综合光子神经网络(IPNN)成为常规电子AI加速器的有前途的后继者,因为它们在计算速度和能源效率方面提供了实质性的提高。特别是,相干IPNN使用Mach-Zehnder干涉仪(MZIS)的阵列进行单位转换来执行节能矩阵矢量乘法。然而,IPNN中的基本MZI设备易受光刻变化和热串扰引起的不确定性,并且由于不均匀的MZI插入损失和量化错误而导致不确定的不确定性,这是由于调谐相角的编码较低而导致的。在本文中,我们首次使用自下而上的方法系统地表征了IPNN中这种不确定性和不确定性(共同称为缺陷)的影响。我们表明,它们对IPNN准确性的影响可能会根据受影响组件的调谐参数(例如相角),其物理位置以及缺陷的性质和分布而差异很大。为了提高可靠性措施,我们确定了关键的IPNN构件,在不完美之下,这些基础可能导致分类准确性的灾难性降解。我们表明,在多个同时缺陷下,即使不完美参数限制在较小的范围内,IPNN推断精度也可能会降低46%。我们的结果还表明,推论精度对影响IPNN输入层旁边的线性层中MZI的缺陷敏感。
translated by 谷歌翻译
基于奇异值分解的相干集成光子神经网络(SC-IPNN)具有大的占地面积,遭受高静态功耗进行训练和推理,并且不能使用传统的DNN修剪技术进行修剪。我们利用彩票假设提出了一种用于SC-IPN的第一种硬件感知修剪方法,通过最小化重量参数的数量来缓解这些挑战。我们修剪基于多层的Perceptron的SC-IPN,并显示高达89%的相位角,其对应于SC-IPNN中的重量参数,可以在减少时具有可忽略的精度损失(小于5%)。静电功耗高达86%。
translated by 谷歌翻译
我们提出了一种用于相干光子神经网络的新型硬件感知幅度修剪技术。该技术可以将99.45%的网络参数进行99.45%,并将静态功耗降低98.23%,精度损失可忽略不计。
translated by 谷歌翻译
We study the problem of training and certifying adversarially robust quantized neural networks (QNNs). Quantization is a technique for making neural networks more efficient by running them using low-bit integer arithmetic and is therefore commonly adopted in industry. Recent work has shown that floating-point neural networks that have been verified to be robust can become vulnerable to adversarial attacks after quantization, and certification of the quantized representation is necessary to guarantee robustness. In this work, we present quantization-aware interval bound propagation (QA-IBP), a novel method for training robust QNNs. Inspired by advances in robust learning of non-quantized networks, our training algorithm computes the gradient of an abstract representation of the actual network. Unlike existing approaches, our method can handle the discrete semantics of QNNs. Based on QA-IBP, we also develop a complete verification procedure for verifying the adversarial robustness of QNNs, which is guaranteed to terminate and produce a correct answer. Compared to existing approaches, the key advantage of our verification procedure is that it runs entirely on GPU or other accelerator devices. We demonstrate experimentally that our approach significantly outperforms existing methods and establish the new state-of-the-art for training and certifying the robustness of QNNs.
translated by 谷歌翻译
The increasing number of surveillance cameras and security concerns have made automatic violent activity detection from surveillance footage an active area for research. Modern deep learning methods have achieved good accuracy in violence detection and proved to be successful because of their applicability in intelligent surveillance systems. However, the models are computationally expensive and large in size because of their inefficient methods for feature extraction. This work presents a novel architecture for violence detection called Two-stream Multi-dimensional Convolutional Network (2s-MDCN), which uses RGB frames and optical flow to detect violence. Our proposed method extracts temporal and spatial information independently by 1D, 2D, and 3D convolutions. Despite combining multi-dimensional convolutional networks, our models are lightweight and efficient due to reduced channel capacity, yet they learn to extract meaningful spatial and temporal information. Additionally, combining RGB frames and optical flow yields 2.2% more accuracy than a single RGB stream. Regardless of having less complexity, our models obtained state-of-the-art accuracy of 89.7% on the largest violence detection benchmark dataset.
