And there is some robustness in the systems.

而且系统具有一定的。

Another is that we need to strap everything down because current eye-tracking algorithms don't have the robustness that we need.

另一个原是，我们需要固定好所有东西，当前的眼动追踪算法不具备我们所需的。

For example, adversary robustness of proxy models, representation engineering, power aversion, and just like making sure that the model is honest.

例如，代理模型的对抗、表征工程、对权力的回避，以及确保模型诚实无欺。

Robustness can be affected by multiple factors, such as an aging facility, insufficient maintenance or an operational design that is vulnerable to human error.

可能受到多种素的响, 例如设备老化、维护不足或易受人错误响的操作设计。

So, you know, we're There's a whole industry around sort of figuring out how do you exact the robustness and precision out of these models.

所以，你知道，整个行业都在研究如何从这些模型中提取出和精确。

The robustness of the answer can be questionable, but assuming, and let's just for argument's sake, perfect robustness, I think it can really simplify the interface to AI.

答案的可能值得怀疑，但假设——姑且这么说——完美的，我认真的可以简化与人工智能的交互界面。

For instance, it can measure the adversarial robustness of such a network, and this is super useful, because it gives us information whether there are possible forged inputs that could break our learning systems.

比如，可以测量这样一个神经网络的对抗，这超级有用，可以让我们知道是否存在可能破坏学习系统的伪造样本输入。

And so there's some aspect of imperfection that we need to have built in, like robustness to imperfection be part of our systems, which is a difficult thing for engineers to contend with.

此， 我们需要内置一些不完美的方面，就像将对不完美的作我们系统的一部分，这对工程师来说是一个难以应对的问题。

And basically this, the fact that we're trying to learn these neural networks that are predicting these features from images that are robust on data augmentation has been the key for visual self-supervised learning.

基本上，这一关键在于我们正尝试训练的神经网络，们能够从经过数据增强处理的图像中预测出这些特征，并且具备。这已成视觉自监督学习的核心所在。

The results demonstrated that this system was robust against various illuminations and complex backgrounds, and yielded satisfactory segmentation and picking-point detection performances for minor and medium occlusion or overlap, and for medium and large mangoes.

研究结果表明，该系统在各种光照条件和复杂背景下表现出较强的，对于轻微和中度遮挡或重叠情况下的中等及大型芒果，其分割效果和采摘点检测能均令人满意。