当前基于神经网络的端到端SAT求解模型在各类SAT问题求解上展现了巨大潜力。然而SAT问题难以容忍误差存在,神经网络模型无法保证不产生预测误差。为利用SAT问题实例特性来减少模型预测误差,提出了错误偏好变量嵌入架构(architecture of ...当前基于神经网络的端到端SAT求解模型在各类SAT问题求解上展现了巨大潜力。然而SAT问题难以容忍误差存在,神经网络模型无法保证不产生预测误差。为利用SAT问题实例特性来减少模型预测误差,提出了错误偏好变量嵌入架构(architecture of embedding error-preference variables, AEEV)。该架构包含错误偏好变量嵌入调整算法和动态部分标签训练模式。首先,为利用参与越多未满足子句的变量越可能被错误分类这一特性,提出了错误偏好变量嵌入调整算法,在消息传递过程中根据变量参与的未满足子句个数来调整其嵌入。此外,提出了动态部分标签监督训练模式,该模式利用了SAT问题实例的变量赋值之间存在复杂依赖关系这一特性,避免为全部变量提供标签,仅为错误偏好变量提供一组来自真实解的标签,保持其他变量标签为预测值不变,以在训练过程管理一个更小的搜索空间。最后,在3-SAT、k-SAT、k-Coloring、3-Clique、SHA-1原像攻击以及收集的SAT竞赛数据集上进行了实验验证。结果表明,相较于目前较先进的基于神经网络的端到端求解模型QuerySAT,AEEV在包含600个变量的k-SAT数据集上准确率提升了45.81%。展开更多
As digital image techniques have been widely used, the requirements for high-resolution images become increasingly stringent. Traditional single-frame interpolation techniques cannot add new high frequency information...As digital image techniques have been widely used, the requirements for high-resolution images become increasingly stringent. Traditional single-frame interpolation techniques cannot add new high frequency information to the expanded images, and cannot improve resolution in deed. Multiframe-based techniques are effective ways for high-resolution image reconstruction, but their computation complexities and the difficulties in achieving image sequences limit their applications. An original method using an artificial neural network is proposed in this paper. Using the inherent merits in neural network, we can establish the mapping between high frequency components in low-resolution images and high-resolution images. Example applications and their results demonstrated the images reconstructed by our method are aesthetically and quantitatively (using the criteria of MSE and MAE) superior to the images acquired by common methods. Even for infrared images this method can give satisfactory results with high definition. In addition, a single-layer linear neural network is used in this paper, the computational complexity is very low, and this method can be realized in real time.展开更多
文摘As digital image techniques have been widely used, the requirements for high-resolution images become increasingly stringent. Traditional single-frame interpolation techniques cannot add new high frequency information to the expanded images, and cannot improve resolution in deed. Multiframe-based techniques are effective ways for high-resolution image reconstruction, but their computation complexities and the difficulties in achieving image sequences limit their applications. An original method using an artificial neural network is proposed in this paper. Using the inherent merits in neural network, we can establish the mapping between high frequency components in low-resolution images and high-resolution images. Example applications and their results demonstrated the images reconstructed by our method are aesthetically and quantitatively (using the criteria of MSE and MAE) superior to the images acquired by common methods. Even for infrared images this method can give satisfactory results with high definition. In addition, a single-layer linear neural network is used in this paper, the computational complexity is very low, and this method can be realized in real time.
