使用Tensorflow数据并行，多GPU训练的demo。模型是一个image2image的模型，参考了dncnn。训练数据转为TFRecord文件。

A key determinant of overall system performance and power dissipation is the cache hierarchy since access to off-chip memory consumes many more cycles and energy than on-chip accesses. In addition, multi-core processors are expected to place ever higher bandwidth demands on the memory system. All these issues make it important to avoid off-chip memory access by improving the efficiency of the on-chip cache. Future multi-core processors will have many large cache banks connected by a network and shared by many cores. Hence, many important problems must be solved: cache resources must be allocated across many cores, data must be placed in cache banks that are near the accessing core, and the most important data must be identified for retention. Finally, difficulties in scaling existing technologies require adapting to and exploiting new technology constraints. The book attempts a synthesis of recent cache research that has focused on innovations for multi-core processors. It is an excellent starting point for early-stage graduate students, researchers, practitioners who wish to understand the landscape of recent cache research. The book is suitable as a reference for advanced computer architecture classes as well as for experienced researchers and VLSI engineers.

这是一本比较学术的书了， 是美国做多核研究的教授联合SUN编写的关于多核系统设计和编程的问题的综述。 对于有志于从事系统底层设计的朋友有借鉴或者入门的作用。

这是MADDPG算法的原始论文。MADDPG算法是一种非常优秀的多智能体强化学习算法，感兴趣的可以下载下来看看

四水平响应曲面法优化

1 Introduction 我们的方法是基于以下观察:有大量在线图片的情况下，应该存在在相似光照，天气，曝光条件，相似分辨率和足够长基线的子集。通过自动识别这些子集，我们可以极大地简化问题，在提供足够的视差进行精确重建的同时，匹配外观和比例相似的图像。虽然这个想法是概念上很简单,他的有效执行需要两个方面：在图像层面，估计尺度，外观和足够长的基线；在像素层面，处理遮挡，杂乱，局部光线变化，并鼓励水平和垂直上视差的匹配。我们的主要贡献是设计和分析这样一个自适应的视图选择过程。我们发现这种方法在很多场景和cpc上都是有效的。事实上，我们的实验表明，简单的匹配指标能够在许多场景的重要部分上容忍惊人的广泛的照明变化。虽然我们希望未来的工作能扩展这一操作范围，甚至利用外观上的巨大变化，但我们相信结合简单度量的视图选择是一种有效的工具，也是从互联网派生的集合中重建场景的重要的第一步。

Distributed Optimization for Continuous-Time Multi-Agent Systems with External Disturbance and Discrete-Time Communication

如何在 Matlab 2019b 中创建多流 CNN 模型的示例

密集杂波环境下的多目标跟踪（MTT）一直是雷达目标跟踪领域的研究难点，关键是有效地将状态滤波与数据关联相结合。 在密集杂波环境中，除了目标点的回波之外，还存在来自未知散射的大量杂波干扰，因此很难处理数据。 本文提出了一种基于轨迹定向多假设跟踪（TOMHT）和支持向量机（SVM）的密集杂波环境下的杂波滤波算法，用于对杂波进行滤波，并为后续的目标跟踪提供先验的环境信息。 。 在满足跟踪精度的前提下，降低了混乱的密度，提高了数据关联的效率。 结果表明，该算法可以有效抑制杂波并提高跟踪性能。

Chapter I: Adaptation and Congestion in a Multi-Agent System to Analyse Empirical Traffic Problems Chapter II: A Multi-Agent Modeling Approach to Simulate Dynamic Activity-Travel Patterns Chapter III: MATSim-T: Architecture and Simulation Times Chapter IV: TRASS: A Multi-Purpose Agent-Based Simulation Framework for Complex Traffic Simulation Applications Chapter V: Applying Situated Agents to Microscopic Traffic Modelling Chapter VI: Fundamentals of Pedestrian and Evacuation Dynamics Chapter VII:“Social Potential” Models for Modeling Traffic and Transportation Chapter VIII: Towards Simulating Cognitive Agents in Public Transport Systems Chapter IX：An Unmanaged Intersection Protocol and ImprovedIntersection Safety for Autonomous Vehicles Chapter X：Valuation-Aware Traffic Control: The Notion and the Issues Chapter XI：Learning Agents for Collaborative Driving Chapter XII：Traffic Congestion Management as a Learning Agent Coordination Problem Chapter XIII：Exploring the Potential of Multiagent Learning for Autonomous Intersection Control Chapter XIV：New Approach to Smooth Traffic Flow with Route Information Sharing Multiagent Learning on Traffic：Lights Control: Effects of Using Shared Information Chapter XVI：The Merit of Agents in Freight Transport Chapter XVII Analyzing Transactions Costs in Transport Corridors Using Multi Agent-Based Simulation Chapter XVIII：A Multi-Agent Simulation of Collaborative Air Traffic Flow Management