The Nobel Prize in Physics 2024 ｜ 2024 年诺贝尔物理学奖
输入“/”快速插入内容
The Nobel Prize in Physics 2024 ｜ 2024 年诺贝尔物理学奖
The Nobel Prize in Physics 2024 ｜ 2024 年诺贝尔物理学奖
⏰ 时间：2024-10-08
This year’s laureates used tools from physics to construct methods that helped lay the foundation for today’s powerful machine learning. John Hopfield created a structure that can store and reconstruct information. Geoffrey Hinton invented a method that can independently discover properties in data and which has become important for the large artificial neural networks now in use.
今年的获奖者使用物理学工具构建了有助于奠定当今强大机器学习基础的方法。 John Hopfield 创造了一种可以存储和重构信息的结构。 Geoffrey Hinton 发明了一种可以独立发现数据中属性的方法，这对于当前使用的大型人工神经网络非常重要。
They used physics to find patterns in information
他们运用物理学来发现信息中的规律
Many people have experienced how computers can translate between languages, interpret images and even conduct reasonable conversations. What is perhaps less well known is that this type of technology has long been important for research, including the sorting and analysis of vast amounts of data. The development of machine learning has exploded over the past fifteen to twenty years and utilises a structure called an artificial neural network. Nowadays, when we talk about artificial intelligence , this is often the type of technology we mean.
许多人经历过电脑如何在语言间翻译，解释图像，甚至进行合理的对话。或许不太为人所知的是，这种技术长期以来一直在研究中很重要，包括对大量数据的分类和分析。机器学习的发展在过去 15 到 20 年中爆发式增长，并利用了一种称为人工神经网络的结构。如今，当我们谈论 人工智能 时，这通常就是我们所指的技术类型。
Although computers cannot think, machines can now mimic functions such as memory and learning. This year’s laureates in physics have helped make this possible. Using fundamental concepts and methods from physics, they have developed technologies that use structures in networks to process information.
尽管计算机无法思考，但机器现在可以模仿诸如记忆和学习等功能。今年的物理学奖得主帮助实现了这一点。他们利用物理学的基本概念和方法，开发了使用网络结构来处理信息的技术。
Machine learning differs from traditional software, which works like a type of recipe. The software receives data, which is processed according to a clear description and produces the results, much like when someone collects ingredients and processes them by following a recipe, producing a cake. Instead of this, in machine learning the computer learns by example, enabling it to tackle problems that are too vague and complicated to be managed by step by step instructions. One example is interpreting a picture to identify the objects in it.
机器学习有别于传统软件，后者像食谱一样运作。软件接收数据，根据明确的说明进行处理并产生结果，就像当有人收集配料并按照食谱加工，制作出一个蛋糕一样。相反，在机器学习中，计算机通过学习示例来解决那些过于模糊和复杂而无法用逐步指令管理的问题。一个例子是解释图像以识别其中的物体。
Mimics the brain 模仿大脑
An artificial neural network processes information using the entire network structure. The inspiration initially came from the desire to understand how the brain works. In the 1940s, researchers had started to reason around the mathematics that underlies the brain’s network of neurons and synapses. Another piece of the puzzle came from psychology, thanks to neuroscientist Donald Hebb’s hypothesis about how learning occurs because connections between neurons are reinforced when they work together.
一个人工神经网络使用整个网络结构来处理信息。这种启发最初来自于想要理解大脑如何工作的愿望。在 1940 年代，研究人员已经开始围绕支撑大脑神经元和突触网络的数学进行推理。心理学也提供了一些线索，归功于神经科学家唐纳德·赫布提出的关于学习是如何发生的假说，即当神经元共同工作时，它们之间的连接会得到加强。
Later, these ideas were followed by attempts to recreate how the brain’s network functions by building artificial neural networks as computer simulations. In these, the brain’s neurons are mimicked by nodes that are given different values, and the synapses are represented by connections between the nodes that can be made stronger or weaker. Donald Hebb’s hypothesis is still used as one of the basic rules for updating artificial networks through a process called training .
