还有 Chris Eliasmith 写的《How to Build a Brain》。关于神经元如何表征函数并构建为一个更大的整体，书里提出了一些很有意思的理论。我不是神经科学家，但直觉告诉我，他可能正在逼近一个扎实的中层……
Also “How to Build a Brain” by Chris Eliasmith. Interesting theories on how neurons represent functions and then build into a greater whole. I’m not a neuroscientist but my intuition says he might be getting closer to a solid mid-level…
……42. How The Mind Works - Steven Pinker 43. Images and Words - Steven Pinker 44. Words and Rules - Steven Pinker 45. The Blank Slate - Steven Pinker 46. Consciousness Explained - Daniel Dennett 47. How to Build a Brain: A Neural Architecture for Biological Cognition - Chris Eliasmith 48. Introduction to Artificial Intelligence - Eugene Charniak & Drew McDermott 49. Metamagical Themas - Douglas Hofstadter 50. I Am…
…42. How The Mind Works - Steven Pinker 43. Images and Words - Steven Pinker 44. Words and Rules - Steven Pinker 45. The Blank Slate - Steven Pinker 46. Consciousness Explained - Daniel Dennett 47. How to Build a Brain: A Neural Architecture for Biological Cognition - Chris Eliasmith 48. Introduction to Artificial Intelligence - Eugene Charniak & Drew McDermott 49. Metamagical Themas - Douglas Hofstadter 50. I Am…
> (...) 我开始读 Chris Eliasmith 的《How to Build a Brain》。读完后，我真切地觉得符合生物学特性的建模对认知科学的发展极其重要。它对 backpropagation 给出了符合生物学机制的合理解释吗？
> (...) I started reading “How to Build a Brain” by Chris Eliasmith. By the end of it, I truly felt biologically plausible modelling was hugely important for the advance of Cognitive Science. Does it give a biologically plausible explanation for backpropagation?
呵。看来这种书名套路挺常见的。还有 Chris Eliasmith 写的《How to Build A Brain》[1] 和 Ray Kurzweil 写的《How To Create A Mind》[2] 呢。[1]: https://www.amazon.com/How-Build-Brain-Architecture-Architec... [2]: https://www.amazon.com/How-Create-Mind-Thought-Revealed/dp/1...
Heh. Seems to be a common pattern in book titles. There are also How to Build A Brain[1] by Chris Eliasmith and How To Create A Mind[2] by Ray Kurzweil as well. [1]: https://www.amazon.com/How-Build-Brain-Architecture-Architec... [2]: https://www.amazon.com/How-Create-Mind-Thought-Revealed/dp/1...
这跟过去 50 年里我们在上百个盲目自信的“研究者”身上见过的夸大其词的废话如出一辙。Eliasmith 写了本叫《How to Build a Brain》的书，Hawkins 围绕一套理论创办了整家 Numenta 公司，结果近 20 年来没搞出任何稍微有用或有趣的东西，现在已经转型去为当前流行风向的 ML 方法做工具了。……
It's the same hyperbolic nonsense we've seen from hundreds of other confident "researchers" over the past 50 years. Eliasmith has a book called "How to Build a Brain", Hawkins built an entire company, Numenta, around a theory that hasn't created anything remotely useful or interesting in almost 2 decades and has pivoted to creating tools for current ML zeitgeist methods.…
……https://en.wikipedia.org/wiki/Cognitive_architecture#Notable... Eliasmith 搞出了“Semantic Pointer Architecture”，算是 CS 和 CogSci 的某种跨界融合 https://en.wikipedia.org/wiki/Spaun_(Semantic_Pointer_Archit...，另外也可以看看他那本《How to build a Brain》。真希望现在的 AI 研究能从深度学习的 local minima 里跳出来，过去几十年认知科学领域明明取得了那么多进展。
…https://en.wikipedia.org/wiki/Cognitive_architecture#Notable... Eliasmith created "Semantic Pointer Architecture" which is sort of a crossover between CS and CogSci https://en.wikipedia.org/wiki/Spaun_(Semantic_Pointer_Archit..., also see his book on "How to build a Brain" I wish the current AI research would get unstuck from local minima of deep learning, there's been so much progress in cognitive sciences in the last few decades.