translated by 谷歌翻译
We study the problem of learning controllers for discrete-time non-linear stochastic dynamical systems with formal reach-avoid guarantees. This work presents the first method for providing formal reach-avoid guarantees, which combine and generalize stability and safety guarantees, with a tolerable probability threshold $p\in[0,1]$ over the infinite time horizon. Our method leverages advances in machine learning literature and it represents formal certificates as neural networks. In particular, we learn a certificate in the form of a reach-avoid supermartingale (RASM), a novel notion that we introduce in this work. Our RASMs provide reachability and avoidance guarantees by imposing constraints on what can be viewed as a stochastic extension of level sets of Lyapunov functions for deterministic systems. Our approach solves several important problems -- it can be used to learn a control policy from scratch, to verify a reach-avoid specification for a fixed control policy, or to fine-tune a pre-trained policy if it does not satisfy the reach-avoid specification. We validate our approach on $3$ stochastic non-linear reinforcement learning tasks.
translated by 谷歌翻译
在自动机器人群的现有文献中,采用的可见性模型具有一些与实际传感设备实现不符的理想主义假设。本文在更现实的可见性模型中调查了这个问题,称为不透明的脂肪机器人,具有纤细的全向相机。机器人被建模为单位磁盘,每个磁盘都具有全向摄像头,表示为尺寸较小的磁盘。我们假设机器人具有指南针,可以在其局部坐标系统的两个轴方向和方向上达成共识。机器人配备了可见的灯光,这些灯光是通信的媒介,也可以用作记忆的形式。我们为相互可见性问题提供了分布式算法,该算法在半同步设置中被证明是正确的。我们的算法还为领导者选举提供了解决方案,我们将其用作主要算法中的子例程。尽管在完整的可见性模型中,领导者选举在两个轴心协议中是微不足道的,但在我们的案例中,这是具有挑战性的,并且具有独立的利益。
translated by 谷歌翻译
我们考虑在离散时间非线性随机控制系统中正式验证几乎核实(A.S.)渐近稳定性的问题。在文献中广泛研究确定性控制系统中的验证稳定性,验证随机控制系统中的验证稳定性是一个开放的问题。本主题的少数现有的作品只考虑专门的瞬间形式,或对系统进行限制性假设,使其无法与神经网络策略的学习算法不适用。在这项工作中,我们提出了一种具有两种新颖方面的一般非线性随机控制问题的方法:(a)Lyapunov函数的经典随机扩展,我们使用排名超大地区(RSMS)来证明〜渐近稳定性,以及(B)我们提出一种学习神经网络RSM的方法。我们证明我们的方法保证了系统的渐近稳定性,并提供了第一种方法来获得稳定时间的界限,其中随机Lyapunov功能不。最后,我们在通过神经网络政策的一套非线性随机强化学习环境上通过实验验证我们的方法。
translated by 谷歌翻译
纵向脑磁共振成像(MRI)含有病理扫描的登记是由于组织外观变化而挑战,仍然是未解决的问题。本文介绍了第一脑肿瘤序列登记(Brats-Reg)挑战,重点是估计诊断患有脑弥漫性胶质瘤的同一患者的术前和后续扫描之间的对应关系。 Brats-Reg挑战打算建立可变形登记算法的公共基准环境。关联的数据集包括根据公共解剖模板,为每个扫描的大小和分辨率策划的DE识别的多机构多参数MRI(MPMRI)数据。临床专家在扫描内产生了广泛的标志标记点,描述了跨时域的不同解剖位置。培训数据以及这些地面真相注释将被释放给参与者来设计和开发他们的注册算法,而组织者将扣留验证和测试数据的注释,并用于评估参与者的集装箱化算法。每个所提交的算法都将使用几个度量来定量评估,例如中位绝对误差(MAE),鲁棒性和雅可比的决定因素。
translated by 谷歌翻译
贝叶斯神经网络(BNNS)将分布放在神经网络的重量上,以模拟数据的不确定性和网络的预测。我们考虑在具有无限时间地平线系统的反馈循环中运行贝叶斯神经网络策略时验证安全的问题。与现有的基于样品的方法相比,这是不可用的无限时间地平线设置,我们训练一个单独的确定性神经网络,用作无限时间的地平线安全证书。特别是,我们证明证书网络保证了系统的安全性在BNN重量后部的子集上。我们的方法首先计算安全重量,然后改变BNN的重量后,以拒绝在该组外的样品。此外,我们展示了如何将我们的方法扩展到安全探索的强化学习环境,以避免在培训政策期间的不安全轨迹。我们在一系列加固学习基准上评估了我们的方法,包括非Lyapunovian安全规范。
translated by 谷歌翻译