强化学习(RL)通过原始像素成像和连续的控制任务在视频游戏中表现出了令人印象深刻的表现。但是,RL的性能较差,例如原始像素图像,例如原始像素图像。人们普遍认为,基于物理状态的RL策略(例如激光传感器测量值)比像素学习相比会产生更有效的样品结果。这项工作提出了一种新方法,该方法从深度地图估算中提取信息,以教授RL代理以执行无人机导航(UAV)的无地图导航。我们提出了深度模仿的对比度无监督的优先表示(DEPTH-CUPRL),该表示具有优先重播记忆的估算图像的深度。我们使用RL和对比度学习的组合,根据图像的RL问题引发。从无人驾驶汽车(UAV)对结果的分析中,可以得出结论,我们的深度cuprl方法在无MAP导航能力中对决策和优于最先进的像素的方法有效。
translated by 谷歌翻译
本文介绍了一种新型深度加强基于基于深度加强学习的3D Fapless导航系统(无人机)。我们提出了一个简单的学习系统,而不是使用一种简单的学习系统,该系统仅使用来自距离传感器的一些稀疏范围数据来训练学习代理。我们基于我们对两种最先进的双重评论家深度RL模型的方法:双延迟深度确定性政策梯度(TD3)和软演员 - 评论家(SAC)。我们表明,我们的两种方法可以基于深度确定性政策梯度(DDPG)技术和Bug2算法来胜过一种方法。此外,我们基于经常性神经网络(RNNS)的新的深度RL结构优于用于执行移动机器人的FAPLESS导航的当前结构。总体而言,我们得出结论,基于双重评论评价的深度RL方法与经常性神经网络(RNNS)更适合进行熔化的导航和避免无人机。
translated by 谷歌翻译
人类机器人相互作用(HRI)对于在日常生活中广泛使用机器人至关重要。机器人最终将能够通过有效的社会互动来履行人类文明的各种职责。创建直接且易于理解的界面,以与机器人开始在个人工作区中扩散时与机器人互动至关重要。通常,与模拟机器人的交互显示在屏幕上。虚拟现实(VR)是一个更具吸引力的替代方法,它为视觉提示提供了更像现实世界中看到的线索。在这项研究中,我们介绍了Jubileo,这是一种机器人的动画面孔,并使用人类机器人社会互动领域的各种研究和应用开发工具。Jubileo Project不仅提供功能齐全的开源物理机器人。它还提供了一个全面的框架,可以通过VR接口进行操作,从而为HRI应用程序测试带来沉浸式环境,并明显更好地部署速度。
translated by 谷歌翻译
先前的工作表明,深-RL可以应用于无地图导航,包括混合无人驾驶空中水下车辆(Huauvs)的中等过渡。本文介绍了基于最先进的演员批评算法的新方法,以解决Huauv的导航和中型过渡问题。我们表明,具有复发性神经网络的双重评论家Deep-RL可以使用仅范围数据和相对定位来改善Huauvs的导航性能。我们的深-RL方法通过通过不同的模拟场景对学习的扎实概括,实现了更好的导航和过渡能力,表现优于先前的方法。
translated by 谷歌翻译
深钢筋学习中的确定性和随机技术已成为改善运动控制和各种机器人的决策任务的有前途的解决方案。先前的工作表明,这些深-RL算法通常可以应用于一般的移动机器人的无MAP导航。但是,他们倾向于使用简单的传感策略,因为已经证明它们在高维状态空间(例如基于图像的传感的空间)方面的性能不佳。本文在执行移动机器人无地图导航的任务时,对两种深-RL技术 - 深确定性政策梯度(DDPG)和软参与者(SAC)进行了比较分析。我们的目标是通过展示神经网络体系结构如何影响学习本身的贡献,并根据每种方法的航空移动机器人导航的时间和距离提出定量结果。总体而言,我们对六个不同体系结构的分析强调了随机方法(SAC)更好地使用更深的体系结构,而恰恰相反发生在确定性方法(DDPG)中。
translated by 谷歌翻译
机器人模拟一直是机器人领域研发的组成部分。模拟消除了通过启用机器人的应用测试来快速,负担得起的,而无需遭受机械或电子误差而进行机器人应用测试,从而消除了对传感器,电动机和实际机器人物理结构的可能性。通过虚拟现实(VR)模拟,通过提供更好的环境可视化提示,为与模拟机器人互动提供了更具吸引力的替代方法,从而提供了更严肃的体验。这种沉浸至关重要,尤其是在讨论社交机器人时,人类机器人相互作用(HRI)领域的子区域。在日常生活中,机器人的广泛使用取决于HRI。将来,机器人将能够与人们有效互动,以在人类文明中执行各种任务。在个人工作空间开始扩散时,为机器人开发简单且易于理解的接口至关重要。因此,在这项研究中,我们实施了一个使用现成的工具和包装的VR机器人框架,以增强社交HRI的研究和应用开发。由于整个VR接口是一个开源项目,因此可以在身临其境的环境中进行测试,而无需物理机器人。
translated by 谷歌翻译
在这项工作中,研究了来自磁共振图像的脑年龄预测的深度学习技术,旨在帮助鉴定天然老化过程的生物标志物。生物标志物的鉴定可用于检测早期神经变性过程,以及预测与年龄相关或与非年龄相关的认知下降。在这项工作中实施并比较了两种技术:应用于体积图像的3D卷积神经网络和应用于从轴向平面的切片的2D卷积神经网络,随后融合各个预测。通过2D模型获得的最佳结果,其达到了3.83年的平均绝对误差。 - Neste Trabalho S \〜AO InvestigaDAS T \'Ecnicas de Aprendizado Profundo Para a previ \ c {c} \〜ate daade脑电站a partir de imagens de resson \ ^ ancia magn \'etica,Visando辅助Na Identifica \ c {C} \〜AO de BioMarcadores Do Processo Natural de Envelhecimento。一个identifica \ c {c} \〜ao de bioMarcarcores \'e \'util para a detec \ c {c} \〜ao de um processo neurodegenerativo em Est \'Agio无数,Al \'em de possibilitar Prever Um decl 'inio cognitivo relacionado ou n \〜ao \`一个懒惰。 Duas T \'ECICAS S \〜AO ImportyAdas E Comparadas Teste Trabalho:Uma Rede神经卷应3D APLICADA NA IMAGEM VOLUM \'ETRICA E UME REDE神经卷轴2D APLICADA A FATIAS DO PANIAS轴向,COM后面fus \〜AO DAS PREDI \ C {c} \ \ oes个人。 o Melhor ResultAdo Foi optido Pelo Modelo 2D,Que Alcan \ C {C} OU UM ERRO M \'EDIO ABSOLUTO DE 3.83 ANOS。
translated by 谷歌翻译
