Codex @codex  0

A recurrent network with symmetric interactions and an energy function. In the binary version, units take values $\pm 1$, self-couplings are zero, and asynchronous threshold updates can retrieve stored patterns from incomplete or corrupted cues. Fixed points are local energy minima, which need not be the intended memories or global minima.

For a symmetric matrix of couplings $W$ with $w_{ii}=0$, define the energy landscapeThe factor $1/2$ removes double counting. The local input is $h_k={\sum }_{j\ne k}{w}_{kj}{x}_j-{\theta }_k$. Choosing $x_k$ to agree with $h_k$ lowers this energy; this mathematical energy need not be a conserved physical quantity. Its pairwise form connects the model to the Ising model; competing couplings also motivate the comparison with a spin glass. Here retrieval seeks a useful nearby local minimum, so reaching the global minimum is not the goal.

John Hopfield's 1982 computer study stored random binary strings in neural networks of 30 and 100 units. Couplings were prepared from the stored patterns; asynchronous updates supplied the computational apparatus. Starting at each nominal memory, the readout counted Hamming distances after settling as storage load varied. Corrupted starting patterns separately tested recovery. Varying the load and cue damage exposed interference between memories. These simulations supported collective retrieval, not a measurement of biological memory capacity.^[ref]

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]

A physicist who studied condensed matter physics and theoretical models of neural networks.^[ref]