基于惯性数据的人类活动识别(HAR)是从智能手机到超低功率传感器的嵌入式设备上越来越扩散的任务。由于深度学习模型的计算复杂性很高,因此大多数嵌入式HAR系统基于简单且不那么精确的经典机器学习算法。这项工作弥合了在设备上的HAR和深度学习之间的差距,提出了一组有效的一维卷积神经网络(CNN),可在通用微控制器(MCUS)上部署。我们的CNN获得了将超参数优化与子字节和混合精确量化的结合,以在分类结果和记忆职业之间找到良好的权衡。此外,我们还利用自适应推断作为正交优化,以根据处理后的输入来调整运行时的推理复杂性,从而产生更灵活的HAR系统。通过在四个数据集上进行实验,并针对超低功率RISC-V MCU,我们表明(i)我们能够为HAR获得一组丰富的帕累托(Pareto)最佳CNN,以范围超过1个数量级记忆,潜伏期和能耗; (ii)由于自适应推断,我们可以从单个CNN开始得出> 20个运行时操作模式,分类分数的不同程度高达10%,并且推理复杂性超过3倍,并且内存开销有限; (iii)在四个基准中的三个基准中,我们的表现都超过了所有以前的深度学习方法,将记忆占用率降低了100倍以上。获得更好性能(浅层和深度)的少数方法与MCU部署不兼容。 (iv)我们所有的CNN都与推理延迟<16ms的实时式evice Har兼容。他们的记忆职业在0.05-23.17 kb中有所不同,其能源消耗为0.005和61.59 UJ,可在较小的电池供应中进行多年的连续操作。
translated by 谷歌翻译
量化广泛用于云和边缘系统,以减少深层神经网络的记忆占用,潜伏期和能耗。特别是,混合精液量化,即,在网络的不同部分中使用不同的位宽度,已被证明可以提供出色的效率提高,尤其是通过自动化神经体系结构确定的优化的位宽度分配,尤其是通过自动化的位宽度分配(NAS)工具。最先进的混合精液在层面上,即,它对每个网络层的权重和激活张量使用不同的位宽度。在这项工作中,我们扩大了搜索空间,提出了一种新颖的NA,该NAS独立选择每个重量张量通道的位宽度。这为工具提供了额外的灵活性,即仅针对与最有用的功能相关的权重分配更高的精度。在MLPERF微小的基准套件上进行测试,我们获得了精确度大小与精度与能量空间的帕累托最佳模型的丰富集合。当部署在MPIC RISC-V边缘处理器上时,我们的网络将记忆和能量分别减少了63%和27%,而与层的方法相比,以相同的精度为单位。
translated by 谷歌翻译
与液态燃料相比,电动汽车(EV)的广泛采用受到目前能量和功率密度低的电池的限制,并且会随着时间的推移而衰老和性能恶化。因此,在电动汽车生命周期内监视电池电量状态(SOC)和健康状况(SOH)是一个非常相关的问题。这项工作提出了一个电池数字双结构结构,旨在在运行时准确反映电池动力学。为了确保有关非线性现象的高度正确性,数字双胞胎依赖于在电池演化痕迹随时间训练的数据驱动模型中依靠:SOH模型,反复执行以估计最大电池容量的退化和SOC型号的降级,定期重新训练以反映衰老的影响。拟议的数字双结构将在公共数据集上举例说明,以激发其采用并证明其有效性,并具有很高的准确性和推理以及与车载执行兼容的时间。
translated by 谷歌翻译
人类活动识别(HAR)已成为嵌入式设备(例如智能手表)越来越流行的任务。大多数用于超低功率设备的HAR系统基于经典机器学习(ML)模型,而深度学习(DL)虽然达到最先进的精度,但由于其高能量消耗而不太受欢迎,这构成对电池经营和资源约束的设备的重大挑战。在这项工作中,由于由决策树(DT)和一个维度卷积神经网络(1D CNN)组成的层次结构,我们弥合了设备HAR和DL之间的差距。这两个分类器以两种不同的子任务的方式运行:DT仅分类最简单的活动,而CNN则处理更复杂的活动。通过对最先进的数据集进行实验并针对单核RISC-V MCU,我们表明这种方法可节省高达67.7%的能源W.R.T. ISO准确性的“独立” DL架构。此外,两阶段系统要么引入可忽略不计的内存开销(最多200 b),要么相反,可以减少整体记忆职业。
translated by 谷歌翻译
Artificial neural networks can learn complex, salient data features to achieve a given task. On the opposite end of the spectrum, mathematically grounded methods such as topological data analysis allow users to design analysis pipelines fully aware of data constraints and symmetries. We introduce a class of persistence-based neural network layers. Persistence-based layers allow the users to easily inject knowledge about symmetries (equivariance) respected by the data, are equipped with learnable weights, and can be composed with state-of-the-art neural architectures.
