Inference device, convolution computation method and program

A convolution computation method for an inference device that comprises a weight storage part that stores weights and an input data storage part that stores input data, executes convolution computation in convolutional neural network using the weights and input data, wherein

• the method comprises:
• adding up weight elements to be multiplied with elements of the input data for each of variable values of the elements of the input data,
• multiplying each of the variable values of the elements of the input data with each cumulative sum value of weights corresponding to the variable values of the elements of the input data, and
• adding up a plurality of multiplication results obtained by the multiplication.

A non-transient computer readable medium storing a program executed by a computer implemented in an inference device that comprises a weight storage part that stores weights and an input data storage part that stores input data, executes convolution computation in convolutional neural network using the weights and input data,

• wherein the program causes the computer to execute the following processes:
• adding up weight elements to be multiplied with elements of the input data for each of variable values of the elements of the input data,
• multiplying each of the variable values of the elements of the input data with each cumulative sum value of weights corresponding to the variable values of the elements of the input data, and
• adding up a plurality of multiplication results obtained by the multiplication.