Building machines that learn and think like people
Building machines that learn and think like people
复制标题
DOI：
10.1017/s0140525x16001837
复制
发表时间：
2017-01-01
影响因子：
29.3
通讯作者：
Gershman, Samuel J.
中科院分区：
文献类型：
--
作者：
Lake, Brenden M.;Ullman, Tomer D.;Gershman, Samuel J.
人工智能的最新进展重新激发了人们对构建像人一样学习和思考的系统的兴趣。许多进步来自于使用在对象识别、视频游戏和棋盘游戏等任务中端到端训练的深度神经网络，在某些方面实现了与人类相当甚至超过人类的性能。尽管它们具有生物学灵感和性能成就，但这些系统在关键方面与人类智能不同。我们回顾了认知科学的进展，认为真正像人类一样学习和思考的机器必须超越当前的工程趋势，无论是学习什么还是如何学习。具体来说，我们认为这些机器应该（1）建立支持解释和理解的世界因果模型，而不仅仅是解决模式识别问题;（2）以物理学和心理学的直觉理论为基础的学习，以支持和丰富所学到的知识;（3）利用组合性和学会学习，以快速获取和概括知识，以适应新的任务和情况。我们提出了实现这些目标的具体挑战和有希望的路线，这些目标可以将最近神经网络进步的优势与更结构化的认知模型结合起来。
Recent progress in artificial intelligence has renewed interest in building systems that learn and think like people. Many advances have come from using deep neural networks trained end-to-end in tasks such as object recognition, video games, and board games, achieving performance that equals or even beats that of humans in some respects. Despite their biological inspiration and performance achievements, these systems differ from human intelligence in crucial ways. We review progress in cognitive science suggesting that truly human-like learning and thinking machines will have to reach beyond current engineering trends in both what they learn and how they learn it. Specifically, we argue that these machines should (1) build causal models of the world that support explanation and understanding, rather than merely solving pattern recognition problems; (2) ground learning in intuitive theories of physics and psychology to support and enrich the knowledge that is learned; and (3) harness compositionality and learning-to-learn to rapidly acquire and generalize knowledge to new tasks and situations. We suggest concrete challenges and promising routes toward these goals that can combine the strengths of recent neural network advances with more structured cognitive models.