.png){kind=icon}
返回
Engineering a Less Artificial Intelligence
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neuron.2019.08.034.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
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.
Keyword:
DEEP LEARNING-MODELS
WHITE-NOISE ANALYSIS
HIERARCHICAL-MODELS
RECEPTIVE-FIELDS
VISUAL NEURONS
RESPONSES
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
15
论文数:
1.4W
被引数:
9.9W
机构
引用论文
SPO13 negatively regulates the progression of mitotic and meiotic nuclear division in Saccharomyces cerevisiae..png)
Genetics
OAAI
GeneticsIF0
OAAI分享收藏Fatty Acid Ethyl Esters: A Novel Biologic Marker for Heavy In Utero Ethanol Exposure: A Case Report
PREAI
分享收藏Real-time and offline techniques for identifying obstructive sleep apnea patients用于识别阻塞性睡眠呼吸暂停患者的实时和离线技术
PREAI
分享收藏
Genomic-sequence comparison of two unrelated isolates of the human gastric pathogen Helicobacter pyloriNature
NatureIF0
PREAI
分享收藏
查看更多内容