Visual oddity task was conceived as a universal ethnic-independent analytic intelligence test for humans. Advancements in artificial intelligence led to important breakthroughs, yet competing with humans on such analytic intelligence tasks remains challenging and typically resorts to non-biologically-plausible architectures. We present a biologically realistic system that receives inputs from synthetic eye movements - saccades, and processes them with neurons incorporating dynamics of neocortical neurons. We introduce a procedurally generated visual oddity dataset to train an architecture extending conventional relational networks and our proposed system. Both approaches surpass the human accuracy, and we uncover that both share the same essential underlying mechanism of reasoning. Finally, we show that the biologically inspired network achieves superior accuracy, learns faster and requires fewer parameters than the conventional network.
翻译:视觉奇特的任务被设计为人类的全民族独立分析智力测试。人工智能的进步导致了重要的突破,然而在这种分析智能任务上与人类竞争仍然具有挑战性,而且通常使用非生物可移植的建筑。我们提出了一个生物上现实的系统,接受合成眼睛运动-甲状腺运动的投入,并用神经元处理它们,其中含有新气候神经的动态。我们引入了一个程序生成的视觉奇特数据集,以训练一个扩展常规关系网络和我们拟议系统的架构。这两种方法都超过了人类的准确性,我们发现两者都有着相同的基本推理机制。最后,我们显示生物启发的网络比常规网络更精准,学习速度更快,需要的参数也比常规网络少。