后来，这些想法被用来尝试重建大脑网络的功能，方法是建立人工神经网络作为计算机模拟。在这些模拟中，大脑的神经元被节点所模拟，这些节点被赋予不同的值，而突触则由节点之间的连接来表示，这些连接可以变得更强或更弱。唐纳德·赫布的假说仍被用作通过称为 训练 的过程更新人工网络的基本规则之一。
At the end of the 1960s, some discouraging theoretical results caused many researchers to suspect that these neural networks would never be of any real use. However, interest in artificial neural networks was reawakened in the 1980s, when several important ideas made an impact, including work by this year’s laureates.
在 1960 年代末，一些令人沮丧的理论结果使许多研究人员怀疑这些神经网络永远不会有任何真实用途。然而，当包括今年获奖者的工作在内的几个重要思想产生影响时，人工神经网络的兴趣在 1980 年代得到了重新唤起。
Associative memory 关联记忆
Imagine that you are trying to remember a fairly unusual word that you rarely use, such as one for that sloping floor often found in cinemas and lecture halls. You search your memory. It’s something like ramp … perhaps rad…ial ? No, not that. Rake , that’s it!
设想您正试图记住一个相当不寻常的词语，您很少使用它，例如那种常见于电影院和讲堂里的倾斜地板。您回忆着它。它看起来像是 坡道 …也许是 径向 ？不，不是那个。 坡 ，就是这个！
This process of searching through similar words to find the right one is reminiscent of the associative memory that the physicist John Hopfield discovered in 1982. The Hopfield network can store patterns and has a method for recreating them. When the network is given an incomplete or slightly distorted pattern, the method can find the stored pattern that is most similar.
这个通过搜索相似词来找到合适词语的过程，让人联想到物理学家约翰·霍普菲尔德在 1982 年发现的联想记忆。 霍普菲尔德网络 可以存储模式，并有一种方法来重建它们。当网络被给予不完整或略有失真的模式时，该方法可以找到最相似的存储模式。
Hopfield had previously used his background in physics to explore theoretical problems in molecular biology. When he was invited to a meeting about neuroscience he encountered research into the structure of the brain. He was fascinated by what he learned and started to think about the dynamics of simple neural networks. When neurons act together, they can give rise to new and powerful characteristics that are not apparent to someone who only looks at the network’s separate components.
霍普菲尔德先前利用他在物理学方面的背景探究分子生物学中的理论问题。当他受邀参加一次神经科学会议时，他接触到了大脑结构的研究。他被所学到的内容所吸引，开始思考简单神经网络的动力学。当神经元协同作用时，它们能产生全新而强大的特性，这些特性对于仅关注网络独立组成部分的人而言是不明显的。
In 1980, Hopfield left his position at Princeton University, where his research interests had taken him outside the areas in which his colleagues in physics worked, and moved across the continent. He had accepted the offer of a professorship in chemistry and biology at Caltech (California Institute of Technology) in Pasadena, southern California. There, he had access to computer resources that he could use for free experimentation and to develop his ideas about neural networks.
1980 年，霍普菲尔德离开了普林斯顿大学，他的研究兴趣已经超出了同事们在物理领域的工作范围，并搬到了另一个大洲。他接受了加州理工学院（位于加利福尼亚州南部帕萨迪纳）化学和生物学教授的 offer。在那里，他可以自由使用计算机资源来实验和发展他关于神经网络的想法。
However, he did not abandon his foundation in physics, where he found inspiration for his understanding of how systems with many small components that work together can give rise to new and interesting phenomena. He particularly benefitted from having learned about magnetic materials that have special characteristics thanks to their atomic spin – a property that makes each atom a tiny magnet. The spins of neighbouring atoms affect each other; this can allow domains to form with spin in the same direction. He was able to make a model network with nodes and connections by using the physics that describes how materials develop when spins influence each other.
