千脑智能
最新书摘：
-
骑羊的兔哥2024-03-18这种种模型有时候也会出错。比如，截肢的人经常会感觉失去的肢体似乎还在。大脑构建的模型还记录着被截去的肢体以及它所处的位置，所以虽然这个肢体不存在了，但是患者还是能感知到它的信号并且觉得它还在身体上，甚至“幻肢”还可以“移动”到不同的位置
-
骑羊的兔哥2024-03-18人类一样意识到自己的存在吗人类一样意识到自己的存在吗？我相信答案是肯定的。
-
骑羊的兔哥2024-03-18人工神经网络不能像大脑那样对世界建模，那么我认为任何深度学习网络都无法实现通用人工智能的目标。深度学习网络目前取得了不错的性能，但这并不是因为它们解决了知识表征问题。相反，它们完全避开了这一问题，转而依赖于统计信息和大量的数据。
-
骑羊的兔哥2024-03-18人类会不断修正自己对世界建立的模型。相较之下，深度学习网络在部署之前需要经过充分的训练，并且一经部署就无法在运行时学习新的东西了
-
骑羊的兔哥2024-03-18芒卡斯尔认为，每根皮质柱中都存在一种通用的算法，但他不知道这种算法是什么。弗朗西斯·克里克认为，我们需要一个新的框架来理解大脑，然而他也不知道这个框架应该是什么。2016年的那一天，我手里握着咖啡杯，突然意识到芒卡斯尔的算法和克里克的框架都基于参考系。虽然我还没有弄清楚神经元是如何做到这一点的，但我知道这一定是真的。参考系正是其中缺失的成分，是揭开新皮质之谜和理解智能的关键。
-
骑羊的兔哥2024-03-18迷你皮质柱中，会有多个神经元对同一输入模式产生应激反应。它们就像在起跑线上的选手，都在等待相同的信号。如果它们都获得了输入，就都会发射脉冲信号。但如果有一个或几个神经元已经处于预测状态，根据我们的理论，只有这些神经元才会发射脉冲信号，其他神经元则会被抑制。因此，当一个未预测到的输入到达时，多个神经元会同时被激发，但如果输入是预测到的，那么将只有处于预测状态的神经元会发射脉冲信号。这是从新皮质中观察到的一个常见现象：未预测到的输入通常会比预测到的输入引起更大的刺激
-
目送飞鸿2021-08-07“Uploading your brain” is a misleading phrase. What you have really done is split yourself into two people....Uploading your brain at first sounds like a great idea. Who wouldn’t want to live forever? But making a copy of ourselves by uploading our brain into a computer will not achieve immortality any more than having children will. Copying yourself is a fork in the road, not an extension of it. Two sentient beings continue after the fork, not one. Once you realize this, then the appeal of uploading your brain begins to fade.
-
目送飞鸿2021-08-07But our emergent intelligence has had a consequence that is not necessarily in the best interest of genes....Because of our knowledge and intelligence, we can consider acting in ways that are not in the best interest of genes, such as using birth control or modifying genes that we don’t like....The mental “I” that exists in our brains wants to break free from its genetic servitude, to no longer be held captive by the Darwinian processes that got us all here.
-
目送飞鸿2021-08-07If we could sense all frequencies of electromagnetic radiation, then we would see radio broadcasts and radar and would have X-ray vision. With different sensors, the same universe would lead to different perceptual experiences.The two important points are that the brain only knows about a subset of the real world, and that what we perceive is our model of the world, not the world itself.
-
目送飞鸿2021-08-05The secret ingredient, if you will, is that intelligence is created through thousands of small models of the world, where each model uses reference frames to store knowledge and create behaviors.
-
目送飞鸿2021-08-05I believe the future of AI will be based on brain principles. Truly intelligent machines, AGI, will learn models of the world using maplike reference frames just like the neocortex.
-
目送飞鸿2021-08-04Knowledge in the brain is distributed. Nothing we know is stored in one place, such as one cell or one column....This is why we call it the Thousand Brains Theory: knowledge of any particular item is distributed among thousands of complementary models.