Neural network method and apparatus

A neural network apparatus comprising:

• a processor configured to:
• obtain synaptic weights for synapses of a neural network, where the neural network includes a plurality of layers that each include plural neurons, with plural synapses connecting neurons included in neighboring layers of the plurality of layers;
• and
• implement, using the synaptic weights, at least a layer of the neural network without weight sharing,
• wherein the synaptic weights include weights, previously having pre-regularized values greater than zero and less than a value of a variable a that is greater than zero, that are regularized values having been set to zero,
• wherein the synaptic weights include weights, previously having pre-regularized values greater than a value of a variable b that is greater than the value of the variable a, that are additional regularized values having been set to the value of the variable b.

A neural network apparatus comprising:

• a processor configured to:
• obtain synaptic weights for synapses for a layer of a neural network, where the layer of the neural network includes plural neurons, and where the synaptic weights correspond to weighted connections for respective inputs to the plural neurons;
• and
• implement the layer of the neural network with the synaptic weights,
• wherein the synaptic weights include weights, previously having pre-regularized values greater than zero and less than a value of a variable a that is greater than zero, that are regularized values having been set to zero,
• wherein the synaptic weights include weights, previously having pre-regularized values greater than a value of a variable b that is greater than the value of the variable a, that are additional regularized values having been set to the value of the variable b, and
• wherein the synaptic weights include synaptic weights that are values dispersed, between the value of the variable b and the value of the variable a, based on previous training of the layer.

A neural network method, the method comprising:

• obtaining and implementing a neural network with a plurality of layers each comprising neurons, with plural synapses connecting neurons included in neighboring layers of the plurality of layers,
• wherein the plural synapses include synaptic weights, as obtained in the obtaining of the neural network, for considering data input to a layer of the plurality of layers having the plural synapses for a trained objective,
• wherein the synaptic weights include weights, previously having pre-regularized values greater than zero and less than a value of a variable a that is greater than zero, that are regularized values having been set to zero,
• wherein the synaptic weights include weights, previously having pre-regularized values greater than a value of a variable b that is greater than the value of the variable a, that are additional regularized values having been set to the value of the variable b, and
• wherein the implementing of the neural network includes implementing the layer of the neural network without weight sharing.