Results 41 to 50 of about 5,206 (257)
AI in game intelligence—from multi-role game to parallel game [PDF]
, 2020 The domestic and overseas research progress of artificial intelligence technology in the field of games was summarized and the significance of the research progress in the field of games for real life was analyzed.In view of the gap between simulation ...
Han, Jinpeng +3 more
core +1 more source
Deception defense method against intelligent penetration attack [PDF]
, 2022 The intelligent penetration attack based on reinforcement learning aims to model the penetration process as a Markov decision process, and train the attacker to optimize the penetration path in a trial-and-error manner, so as to achieve strong attack ...
Changyou XING +3 more
core +1 more source
智能科学与技术学报, 2022 随着基础理论和硬件计算能力的飞速发展，深度学习技术在众多领域取得了令人瞩目的成绩。作为描述客观物理世界的重要工具，长期以来微分方程是各领域研究人员关心的重点。近年来，深度学习和微分方程的结合逐渐成了研究的热点。由于深度学习能够从大量数据中高效地提取特征，微分方程能够反应客观的物理规律，因此二者的结合可以有效地提升深度学习的泛化性，同时增强深度学习的可解释性。首先，介绍了深度学习求解微分方程的基本问题。其次，介绍了两类深度学习求解微分方程的方法：数据驱动和物理知情方法。然后 ...
卢经纬, 程相, 王飞跃
doaj
大数据, 2022 随着大数据的发展以及数据安全相关法规的出台，人们的隐私保护意识逐渐加强，“数据孤岛”现象愈发严重。联邦学习技术作为解决该问题的有效方法之一，已成为当下备受关注的热点。在纵向联邦学习在线推理过程中，当前的主流方法并未考虑对数据标识的保护。针对此问题，提出一种适用于纵向联邦线性模型在线推理过程中的成员推断攻击的隐私保护方法，通过构造具有假阳率的过滤器来避免对数据标识的精确定位，从而保证数据的安全性；使用同态加密实现在线推理过程的全密态，保护中间计算结果；根据同态加密的密文倍乘性质，使用随机数乘法盲化操作 ...
尹虹舒, 周旭华, 周文君
doaj +1 more source
Stealthy data poisoning attack method on offline reinforcement learning in unmanned systems [PDF]
Aiming at the limitations in effectiveness and stealth of existing offline reinforcement learning(RL) data poisoning attacks, a critical time-step dynamic poisoning attack was proposed, perturbing important samples to achieve efficient and covert attacks.
GAO Chaoyang +6 more
core +1 more source
Forwarding efficiency aware traffic scheduling algorithm based on deep reinforcement learning [PDF]
, 2022 The software defined network separates the control plane from the data plane to achieve flexible traffic scheduling, which can use network resources more efficiently.However, with the increase of the number of flow entries, load rate, the number of ...
Chuang SUN +4 more
core +1 more source
The role of child language ability and parental mentalization in early child dysregulation
Infant Mental Health Journal: Infancy and Early Childhood, EarlyView.Abstract Dysregulation in early childhood is associated with increased vulnerability to psychopathology and poor psychosocial outcomes. While there is evidence that both child language ability and parental mentalization are associated with dysregulation in early childhood, there is little understanding of the relationships between these variables, and ...
Sara Cibralic +6 more
wiley +1 more source
智能科学与技术学报, 2020 研究了基于深度强化学习算法的自主式水下航行器（AUV）深度控制问题。区别于传统的控制算法，深度强化学习方法让航行器自主学习控制律，避免人工建立精确模型和设计控制律。采用深度确定性策略梯度方法设计了actor与critic两种神经网络。actor神经网络给出控制策略，critic神经网络用于评估该策略，AUV的深度控制可以通过训练这两个神经网络实现。在OpenAI Gym平台上仿真验证了算法的有效性。
王日中, 李慧平, 崔迪, 徐德民
doaj
Risk, Hazards &Crisis in Public Policy, EarlyView.Abstract Norway's oil sector faces significant security challenges due to rapid technological advancements and heightened geopolitical tensions, particularly concerning threats from Russian drones. The sector maintains a vigilant approach, continually monitoring and adapting to evolving threats.
Riana Steen, Tommy B. Hansen
wiley +1 more source
Research on Stochastic Resonance Based on RLGA and its Application to Underwater Acoustic Signal Detection [PDF]
, 2017 我国在水下通信领域方面正在持续地投入研究，其中一个方面是通信中信号的检测。信号经过水声信道后往往都会被来自船舶、海洋生物或者人为的大量噪声和海面折射反射、频率选择性衰弱引起的干扰淹没，变为微弱信号。而水声信号的检测技术不论在理论钻研还是实际工程甚至国防建设中都具有重要的意义和应用价值。因此，研究微弱信号的检测方法对水声通信的进步和发展很有必要。 一些传统的信号检测方法如匹配滤波、相干检测、时频分析等都采用抑制噪声的方法，往往都是在抑制噪声的同时，在频率结构或者时域幅值上也不同程度地损害了有用信号 ...
季舒瑶
core