Nat Mater:芯片大脑推出有望

2018-02-09 陈宗伦 人民网-生命时报

国际权威学术杂志《自然·材料》近日刊登美国麻省理工学院一项新研究称,科学家已研制出人工突触,“芯片大脑”呼之欲出。

国际权威学术杂志《自然·材料》近日刊登美国麻省理工学院一项新研究称,科学家已研制出人工突触,“芯片大脑”呼之欲出。

人类的大脑虽然只有足球大小,却拥有大约1000亿个神经元。在任意时刻,一个神经元都可通过突触(神经元之间的空隙)将指令传递给成千上万个其他的神经元。大脑中的传递信息的神经突触超过100万亿个,这使得大脑可以闪电般的速度识别模样、记住事实、完成各种学习任务。基于这一原理,科学家试图设计一种类似人类大脑的电脑芯片,令其完成大脑中纷繁复杂的计算工作。制作这种芯片的最大难点是如何在硬件上实现神经突触复制。

麻省理工学院电子与微系统技术实验室研究员吉瓦恩·吉姆教授及其研究团队最新设计出一种“神经形态芯片”,它是由硅鍺材料制作的人工突触组成的。神经形态芯片的组成要件将包括输入、隐藏和输出神经元,每个神经元通过微小的人造突触连接到其他神经元。

吉姆教授表示,新研究在制造便携式低功耗神经形态芯片方面迈出了重要的一步。有了这种全新的芯片,人工智能技术将如虎添翼。指甲盖大小的芯片将取代大型超级计算机,具有非常广阔的商业前景。虚拟现实、可穿戴设备、神经网络连接、物联网等行业都将突破硬件障碍,实现飞跃发展。

原始出处:

版权声明:
本网站所有内容来源注明为“梅斯医学”或“MedSci原创”的文字、图片和音视频资料,版权均属于梅斯医学所有。非经授权,任何媒体、网站或个人不得转载,授权转载时须注明来源为“梅斯医学”。其它来源的文章系转载文章,或“梅斯号”自媒体发布的文章,仅系出于传递更多信息之目的,本站仅负责审核内容合规,其内容不代表本站立场,本站不负责内容的准确性和版权。如果存在侵权、或不希望被转载的媒体或个人可与我们联系,我们将立即进行删除处理。
在此留言
评论区 (3)
#插入话题
  1. [GetPortalCommentsPageByObjectIdResponse(id=1882843, encodeId=6817188284340, content=<a href='/topic/show?id=3b2112532d8' target=_blank style='color:#2F92EE;'>#Nat#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=0, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=12532, encryptionId=3b2112532d8, topicName=Nat)], attachment=null, authenticateStatus=null, createdAvatar=, createdBy=2e6f107, createdName=liye789132251, createdTime=Thu Oct 11 01:51:00 CST 2018, time=2018-10-11, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1458954, encodeId=356c145895462, content=<a href='/topic/show?id=53cc8691532' target=_blank style='color:#2F92EE;'>#芯片#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=29, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=86915, encryptionId=53cc8691532, topicName=芯片)], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=55683, createdName=仁医06, createdTime=Sun Feb 11 01:51:00 CST 2018, time=2018-02-11, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=286507, encodeId=081c28650ea5, content=学习了.涨知识, beContent=null, objectType=article, channel=null, level=null, likeNumber=30, replyNumber=0, topicName=null, topicId=null, topicList=[], attachment=null, authenticateStatus=null, createdAvatar=https://img.medsci.cn/20220115/46bcf39c32de4aa6b45c5f9d66c8ee77/6cb4a20c55bb4b7691122f47747bfca2.jpg, createdBy=9dad1662329, createdName=1ddf0692m34(暂无匿称), createdTime=Fri Feb 09 11:32:05 CST 2018, time=2018-02-09, status=1, ipAttribution=)]
    2018-10-11 liye789132251
  2. [GetPortalCommentsPageByObjectIdResponse(id=1882843, encodeId=6817188284340, content=<a href='/topic/show?id=3b2112532d8' target=_blank style='color:#2F92EE;'>#Nat#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=0, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=12532, encryptionId=3b2112532d8, topicName=Nat)], attachment=null, authenticateStatus=null, createdAvatar=, createdBy=2e6f107, createdName=liye789132251, createdTime=Thu Oct 11 01:51:00 CST 2018, time=2018-10-11, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1458954, encodeId=356c145895462, content=<a href='/topic/show?id=53cc8691532' target=_blank style='color:#2F92EE;'>#芯片#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=29, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=86915, encryptionId=53cc8691532, topicName=芯片)], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=55683, createdName=仁医06, createdTime=Sun Feb 11 01:51:00 CST 2018, time=2018-02-11, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=286507, encodeId=081c28650ea5, content=学习了.涨知识, beContent=null, objectType=article, channel=null, level=null, likeNumber=30, replyNumber=0, topicName=null, topicId=null, topicList=[], attachment=null, authenticateStatus=null, createdAvatar=https://img.medsci.cn/20220115/46bcf39c32de4aa6b45c5f9d66c8ee77/6cb4a20c55bb4b7691122f47747bfca2.jpg, createdBy=9dad1662329, createdName=1ddf0692m34(暂无匿称), createdTime=Fri Feb 09 11:32:05 CST 2018, time=2018-02-09, status=1, ipAttribution=)]
    2018-02-11 仁医06
  3. [GetPortalCommentsPageByObjectIdResponse(id=1882843, encodeId=6817188284340, content=<a href='/topic/show?id=3b2112532d8' target=_blank style='color:#2F92EE;'>#Nat#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=0, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=12532, encryptionId=3b2112532d8, topicName=Nat)], attachment=null, authenticateStatus=null, createdAvatar=, createdBy=2e6f107, createdName=liye789132251, createdTime=Thu Oct 11 01:51:00 CST 2018, time=2018-10-11, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=1458954, encodeId=356c145895462, content=<a href='/topic/show?id=53cc8691532' target=_blank style='color:#2F92EE;'>#芯片#</a>, beContent=null, objectType=article, channel=null, level=null, likeNumber=29, replyNumber=0, topicName=null, topicId=null, topicList=[TopicDto(id=86915, encryptionId=53cc8691532, topicName=芯片)], attachment=null, authenticateStatus=null, createdAvatar=null, createdBy=55683, createdName=仁医06, createdTime=Sun Feb 11 01:51:00 CST 2018, time=2018-02-11, status=1, ipAttribution=), GetPortalCommentsPageByObjectIdResponse(id=286507, encodeId=081c28650ea5, content=学习了.涨知识, beContent=null, objectType=article, channel=null, level=null, likeNumber=30, replyNumber=0, topicName=null, topicId=null, topicList=[], attachment=null, authenticateStatus=null, createdAvatar=https://img.medsci.cn/20220115/46bcf39c32de4aa6b45c5f9d66c8ee77/6cb4a20c55bb4b7691122f47747bfca2.jpg, createdBy=9dad1662329, createdName=1ddf0692m34(暂无匿称), createdTime=Fri Feb 09 11:32:05 CST 2018, time=2018-02-09, status=1, ipAttribution=)]
    2018-02-09 1ddf0692m34(暂无匿称)

    学习了.涨知识

    0