translated by 谷歌翻译
We consider the problem of two active particles in 2D complex flows with the multi-objective goals of minimizing both the dispersion rate and the energy consumption of the pair. We approach the problem by means of Multi Objective Reinforcement Learning (MORL), combining scalarization techniques together with a Q-learning algorithm, for Lagrangian drifters that have variable swimming velocity. We show that MORL is able to find a set of trade-off solutions forming an optimal Pareto frontier. As a benchmark, we show that a set of heuristic strategies are dominated by the MORL solutions. We consider the situation in which the agents cannot update their control variables continuously, but only after a discrete (decision) time, $\tau$. We show that there is a range of decision times, in between the Lyapunov time and the continuous updating limit, where Reinforcement Learning finds strategies that significantly improve over heuristics. In particular, we discuss how large decision times require enhanced knowledge of the flow, whereas for smaller $\tau$ all a priori heuristic strategies become Pareto optimal.
translated by 谷歌翻译
Token free approaches have been successfully applied to a series of word and span level tasks. In this work, we compare a byte-level (ByT5) and a wordpiece based (mT5) sequence to sequence model on the 51 languages of the MASSIVE multilingual semantic parsing dataset. We examine multiple experimental settings: (i) zero-shot, (ii) full gold data and (iii) zero-shot with synthetic data. By leveraging a state-of-the-art label projection method for machine translated examples, we are able to reduce the gap in exact match accuracy to only 5 points with respect to a model trained on gold data from all the languages. We additionally provide insights on the cross-lingual transfer of ByT5 and show how the model compares with respect to mT5 across all parameter sizes.
translated by 谷歌翻译
Artificial neural networks are functions depending on a finite number of parameters typically encoded as weights and biases. The identification of the parameters of the network from finite samples of input-output pairs is often referred to as the \emph{teacher-student model}, and this model has represented a popular framework for understanding training and generalization. Even if the problem is NP-complete in the worst case, a rapidly growing literature -- after adding suitable distributional assumptions -- has established finite sample identification of two-layer networks with a number of neurons $m=\mathcal O(D)$, $D$ being the input dimension. For the range $D<m<D^2$ the problem becomes harder, and truly little is known for networks parametrized by biases as well. This paper fills the gap by providing constructive methods and theoretical guarantees of finite sample identification for such wider shallow networks with biases. Our approach is based on a two-step pipeline: first, we recover the direction of the weights, by exploiting second order information; next, we identify the signs by suitable algebraic evaluations, and we recover the biases by empirical risk minimization via gradient descent. Numerical results demonstrate the effectiveness of our approach.
translated by 谷歌翻译
由于时空事件发生的随机性,在报告的交通中断开始时缺乏信息,并且缺乏运输工程的高级方法来从过去中获得见解,因此预测交通事故持续时间是一个难题事故。本文提出了一个新的Fusion框架,用于通过将机器学习与交通流量/速度和事件描述作为功能进行集成来预测有限信息的事件持续时间,并通过多种深度​​学习方法编码(ANN AUTOCONEDER和角色级别的LSTM-ANN情绪分类器)。该论文在运输和数据科学中构建了跨学科建模方法。该方法提高了适用于基线事件报告的最佳表现ML模型的入射持续时间预测准确性。结果表明,与标准线性或支持矢量回归模型相比,我们提出的方法可以提高准确性$ 60 \%$,并且相对于混合深度学习自动编码的GBDT模型的另外7美元\%$改进,这似乎胜过表现所有其他模型。应用区是旧金山市,富含交通事件日志(全国交通事故数据集)和过去的历史交通拥堵信息(Caltrans绩效测量系统的5分钟精度测量)。
translated by 谷歌翻译
为了了解强化学习的安全威胁(RL)算法,本文研究中毒攻击以操纵\ emph {any}订单 - 最佳学习算法对偶发性RL中有针对性的政策,并研究了两种自然中毒攻击的潜在损害,即,\ emph {Reward}和\ Emph {Action}的操作。我们发现攻击的影响至关重要地取决于奖励是有界还是无限的。在有限的奖励设置中,我们表明只有奖励操纵或只有动作操纵不能保证成功的攻击。但是,通过结合奖励和行动操纵,对手可以操纵任何订单最佳学习算法,以遵循任何有针对性的策略,并使用$ \ tilde {\ theta}(\ sqrt {t})$总攻击成本,这是订单 - 优越,最佳的攻击成本不知道基础MDP。相反,在无限的奖励设置中,我们表明奖励操纵攻击足以使对手成功操纵任何订单最佳学习算法,以使用$ \ tilde {o}(\ sqrt {t})遵循任何有针对性的策略污染。我们的结果揭示了有关中毒攻击无法获得或无法实现的有用见解,并将刺激有关强大RL算法设计的更多作品。
translated by 谷歌翻译