《稀疏分布式记忆》封面

稀疏分布式记忆

Sparse distributed memory

Pentti Kanerva · 初版 1988 年

3人推荐
8位读者提及
10次提及

Hacker News 上怎么说

  • Kanerva 也是 80 年代末那本(个人认为被严重低估的)书《Sparse Distributed Memory》的作者,该书为很多这类研究奠定了基础,比 Numenta 早了整整几十年……

    Kanerva is also the author of the (vastly underrated IMHO) book Sparse Distributed Memory from the late 80s that set the stage for a lot of this and predates Numenta by a couple of decades...

  • Kanerva 的《Sparse Distributed Memory》相当了不起:https://en.wikipedia.org/wiki/Sparse_distributed_memory 不过它是一本书:https://www.amazon.com/Sparse-Distributed-Memory-MIT-Press/d...

    Kanerva's Sparse Distributed Memory is quite remarkable: https://en.wikipedia.org/wiki/Sparse_distributed_memory it's a book though: https://www.amazon.com/Sparse-Distributed-Memory-MIT-Press/d...

  • 《Sparse Distributed Memory》是 Pentti Kanerva 写的一本非常棒的书,他在书中提出假说,认为高维二进制向量(超向量,hypervectors)是理解人类记忆和认知的关键。Kanerva 在很大程度上关注的是……

    "Sparse Distributed Memory" is a lovely book by Pentti Kanerva in which he hypothesizes that high dimensional binary vectors (hypervectors) is key to understanding human memory and cognition. To a large part Kanerva is concerned…

  • 我 90 年代中期的 AI 藏书中没保留几本,但出于某种原因,每当我清理淘汰旧书时,Kanerva 的《Sparse Distributed Memory》总是能幸免留下来。这个想法里有些东西似乎非常吸引人,我一直在等一个由头,看看能不能把其中的一些想法融合……

    I don't keep around many items from my collection of my mid-90s AI books, but for some reason Kanerva's Sparse Distributed Memory book always managed to make the cut whenever I go in to cull things. There is something about the idea that seems appealing and I keep waiting for some excuse to see if any of the ideas can be melded…

  • 向量符号架构(Vector Symbolic Architecture,VSA)是欧洲的叫法。基础是 Pentti Kanerva 1988 年的书《Sparse Distributed Memory》。现在被称为“HDC”或“HD”。可以搜搜 Pentti Kanerva,他现在是加利福尼亚大学伯克利分校 Redwood 理论神经科学中心的主任科学家,或者 Mohsen Imani,现任职于加州大学欧文分校,之前在加州大学圣迭戈分校。入门……

    Vector Symbolic Architecture (VSA) is the European name. Base is Pentti Kanerva's 1988 book, "Sparse Distributed Memory". Now referred to as "HDC" or "HD". Search Pentti Kanerva now Staff Scientist at UC Berkeley Redwood Center for Theoretical Neuroscience or Mohsen Imani, now UC Irvine former at UC San Diego. Introductory…

  • …某些结构(例如作为某种“信息中枢”的丘脑),向后(朝向输入端)的连接比向前的连接几乎多出近十倍。* 大脑使用的是稀疏分布式内存(Sparse Distributed Memory, SDM)。参见 Pentti Kanerva(NASA 研究员)的 SDM。* 神经元模型拥有的变量/参数(可用于传输或处理信息)远多于人工神经网络通常的节点/连接……

    …some structures (e.g. the thalamus, that is a kind of "hub of information") connections going backward (toward the input) exceed the connections going forward by almost a factor of ten. * Brain uses Sparse Distributed Memory (SDM). See SDM by Pentti Kanerva (NASA researcher). * Neuron models have many more variable/parameters (that can be used to transfer or process information) than usual nodes/links from artificial neural…

正在加载完整评论……

键盘快捷键

/
聚焦搜索框
j / k
下一本 / 上一本
Enter
打开选中的书
Esc
关闭 / 返回
g h
回到首页
g b
值得读精选
g t
历史总榜
g r
上升最快
g l
我的书架
?
显示本帮助