...
首页> 外文期刊>Neuron >Engineering a Less Artificial Intelligence
【24h】

Engineering a Less Artificial Intelligence

机译:工程不太人工智能

获取原文
获取原文并翻译 | 示例
           

摘要

Despite enormous progress in machine learning, artificial neural networks still lag behind brains in their ability to generalize to new situations. Given identical training data, differences in generalization are caused by many defining features of a learning algorithm, such as network architecture and learning rule. Their joint effect, called "inductive bias,'' determines how well any learning algorithm-or brain-generalizes: robust generalization needs good inductive biases. Artificial networks use rather nonspecific biases and often latch onto patterns that are only informative about the statistics of the training data but may not generalize to different scenarios. Brains, on the other hand, generalize across comparatively drastic changes in the sensory input all the time. We highlight some shortcomings of state-of-the-art learning algorithms compared to biological brains and discuss several ideas about how neuroscience can guide the quest for better inductive biases by providing useful constraints on representations and network architecture.
机译:尽管在机器学习方面取得了巨大进步,但人工神经网络仍然落后于大脑,以概括为新情况。给定相同的训练数据,泛化的差异是由学习算法的许多定义特征引起的,例如网络架构和学习规则。他们的联合效果称为“归纳偏见”,决定了任何学习算法 - 或脑概括的程度:鲁棒概括需要良好的感应偏见。人造网络使用相当不特异性的偏见,并且经常锁存在唯一关于统计数据的模式上的模式。培训数据但可能无法概括不同的情景。另一方面,大脑横穿了一直跨越感官输入的相对激烈的变化。与生物大脑相比,我们突出了最先进的学习算法的一些缺点关于神经科学如何指导追求更好的感应偏差的几个想法,通过为表示和网络架构提供有用的限制。

著录项

  • 来源
    《Neuron》 |2019年第6期|共13页
  • 作者单位

    Univ Tubingen IBMI Tubingen Germany;

    Baylor Coll Med Dept Neurosci Houston TX 77030 USA;

    Baylor Coll Med Dept Neurosci Houston TX 77030 USA;

    Univ Tubingen Bernstein Ctr Computat Neurosci Tubingen Germany;

    Baylor Coll Med Dept Neurosci Houston TX 77030 USA;

  • 收录信息
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类 神经病学;
  • 关键词

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号