Toward human-level concept learning: Pattern benchmarking for AI algorithms

被引:14
|
作者
Holzinger, Andreas [1 ,3 ]
Saranti, Anna [1 ,3 ]
Angerschmid, Alessa [1 ,3 ]
Finzel, Bettina [2 ]
Schmid, Ute [2 ]
Mueller, Heimo [3 ]
机构
[1] Univ Nat Resources & Life Sci Vienna, Human Ctr AI Lab, Vienna, Austria
[2] Univ Bamberg, Bamberg, Germany
[3] Med Univ Graz, Graz, Austria
来源
PATTERNS | 2023年 / 4卷 / 08期
基金
奥地利科学基金会;
关键词
PROGRESSIVE MATRICES; LANGUAGE;
D O I
10.1016/j.patter.2023.100788
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Artificial intelligence (AI) today is very successful at standard pattern-recognition tasks due to the availability of large amounts of data and advances in statistical data-driven machine learning. However, there is still a large gap between AI pattern recognition and human-level concept learning. Humans can learn amazingly well even under uncertainty from just a few examples and are capable of generalizing these concepts to solve new conceptual problems. The growing interest in explainable machine intelligence requires experimental environments and diagnostic/benchmark datasets to analyze existing approaches and drive progress in pattern analysis and machine intelligence. In this paper, we provide an overview of current AI solutions for benchmarking concept learning, reasoning, and generalization; discuss the state-of-the-art of existing diagnostic/benchmark datasets (such as CLEVR, CLEVRER, CLOSURE, CURI, Bongard-LOGO, V-PROM, RAVEN, Kandinsky Patterns, CLEVR-Humans, CLEVRER-Humans, and their extension containing human language); and provide an outlook of some future research directions in this exciting research domain.
引用
收藏
页数:21
相关论文
共 50 条
  • [1] Editorial: Toward and Beyond Human-Level AI
    Dunin-Barkowski, Witali
    FRONTIERS IN NEUROROBOTICS, 2020, 14
  • [2] Companion Cognitive Systems - A step toward human-level AI
    Forbus, Kenneth D.
    Hinrichs, Thomas R.
    AI MAGAZINE, 2006, 27 (02) : 83 - 95
  • [3] Companion cognitive systems: A step toward human-level AI
    Department of Computer Science
    不详
    不详
    AI Mag, 2006, 2 (83-95):
  • [4] Editorial: Toward and beyond human-level AI, volume II
    Dunin-Barkowski, Witali
    Gorban, Alexander
    FRONTIERS IN NEUROROBOTICS, 2023, 16
  • [5] Learning Human-Level AI abilities to drive racing cars
    Gallego, Francisco
    Llorens, Faraon
    Pujol, Mar
    Rizo, Ramon
    ARTIFICIAL INTELLIGENCE RESEARCH AND DEVELOPMENT, 2005, 131 : 33 - 40
  • [6] Artificial Intelligence and Virtual Worlds - Toward Human-Level AI Agents
    Petrovic, Vladimir M.
    IEEE ACCESS, 2018, 6 : 39976 - 39988
  • [7] From here to human-level AI
    McCarthy, John
    ARTIFICIAL INTELLIGENCE, 2007, 171 (18) : 1174 - 1182
  • [8] From here to human-level AI
    McCarty, J
    PRINCIPLES OF KNOWLEDGE REPRESENTATION AND REASONING: PROCEEDINGS OF THE FIFTH INTERNATIONAL CONFERENCE (KR '96), 1996, : 640 - 646
  • [9] Human-level concept learning through probabilistic program induction
    Lake, Brenden M.
    Salakhutdinov, Ruslan
    Tenenbaum, Joshua B.
    SCIENCE, 2015, 350 (6266) : 1332 - 1338
  • [10] Object recognition for power equipment via human-level concept learning
    Xiong, Siheng
    Liu, Yadong
    Yan, Yingjie
    Pei, Ling
    Xu, Peng
    Fu, Xiaofei
    Jiang, Xiuchen
    IET GENERATION TRANSMISSION & DISTRIBUTION, 2021, 15 (10) : 1578 - 1587