The large gap between the generalization level of state-of-the-art machine learning and human learning systems calls for the development of artificial intelligence (AI) models that are truly inspired by human cognition. In tasks related to image analysis, searching for pixel-level regularities has reached a power of information extraction still far from what humans capture with image-based observations. This leads to poor generalization when even small shifts occur at the level of the observations. We explore a perspective on this problem that is directed to learning the generative process with causality-related foundations, using models capable of combining symbolic manipulation, probabilistic reasoning and pattern recognition abilities. We briefly review and explore connections of research from machine learning, cognitive science and related fields of human behavior to support our perspective for the direction to more robust and human-like artificial learning systems.

中文翻译：

---

通过更高级别的信息提取进行因果表示学习


最先进的机器学习和人类学习系统的泛化水平之间存在巨大差距，这要求开发真正受人类认知启发的人工智能 （AI） 模型。在与图像分析相关的任务中，搜索像素级规律已经达到了信息提取的能力，但与人类通过基于图像的观察所捕获的能力相去甚远。当在观测值级别发生微小的偏移时，这会导致泛化效果不佳。我们探讨了这个问题的一个观点，即使用能够结合符号操作、概率推理和模式识别能力的模型，以因果关系为基础来学习生成过程。我们简要回顾和探索机器学习、认知科学和人类行为相关领域的研究联系，以支持我们对更强大和类似人类的人工学习系统方向的看法。