题，我们在本文中提出了一种名为Giaug的有效的DNN体系结构增强方法。具体而言，我们首先提出了一种基于图同构的机制，其优点是有效地生成$ \ boldsymbol n $（即$ \ boldsymbol n！$）的阶乘，对具有$ \ boldsymbol n $ n $ n $ n $ \ boldsymbol n $的单个体系结构进行了带注释的体系结构节点。此外，我们还设计了一种通用方法，将体系结构编码为适合大多数预测模型的形式。结果，可以通过各种基于性能预测因子的NAS算法灵活地利用Giaug。我们在中小型，中，大规模搜索空间上对CIFAR-10和Imagenet基准数据集进行了广泛的实验。实验表明，Giaug可以显着提高大多数最先进的同伴预测因子的性能。此外，与最先进的NAS算法相比，Giaug最多可以在ImageNet上节省三级计算成本。