arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2002.04021cs.AIcs.RO
收藏

基于对象分解认知程序的快速概念推理模型

A Model of Fast Concept Inference with Object-Factorized Cognitive Programs

California Institute of Technology(加州理工学院);Vicarious AI(Vicarious人工智能公司)

Daniel P. Sawyer, Miguel Lázaro-Gredilla, Dileep George

摘要:

人类从少数图像中快速识别一般概念的能力已经被证明很难用机器人来模仿。最近,开发了一种计算机体系结构,其允许机器人通过使用原始认知功能的指令集将概念建模为认知程序来模仿这种人类能力的某些方面。这使得机器人能够在推广到物理世界之前,通过在世界模型中模拟候选程序来模仿人类的想象力。然而,这个模型使用了一个简单的搜索算法,需要30分钟才能发现一个概念,并且对于超过20条指令的程序来说变得难以处理。为了克服这一瓶颈,我们提出了一种算法,该算法模拟了人类对对象分解和子目标的认知能力,允许人类级别的推理速度,提高准确性,并使输出更具可解释性。

英文摘要:

The ability of humans to quickly identify general concepts from a handful of images has proven difficult to emulate with robots. Recently, a computer architecture was developed that allows robots to mimic some aspects of this human ability by modeling concepts as cognitive programs using an instruction set of primitive cognitive functions. This allowed a robot to emulate human imagination by simulating candidate programs in a world model before generalizing to the physical world. However, this model used a naive search algorithm that required 30 minutes to discover a single concept, and became intractable for programs with more than 20 instructions. To circumvent this bottleneck, we present an algorithm that emulates the human cognitive heuristics of object factorization and sub-goaling, allowing human-level inference speed, improving accuracy, and making the output more explainable.

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。

↑