人工智能下载,深度学习下载列表第1264页

[深度学习] Flow Topology on Closed-loop Stability of Vehicle Platoon

说明： Besides automated controllers, the information flow among vehicles can significantly affect the dynamics of a platoon. This paper studies the influence of information flow topology on the closed-loop stability of homogeneous vehicular platoon moving
<czzc1990> 上传 | 大小：495kb

[深度学习] Robust control of heterogeneous vehicular platoon with uncertain dynamics

说明： Platoon formation of highway vehicles has the potential to significantly enhance road safety, improve highway utility, and increase traffic efficiency. However, various uncertainties and disturbances that are present in real-world driving conditions
<czzc1990> 上传 | 大小：592kb

[深度学习] Sampled-data vehicular platoon control with communication delay

说明： This article investigates sampled-data vehicular platoon control with communication delay. A new sampled-data control method is established, in which the effect of the communication delay is involved. First, a linearized vehicle longitudinal dynamic
<czzc1990> 上传 | 大小：1mb

[深度学习] Neural Networks and Learning Machines

说明： Decoupling of linear time-invariant systems by state feedback and precompensation has been treated in several papers (Falb and Wolovich 1967, Gilbert 1969, Wonham and Morse 1970, Silverman and Payne 1(71). A generalization of some results for time-v
<czzc1990> 上传 | 大小：403kb

[深度学习] Deep Learning

说明： Deep learning allows computational models that are composed of multiple processing layers to learn representations of data with multiple levels of abstraction. These methods have dramatically improved the state-of-the-art in speech recognition, visu
<czzc1990> 上传 | 大小：2mb

[深度学习] resnet50_weights_tf_dim_ordering_tf_kernels_notop

说明： resnet50_weights_tf_dim_ordering_tf_kernels_notop Linux下是放在“~/.keras/models/”中 Win下则放在Python的“settings/.keras/models/”中 Windows-weights路径：C:\Users\你的用户名\.keras\models anaconda下依然好用
<ttz_csdn> 上传 | 大小：83mb

[深度学习] 基于卷积神经网络的道路车辆检测方法

说明：提出了一种基于卷积神经网络的前方车辆检测方法。首先，根据车底阴影特征，运用基于边缘增强的路面检测算法以及车底阴影自适应分割算法来分割并形成车底候选区域，以解决路面灰度分布不均及光照条件变化问题；其次，运用针对道路交通环境的卷积神经网络结构，建立图像样本库进行网络训练；在此基础上，采用基于卷积神经网络识别的方法以验证并剔除被误检测为车底阴影的候选区域，进而确定真正的车辆目标；最后，修改网络为三分类识别，以验证本文方法的强扩展性的优势。实验结果表明：本文提出的车辆检测方法能够很好地区分车底阴影和
<czzc1990> 上传 | 大小：949kb

[深度学习] 改进的基于卷积神经网络的图像超分辨率算法

说明：针对现有的基于卷积神经网络的图像超分辨率算法参数较多、计算量较大、训练时间较长、图像纹理模糊等问题，结合现有的图像分类网络模型和视觉识别算法对其提出了改进。在原有的三层卷积神经网络中，调整卷积核大小，减少参数；加入池化层，降低维度，减少计算复杂度；提高学习率和输入子块的尺寸，减少训练消耗的时间；扩大图像训练库，使训练库提供的特征更加广泛和全面。实验结果表明，改进算法生成的网络模型取得了更佳的超分辨率结果，主观视觉效果和客观评价指标明显改善，图像清晰度和边缘锐度明显提高。
<czzc1990> 上传 | 大小：3mb