感知机
Perceptrons
Marvin Minsky、Seymour Papert、Léon Bottou · 初版 1969 年
4人推荐
39位读者提及
48次提及
为什么值得读
- 篇幅短小精悍且数学阐述极为透彻清晰
- 严谨证明单层感知机无法解决所有类型的问题
- 对早期神经网络研究的发展产生了决定性影响
Hacker News 上怎么说
正在加载完整评论……
Perceptrons
Marvin Minsky、Seymour Papert、Léon Bottou · 初版 1969 年
正在加载完整评论……
马文·明斯基和西摩尔·帕珀特的《感知机》（Perceptrons）[1]。https://en.wikipedia.org/wiki/Perceptrons_(book) [1] http://libgen.rs/book/index.php?md5=8486B416F728B5D1035D2543...
Perceptrons by Marvin Minsky and Seymour Papert [1]. https://en.wikipedia.org/wiki/Perceptrons_(book) [1] http://libgen.rs/book/index.php?md5=8486B416F728B5D1035D2543...
明斯基的另一本神作是《感知机》（Perceptrons）。而且我没记错的话，篇幅还非常短。对机器学习（ML）感兴趣的人来说，这是一本尤为出色的书。明斯基在书中证明了单层神经网络无法计算所有问题。我记得他还搞了一个……
Another great book by Minsky is Perceptrons. It's really short to boot, IIRC. It is an especially good book for those interested in ML. In it Minsky shows that single layer neural nets can not compute all problems. I remember that he has a…
在很多方面，《感知机》（Perceptrons）依然是我最喜欢的书之一。显然，相比今天的深度神经网络，明斯基和帕珀特分析的单层网络非常原始，而且具体的数学内容……
Perceptrons remains one of my favorite books in many ways. Obviously the single-layer networks Minsky & Papert analyze are very primitive relative to today's deep neural networks, and the actual mathematical content…
这其实没正面回答问题，但我总觉得想学神经网络的人都应该读读马文·明斯基的《感知机》（Perceptrons）。这是一部学术著作。篇幅不长。写得好到离谱，通俗易懂。它塑造了数十年神经网络研究的历史（额……可惜的是，其实是直接扼杀了它 :-) ）。你应该……
This doesn't actually answer the question, but I always think that people who want to study neural nets should read Marvin Minsky's Perceptrons. It's an academic work. It's short. It's incredibly well written and easy to understand. It shaped the history of neural net research for decades (err... stopped it, unfortunately :-) ). You should…
……对普通大众来说是一本绝佳的视觉神经科学入门书，也是优秀的科普写作典范；弗拉基米尔·阿诺德的《惠更斯与巴罗、牛顿与胡克》（Huygens and Barrow, Newton and Hooke），思想密度极高；明斯基和帕珀特的《感知机》（Perceptrons），主要是作为清晰数学阐述的典范
…excellent introduction to visual neuroscience for the layperson and a really, really nice example of good scientific writing Huygens and Barrow, Newton and Hooke by VI Arnold, for the density of ideas Perceptrons by Minsky and Papert, mainly as an example of clear mathematical exposition
……跟几十年前那些对 AI 冷嘲热讽的论调毫无区别。这种话随时都能说。零新见解。零预测能力。关于 AI 进展，历史上是有过实质性反面论证的。去看看马文·明斯基和西摩尔·帕珀特的《感知机》（Perceptrons），看看扎实的反面论证长什么样。它提供了洞见。在当时也是站得住脚的。
…indistinguishable from cynical AI opinions going back decades. It could be made any time. Zero new insight. Zero predictive capacity. Substantive negative arguments about AI progress have been made. See "Perceptrons" by Marvin Minksy and Seymour Papert, for an example of what a solid negative argument looks like. It delivered insights. It made some sense at the time.