还有 Chris Eliasmith 写的《How to Build a Brain》。关于神经元如何表征函数并构建为一个更大的整体，书里提出了一些很有意思的理论。我不是神经科学家，但直觉告诉我，他可能正在逼近一个扎实的中层……
Also “How to Build a Brain” by Chris Eliasmith. Interesting theories on how neurons represent functions and then build into a greater whole. I’m not a neuroscientist but my intuition says he might be getting closer to a solid mid-level…
……42. How The Mind Works - Steven Pinker 43. Images and Words - Steven Pinker 44. Words and Rules - Steven Pinker 45. The Blank Slate - Steven Pinker 46. Consciousness Explained - Daniel Dennett 47. How to Build a Brain: A Neural Architecture for Biological Cognition - Chris Eliasmith 48. Introduction to Artificial Intelligence - Eugene Charniak & Drew McDermott 49. Metamagical Themas - Douglas Hofstadter 50. I Am…
…42. How The Mind Works - Steven Pinker 43. Images and Words - Steven Pinker 44. Words and Rules - Steven Pinker 45. The Blank Slate - Steven Pinker 46. Consciousness Explained - Daniel Dennett 47. How to Build a Brain: A Neural Architecture for Biological Cognition - Chris Eliasmith 48. Introduction to Artificial Intelligence - Eugene Charniak & Drew McDermott 49. Metamagical Themas - Douglas Hofstadter 50. I Am…
> (...) 我开始读 Chris Eliasmith 的《How to Build a Brain》。读完后，我真切地觉得符合生物学特性的建模对认知科学的发展极其重要。它对 backpropagation 给出了符合生物学机制的合理解释吗？
> (...) I started reading “How to Build a Brain” by Chris Eliasmith. By the end of it, I truly felt biologically plausible modelling was hugely important for the advance of Cognitive Science. Does it give a biologically plausible explanation for backpropagation?
呵。看来这种书名套路挺常见的。还有 Chris Eliasmith 写的《How to Build A Brain》[1] 和 Ray Kurzweil 写的《How To Create A Mind》[2] 呢。[1]: https://www.amazon.com/How-Build-Brain-Architecture-Architec... [2]: https://www.amazon.com/How-Create-Mind-Thought-Revealed/dp/1...
Heh. Seems to be a common pattern in book titles. There are also How to Build A Brain[1] by Chris Eliasmith and How To Create A Mind[2] by Ray Kurzweil as well. [1]: https://www.amazon.com/How-Build-Brain-Architecture-Architec... [2]: https://www.amazon.com/How-Create-Mind-Thought-Revealed/dp/1...
这跟过去 50 年里我们在上百个盲目自信的“研究者”身上见过的夸大其词的废话如出一辙。Eliasmith 写了本叫《How to Build a Brain》的书，Hawkins 围绕一套理论创办了整家 Numenta 公司，结果近 20 年来没搞出任何稍微有用或有趣的东西，现在已经转型去为当前流行风向的 ML 方法做工具了。……
It's the same hyperbolic nonsense we've seen from hundreds of other confident "researchers" over the past 50 years. Eliasmith has a book called "How to Build a Brain", Hawkins built an entire company, Numenta, around a theory that hasn't created anything remotely useful or interesting in almost 2 decades and has pivoted to creating tools for current ML zeitgeist methods.…
……https://en.wikipedia.org/wiki/Cognitive_architecture#Notable... Eliasmith 搞出了“Semantic Pointer Architecture”，算是 CS 和 CogSci 的某种跨界融合 https://en.wikipedia.org/wiki/Spaun_(Semantic_Pointer_Archit...，另外也可以看看他那本《How to build a Brain》。真希望现在的 AI 研究能从深度学习的 local minima 里跳出来，过去几十年认知科学领域明明取得了那么多进展。
…https://en.wikipedia.org/wiki/Cognitive_architecture#Notable... Eliasmith created "Semantic Pointer Architecture" which is sort of a crossover between CS and CogSci https://en.wikipedia.org/wiki/Spaun_(Semantic_Pointer_Archit..., also see his book on "How to build a Brain" I wish the current AI research would get unstuck from local minima of deep learning, there's been so much progress in cognitive sciences in the last few decades.