然而，他并没有放弃物理学基础，在那里他找到了对许多小部件协同工作的系统如何产生新颖有趣现象的启发。他特别从学习具有特殊特性的磁性材料中获益，这些特性是由于原子自旋 - 这种属性使每个原子都是一个微小的磁铁。相邻原子的自旋相互影响；这可以让相同方向的自旋区域形成。他能够使用描述自旋相互影响时材料发展的物理学知识，建立了一个带有节点和连接的模型网络。
The network saves images in a landscape
网络保存图像为横向
The network that Hopfield built has nodes that are all joined together via connections of different strengths. Each node can store an individual value – in Hopfield’s first work this could either be 0 or 1, like the pixels in a black and white picture.
霍普菲尔德构建的网络由相互连接的节点组成，连接的强度各不相同。每个节点可以存储一个独立的值 - 在霍普菲尔德的第一项工作中，这个值可以是 0 或 1，就像黑白图片中的像素一样。
Hopfield described the overall state of the network with a property that is equivalent to the energy in the spin system found in physics; the energy is calculated using a formula that uses all the values of the nodes and all the strengths of the connections between them. The Hopfield network is programmed by an image being fed to the nodes, which are given the value of black (0) or white (1). The network’s connections are then adjusted using the energy formula, so that the saved image gets low energy. When another pattern is fed into the network, there is a rule for going through the nodes one by one and checking whether the network has lower energy if the value of that node is changed. If it turns out that energy is reduced if a black pixel is white instead, it changes colour. This procedure continues until it is impossible to find any further improvements. When this point is reached, the network has often reproduced the original image on which it was trained.
霍普菲尔德使用一个等同于物理自旋系统中能量的属性来描述网络的整体状态；能量使用涉及所有节点值和所有连接强度的公式计算。霍普菲尔德网络通过将一幅图像输入到节点中而被编程，节点的值被设置为黑色（0）或白色（1）。然后使用能量公式调整网络的连接，使得保存的图像获得较低的能量。当另一种模式输入网络时，有一个逐个检查节点并查看该节点值的改变是否能使网络能量降低的规则。如果发现将一个黑色像素改为白色可以降低能量，则会改变颜色。这一过程一直持续到无法找到任何进一步的改进为止。达到这一点时，网络通常已经复制了其训练所依据的原始图像。
This may not appear so remarkable if you only save one pattern. Perhaps you are wondering why you don’t just save the image itself and compare it to another image being tested, but Hopfield’s method is special because several pictures can be saved at the same time and the network can usually differentiate between them.
如果您只保存了一个模式，这可能看起来并不那么引人注目。也许您会想知道为什么不直接保存图像本身并将其与正在测试的另一个图像进行比较，但霍普菲尔德的方法是特殊的，因为可以同时保存多张照片，而且网络通常可以区分它们。
Hopfield likened searching the network for a saved state to rolling a ball through a landscape of peaks and valleys, with friction that slows its movement. If the ball is dropped in a particular location, it will roll into the nearest valley and stop there. If the network is given a pattern that is close to one of the saved patterns it will, in the same way, keep moving forward until it ends up at the bottom of a valley in the energy landscape, thus finding the closest pattern in its memory.
霍普菲尔德把在网络中搜索一个已保存的状态比作在丘陵起伏的山谷地形中滚动一个球，摩擦力会减慢其移动。如果在特定位置放下球，它会滚入最近的山谷并在那里停下。如果给网络一个接近其中一个已保存模式的模式，它也会以同样的方式一直向前移动，直到到达能量地形中的一个山谷底部，从而找到其记忆中最相近的模式。
The Hopfield network can be used to recreate data that contains noise or which has been partially erased.
霍普菲尔德网络可用于重建包含噪音或部分被擦除的数据。