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
  • [21] Incipient Fault Identification in Power Distribution Systems via Human-Level Concept Learning
    Xiong, Siheng
    Liu, Yadong
    Fang, Jian
    Dai, Jindun
    Luo, Lingen
    Jiang, Xiuchen
    IEEE TRANSACTIONS ON SMART GRID, 2020, 11 (06) : 5239 - 5248
  • [22] Why AI will never be able to acquire human-level intelligence
    Munoz, Jose M.
    Bernacer, Javier
    Noe, Alva
    Thompson, Evan
    NATURE, 2025, 637 (8047) : 794 - 794
  • [23] Toward human-level tonal and modal melody harmonizations
    Mycka, Jan
    Zychowski, Adam
    Mandziuk, Jacek
    JOURNAL OF COMPUTATIONAL SCIENCE, 2023, 67
  • [24] The meta-ontology of AI systems with human-level intelligence
    Krzanowski, Roman
    Polak, Pawel
    ZAGADNIENIA FILOZOFICZNE W NAUCE-PHILOSOPHICAL PROBLEMS IN SCIENCE, 2022, (73): : 197 - 230
  • [25] Toward Human-Level Qualitative Reasoning with a Natural Language of Thought
    Jackson, Philip C., Jr.
    BIOLOGICALLY INSPIRED COGNITIVE ARCHITECTURES 2021, 2022, 1032 : 195 - 207
  • [26] Human-level control through deep reinforcement learning
    Volodymyr Mnih
    Koray Kavukcuoglu
    David Silver
    Andrei A. Rusu
    Joel Veness
    Marc G. Bellemare
    Alex Graves
    Martin Riedmiller
    Andreas K. Fidjeland
    Georg Ostrovski
    Stig Petersen
    Charles Beattie
    Amir Sadik
    Ioannis Antonoglou
    Helen King
    Dharshan Kumaran
    Daan Wierstra
    Shane Legg
    Demis Hassabis
    Nature, 2015, 518 : 529 - 533
  • [27] Human-level AI's killer application: Interactive computer games
    Laird, JE
    van Lent, M
    SEVENTEENTH NATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE (AAAI-2001) / TWELFTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE (IAAI-2000), 2000, : 1171 - 1178
  • [28] Video Turing Test: A first step towards human-level AI
    Lee, Minsu
    Heo, Yu-Jung
    Choi, Seongho
    Choi, Woo Suk
    Zhang, Byoung-Tak
    AI MAGAZINE, 2023, 44 (04) : 537 - 554
  • [29] Human-level control through deep reinforcement learning
    Mnih, Volodymyr
    Kavukcuoglu, Koray
    Silver, David
    Rusu, Andrei A.
    Veness, Joel
    Bellemare, Marc G.
    Graves, Alex
    Riedmiller, Martin
    Fidjeland, Andreas K.
    Ostrovski, Georg
    Petersen, Stig
    Beattie, Charles
    Sadik, Amir
    Antonoglou, Ioannis
    King, Helen
    Kumaran, Dharshan
    Wierstra, Daan
    Legg, Shane
    Hassabis, Demis
    NATURE, 2015, 518 (7540) : 529 - 533
  • [30] Human-level AI's killer application interactive computer games
    Laird, JE
    van Lent, M
    AI MAGAZINE, 2001, 22 (02) : 15 - 25