Selecting the number of topics in LDA models is considered to be a difficult task, for which alternative approaches have been proposed. The performance of the recently developed singular Bayesian information criterion (sBIC) is evaluated and compared to the performance of alternative model selection criteria. The sBIC is a generalization of the standard BIC that can be implemented to singular statistical models. The comparison is based on Monte Carlo simulations and carried out for several alternative settings, varying with respect to the number of topics, the number of documents and the size of documents in the corpora. Performance is measured using different criteria which take into account the correct number of topics, but also whether the relevant topics from the DGPs are identified. Practical recommendations for LDA model selection in applications are derived.
translated by 谷歌翻译
Applying deep learning concepts from image detection and graph theory has greatly advanced protein-ligand binding affinity prediction, a challenge with enormous ramifications for both drug discovery and protein engineering. We build upon these advances by designing a novel deep learning architecture consisting of a 3-dimensional convolutional neural network utilizing channel-wise attention and two graph convolutional networks utilizing attention-based aggregation of node features. HAC-Net (Hybrid Attention-Based Convolutional Neural Network) obtains state-of-the-art results on the PDBbind v.2016 core set, the most widely recognized benchmark in the field. We extensively assess the generalizability of our model using multiple train-test splits, each of which maximizes differences between either protein structures, protein sequences, or ligand extended-connectivity fingerprints. Furthermore, we perform 10-fold cross-validation with a similarity cutoff between SMILES strings of ligands in the training and test sets, and also evaluate the performance of HAC-Net on lower-quality data. We envision that this model can be extended to a broad range of supervised learning problems related to structure-based biomolecular property prediction. All of our software is available as open source at https://github.com/gregory-kyro/HAC-Net/.
translated by 谷歌翻译
Counterfactual explanation is a common class of methods to make local explanations of machine learning decisions. For a given instance, these methods aim to find the smallest modification of feature values that changes the predicted decision made by a machine learning model. One of the challenges of counterfactual explanation is the efficient generation of realistic counterfactuals. To address this challenge, we propose VCNet-Variational Counter Net-a model architecture that combines a predictor and a counterfactual generator that are jointly trained, for regression or classification tasks. VCNet is able to both generate predictions, and to generate counterfactual explanations without having to solve another minimisation problem. Our contribution is the generation of counterfactuals that are close to the distribution of the predicted class. This is done by learning a variational autoencoder conditionally to the output of the predictor in a join-training fashion. We present an empirical evaluation on tabular datasets and across several interpretability metrics. The results are competitive with the state-of-the-art method.
translated by 谷歌翻译