The 2024 Nobel Prize in Physics is awarded "for foundational discoveries and inventions that enable machine learning with artificial neural networks."
The laureates' work from the early 1980s became the foundation of modern machine learning.
➡️ John Hopfield created an associative memory capable of storing and reconstructing images and other types of patterns in data. His network, the Hopfield network, works similarly to how atomic spins interact in magnetic materials, where each node connects with others. It can correct and complete distorted or incomplete images by methodically working through the nodes and updating their values to reduce the network's energy.
➡️ Geoffrey Hinton used the Hopfield network as the foundation for a new neural network called the Boltzmann machine. This network identifies characteristic features in data. Using tools from statistical physics, it learns to recognize and classify images and generate new ones based on learned patterns. Hinton is one of the pioneers of machine learning.
The machine is trained by feeding it examples that are very likely to arise when it is run. Researchers use the Boltzmann machine to classify images or create new examples of the type of pattern it has been trained on. Hinton built upon this work, helping initiate the current explosive development of machine learning.
The laureates' work has already been of the greatest benefit. In physics, we use artificial neural networks in a vast range of areas, such as developing new materials with specific properties.
Ellen Moons, Chair of the Nobel Committee for Physics
#news @hiaimedia