To avoid unstable learning, a stable adaptive learning algorithm was proposed for discrete-time recurrent neural networks. Unlike the dynamic gradient methods, such as the backpropagation through time and the real tim...To avoid unstable learning, a stable adaptive learning algorithm was proposed for discrete-time recurrent neural networks. Unlike the dynamic gradient methods, such as the backpropagation through time and the real time recurrent learning, the weights of the recurrent neural networks were updated online in terms of Lyapunov stability theory in the proposed learning algorithm, so the learning stability was guaranteed. With the inversion of the activation function of the recurrent neural networks, the proposed learning algorithm can be easily implemented for solving varying nonlinear adaptive learning problems and fast convergence of the adaptive learning process can be achieved. Simulation experiments in pattern recognition show that only 5 iterations are needed for the storage of a 15×15 binary image pattern and only 9 iterations are needed for the perfect realization of an analog vector by an equilibrium state with the proposed learning algorithm.展开更多
车辆自动行驶的安全性和稳定性离不开车道线准确识别。然而,日常驾驶中面临着复杂多变的天气和光照条件、道路标记模糊或遮挡等挑战。研究并设计基于深度神经网络的车道线识别算法,以提高识别技术在面对复杂环境的鲁棒性与检测结果精度...车辆自动行驶的安全性和稳定性离不开车道线准确识别。然而,日常驾驶中面临着复杂多变的天气和光照条件、道路标记模糊或遮挡等挑战。研究并设计基于深度神经网络的车道线识别算法,以提高识别技术在面对复杂环境的鲁棒性与检测结果精度。通过构建以VGG-16为主链并嵌入通道注意力和空间注意力机制的全卷积神经网络模型,实现端到端像素级别的车道线语义分割。嵌入注意力模块的新模型在CULane通用数据集上验证结果同VGG-解码语义分割方法相比,其平均像素准确率与均交并比(Mean Intersection over Union, MIoU)分别提升2.2%与1.3%。且在车道线不存在场景下,预测结果的像素准确率达到70%。嵌入注意力机制的图像分割算法研究为车道线识别问题提供了有效解决方案,有力支撑车道线检测技术在无人驾驶场景的应用。展开更多
针对现有语音情感识别系统的部署功耗高、不具有便携性的缺点,提出一种基于神经网络加速器的FPGA语音情感识别系统设计。在FPGA上实现语音MFCC(Mel Frequency Cepstrum Coefficient)特征的提取,便于进行识别;为神经网络加速器设计指令...针对现有语音情感识别系统的部署功耗高、不具有便携性的缺点,提出一种基于神经网络加速器的FPGA语音情感识别系统设计。在FPGA上实现语音MFCC(Mel Frequency Cepstrum Coefficient)特征的提取,便于进行识别;为神经网络加速器设计指令生成算法,将网络模型部署在神经网络加速器实现语音情感识别。整个系统主要硬件资源消耗为37078个LUT和153个DSP,支持在主流FPGA平台上的部署。经过检验,语音情感识别系统的指令运算误差可达0.06以下,输出误差为0.0004以下,满足语音情感识别的需求。展开更多
基金Project(50276005) supported by the National Natural Science Foundation of China Projects (2006CB705400, 2003CB716206) supported by National Basic Research Program of China
文摘To avoid unstable learning, a stable adaptive learning algorithm was proposed for discrete-time recurrent neural networks. Unlike the dynamic gradient methods, such as the backpropagation through time and the real time recurrent learning, the weights of the recurrent neural networks were updated online in terms of Lyapunov stability theory in the proposed learning algorithm, so the learning stability was guaranteed. With the inversion of the activation function of the recurrent neural networks, the proposed learning algorithm can be easily implemented for solving varying nonlinear adaptive learning problems and fast convergence of the adaptive learning process can be achieved. Simulation experiments in pattern recognition show that only 5 iterations are needed for the storage of a 15×15 binary image pattern and only 9 iterations are needed for the perfect realization of an analog vector by an equilibrium state with the proposed learning algorithm.
文摘车辆自动行驶的安全性和稳定性离不开车道线准确识别。然而,日常驾驶中面临着复杂多变的天气和光照条件、道路标记模糊或遮挡等挑战。研究并设计基于深度神经网络的车道线识别算法,以提高识别技术在面对复杂环境的鲁棒性与检测结果精度。通过构建以VGG-16为主链并嵌入通道注意力和空间注意力机制的全卷积神经网络模型,实现端到端像素级别的车道线语义分割。嵌入注意力模块的新模型在CULane通用数据集上验证结果同VGG-解码语义分割方法相比,其平均像素准确率与均交并比(Mean Intersection over Union, MIoU)分别提升2.2%与1.3%。且在车道线不存在场景下,预测结果的像素准确率达到70%。嵌入注意力机制的图像分割算法研究为车道线识别问题提供了有效解决方案,有力支撑车道线检测技术在无人驾驶场景的应用。
文摘针对现有语音情感识别系统的部署功耗高、不具有便携性的缺点,提出一种基于神经网络加速器的FPGA语音情感识别系统设计。在FPGA上实现语音MFCC(Mel Frequency Cepstrum Coefficient)特征的提取,便于进行识别;为神经网络加速器设计指令生成算法,将网络模型部署在神经网络加速器实现语音情感识别。整个系统主要硬件资源消耗为37078个LUT和153个DSP,支持在主流FPGA平台上的部署。经过检验,语音情感识别系统的指令运算误差可达0.06以下,输出误差为0.0004以下,满足语音情感识别的需求。
