John Hopfield showed how an interacting neural network can retrieve a stored pattern from incomplete information. His 1982 model uses asynchronous updates of simple units, with symmetric couplings allowing an energy-like function to decrease as the network evolves. Stored patterns act as attractors, so the collective dynamics can correct some corrupted input rather than requiring an exact address. The physical analogy connects stable states of an interacting system with associative computation; convergence to a stable state does not by itself guarantee retrieval of the intended pattern.[ref]
Neural networks and physical systems with emergent collective computational abilities by John Joseph Hopfield. Proceedings of the National Academy of Sciences 79, 2554–2558 (1982), associative memory and asynchronous dynamics
A physicist who studied condensed matter physics and theoretical models of neural networks.[ref]
John J. Hopfield - Curriculum vitae. Experience: research physicist and Physics professorships, 1960–1980
Portrait of John Hopfield
. Arthur Petron, own photograph at the Nobel-week press conference, Stockholm, 8 December 2024. Creative Commons Attribution-Share Alike 4.0 International., via Wikimedia Commons. Source. Articles by others on the same topic
John Hopfield is a prominent American physicist and neuroscientist known for his contributions to the fields of computational neuroscience and theoretical biology. He is best recognized for developing the Hopfield network in 1982, a form of recurrent artificial neural network that serves as a model for associative memory. Hopfield networks are particularly noted for their ability to store and recall patterns, making them a foundational concept in neural computation and machine learning.