关于神经网络的视觉分析智能
On the visual analytic intelligence of neural networks
摘要:
视觉古怪任务被认为是一种通用的人类种族独立的分析智力测试。人工智能的进步带来了重要的突破,但在这种分析智能任务上与人类竞争仍然具有挑战性,并且通常采用非生物学合理的架构。我们提出了一个生物现实的系统,从合成的眼球运动-扫视,并与神经元纳入新皮层神经元的动力学处理它们的输入。我们引入了一个程序生成的视觉奇怪的数据集训练的架构扩展传统的关系网络和我们提出的系统。这两种方法都超过了人类的准确性,我们发现,两者都有相同的基本推理机制。最后,我们证明了生物启发网络具有更高的准确性,学习速度更快,并且比传统网络需要更少的参数。
英文摘要:
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.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。