We report new high-quality galaxy scale strong lens candidates found in the Kilo Degree Survey data release 4 using Machine Learning. We have developed a new Convolutional Neural Network (CNN) classifier to search for gravitational arcs, following the prescription by \cite{2019MNRAS.484.3879P} and using only $r-$band images. We have applied the CNN to two "predictive samples": a Luminous red galaxy (LRG) and a "bright galaxy" (BG) sample ($r<21$). We have found 286 new high probability candidates, 133 from the LRG sample and 153 from the BG sample. We have then ranked these candidates based on a value that combines the CNN likelihood to be a lens and the human score resulting from visual inspection (P-value) and we present here the highest 82 ranked candidates with P-values $\ge 0.5$. All these high-quality candidates have obvious arc or point-like features around the central red defector. Moreover, we define the best 26 objects, all with scores P-values $\ge 0.7$ as a "golden sample" of candidates. This sample is expected to contain very few false positives and thus it is suitable for follow-up observations. The new lens candidates come partially from the the more extended footprint adopted here with respect to the previous analyses, partially from a larger predictive sample (also including the BG sample). These results show that machine learning tools are very promising to find strong lenses in large surveys and more candidates that can be found by enlarging the predictive samples beyond the standard assumption of LRGs. In the future, we plan to apply our CNN to the data from next-generation surveys such as the Large Synoptic Survey Telescope, Euclid, and the Chinese Space Station Optical Survey.

中文翻译：

---

千度调查中具有深度学习的新的高质量强镜头候选者

我们报告了使用机器学习在 Kilo 度调查数据第 4 版中发现的新的高质量星系尺度强镜头候选者。我们开发了一种新的卷积神经网络 (CNN) 分类器来搜索引力弧，遵循 \cite{2019MNRAS.484.3879P} 的规定并且仅使用 $r-$band 图像。我们已经将 CNN 应用于两个“预测样本”：一个发光的红色星系 (LRG) 和一个“明亮的星系”(BG) 样本 ($r<21$)。我们发现了 286 个新的高概率候选者，其中 133 个来自 LRG 样本，153 个来自 BG 样本。然后，我们根据一个值对这些候选者进行了排名，该值结合了 CNN 成为镜头的可能性和视觉检查产生的人类得分（P 值），我们在此展示了 P 值 $\ge 0.5$ 的排名最高的 82 个候选者. 所有这些高质量的候选者在中央红色叛逃者周围都有明显的弧形或点状特征。此外，我们定义了最好的 26 个对象，所有对象的分数 P 值 $\ge 0.7$ 作为候选的“黄金样本”。该样本预计包含很少的误报，因此适用于后续观察。新的候选镜头部分来自此处采用的更广泛的足迹，相对于之前的分析，部分来自更大的预测样本（也包括 BG 样本）。这些结果表明，机器学习工具非常有希望在大型调查中找到强大的镜头，并且可以通过扩大超出 LRG 标准假设的预测样本来找到更多候选者。将来，