在最近的研究中，自我监管的预训练模型倾向于在转移学习中优于监督的预训练模型。特别是，可以在语音应用中使用语音级语音表示的自我监督学习（SSL），这些语音应用需要歧视性表示话语中一致属性的表示：说话者，语言，情感和年龄。现有的框架级别的自我监督语音表示，例如WAV2VEC，可以用作带有汇总的话语级表示，但这些模型通常很大。也有SSL技术可以学习话语级的表示。最成功的方法之一是一种对比方法，它需要负采样：选择替代样品与当前样品（锚）对比。但是，这并不确保所有负面样本属于与没有标签的锚类别不同的类别。本文应用了一种非对抗性的自我监督方法来学习话语级的嵌入。我们对没有标签（Dino）从计算机视觉到语音进行了调整，没有标签（Dino）。与对比方法不同，Dino不需要负抽样。我们将Dino与受到监督方式训练的X-Vector进行了比较。当转移到下游任务（说话者验证，语音情绪识别（SER）和阿尔茨海默氏病检测）时，Dino的表现优于X-Vector。我们研究了转移学习过程中几个方面的影响，例如将微调过程分为步骤，块长度或增强。在微调过程中，首先调整最后一个仿射层，然后整个网络一次超过微调。使用较短的块长度，尽管它们产生了更多不同的输入，但并不一定会提高性能，这意味着至少需要具有特定长度的语音段才能为每个应用程序提高性能。增强对SER有帮助。
translated by 谷歌翻译
Ithaca is a Fuzzy Logic (FL) plugin for developing artificial intelligence systems within the Unity game engine. Its goal is to provide an intuitive and natural way to build advanced artificial intelligence systems, making the implementation of such a system faster and more affordable. The software is made up by a C\# framework and an Application Programming Interface (API) for writing inference systems, as well as a set of tools for graphic development and debugging. Additionally, a Fuzzy Control Language (FCL) parser is provided in order to import systems previously defined using this standard.
translated by 谷歌翻译
Many natural language related applications involve text generation, created by humans or machines. While in many of those applications machines support humans, yet in few others, (e.g. adversarial machine learning, social bots and trolls) machines try to impersonate humans. In this scope, we proposed and evaluated several mutation-based text generation approaches. Unlike machine-based generated text, mutation-based generated text needs human text samples as inputs. We showed examples of mutation operators but this work can be extended in many aspects such as proposing new text-based mutation operators based on the nature of the application.
translated by 谷歌翻译
Evaluating new techniques on realistic datasets plays a crucial role in the development of ML research and its broader adoption by practitioners. In recent years, there has been a significant increase of publicly available unstructured data resources for computer vision and NLP tasks. However, tabular data -- which is prevalent in many high-stakes domains -- has been lagging behind. To bridge this gap, we present Bank Account Fraud (BAF), the first publicly available privacy-preserving, large-scale, realistic suite of tabular datasets. The suite was generated by applying state-of-the-art tabular data generation techniques on an anonymized,real-world bank account opening fraud detection dataset. This setting carries a set of challenges that are commonplace in real-world applications, including temporal dynamics and significant class imbalance. Additionally, to allow practitioners to stress test both performance and fairness of ML methods, each dataset variant of BAF contains specific types of data bias. With this resource, we aim to provide the research community with a more realistic, complete, and robust test bed to evaluate novel and existing methods.
translated by 谷歌翻译
Equivariance of neural networks to transformations helps to improve their performance and reduce generalization error in computer vision tasks, as they apply to datasets presenting symmetries (e.g. scalings, rotations, translations). The method of moving frames is classical for deriving operators invariant to the action of a Lie group in a manifold.Recently, a rotation and translation equivariant neural network for image data was proposed based on the moving frames approach. In this paper we significantly improve that approach by reducing the computation of moving frames to only one, at the input stage, instead of repeated computations at each layer. The equivariance of the resulting architecture is proved theoretically and we build a rotation and translation equivariant neural network to process volumes, i.e. signals on the 3D space. Our trained model overperforms the benchmarks in the medical volume classification of most of the tested datasets from MedMNIST3D.
translated by 谷歌翻译
Specular microscopy assessment of the human corneal endothelium (CE) in Fuchs' dystrophy is challenging due to the presence of dark image regions called guttae. This paper proposes a UNet-based segmentation approach that requires minimal post-processing and achieves reliable CE morphometric assessment and guttae identification across all degrees of Fuchs' dystrophy. We cast the segmentation problem as a regression task of the cell and gutta signed distance maps instead of a pixel-level classification task as typically done with UNets. Compared to the conventional UNet classification approach, the distance-map regression approach converges faster in clinically relevant parameters. It also produces morphometric parameters that agree with the manually-segmented ground-truth data, namely the average cell density difference of -41.9 cells/mm2 (95% confidence interval (CI) [-306.2, 222.5]) and the average difference of mean cell area of 14.8 um2 (95% CI [-41.9, 71.5]). These results suggest a promising alternative for CE assessment.
translated by 谷歌翻译
尽管沟通延迟可能会破坏多种系统，但大多数现有的多基因轨迹计划者都缺乏解决此问题的策略。最先进的方法通常采用完美的通信环境，这在现实世界实验中几乎是现实的。本文介绍了强大的Mader（RMADER），这是一个分散的异步多轨迹计划者，可以处理代理商之间的通信延迟。通过广播新优化的轨迹和忠实的轨迹，并执行延迟检查步骤，Rmader即使在通信延迟下也能够保证安全。Rmader通过广泛的仿真和硬件飞行实验得到了验证，并获得了100％的无碰撞轨迹生成成功率，表现优于最先进的方法。
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
本文介绍了Deep-Panther，这是一种基于学习的感知感知的轨迹计划者，用于动态环境中无人驾驶汽车（UAV）。鉴于无人机的当前状态以及障碍物的预测轨迹和大小，深板产生了多个轨迹，以避免动态障碍物，同时使其在板载摄像头的视野（FOV）中最大化。为了获得计算上的实时解决方案，使用基于多模式优化的专家提供的演示来利用模仿学习来训练深层策略。广泛的模拟显示，重型时间比基于优化的专家快两个数量级，同时达到了类似的成本。通过确保将每个专家轨迹分配到损失功能中的一个独特的学生轨迹，深层脚步还可以捕获问题的多模式，并在最多18次的专家方面实现平均误差（MSE）损失（MSE）损失小于最先进的（轻松）获奖者 - 全部方法。还证明了深层扫描剂可以很好地推广到与训练中使用的障碍轨迹的障碍轨迹。
translated by 谷歌翻译