NEURAL NET MODEL AND NEURAL NET OPTIMIZING METHOD AND SYSTEM FOR REALIZING THE SAME

A recursive neural net including processing elements (1) each having a linear saturated function as an input/output function. The elements (1) are divided into a plurality of blocks (2), and the states of the elements (1) are asynchronously updated block by block while being synchronously updated within each block (2). Since convergence is ensured for any symmetric synaptic matrix (W) by selecting a step-size for each particular problem, the neural net can be applied to any optimization problem. In addition, a neural net system is composed of an optical computing unit (201 to 205) performing a vector matrix calculation using light, a threshold processing unit (206) performing a threshold processing operation, a coefficient multiplying unit (209) performing a step-size processing operation, a saturated linear computing unit (207) performing a saturated linear function operation, and a block control unit (208) performing selection of a block to be updated and state updating therefor.