主权项 |
1. A neural network designing method comprising:
a forming procedure causing a computer to form a RNN (Recurrent Neural Network) circuit to include a plurality of oscillating RNN circuits configured to output natural oscillations, and an adding circuit configured to obtain a sum of outputs of the plurality of oscillating RNN circuits; and a computing procedure causing the computer to input discrete data to the plurality of oscillating RNN circuits, in order to compute a fitting curve with respect to the discrete data output from the adding circuit, wherein the computing procedure includes
computing and storing in a storage unit a0,a1, . . . , a2n-1,b1, . . . , b2n-1represented by the following formulas from the discrete data y0=0, y1, . . . , y2n-1, y2n=0,a0=12n∑i=12n-1yi=12n∑i=02nyiaq=ψ(q2n)4nπ2∑i=12n-1yi(-cos(i-1)qπn+2cosiqπn-cos(i+1)qπn)q=1,2…2n-1bq=ψ(q2n)4nπ2∑i=12n-1yi(-sin(i-1)qπn+2siniqπn-sin(i+1)qπn)q=1,2…2n-1ψ(x)=ⅆ2ⅆx2logΓ(x) where ψ(x) denotes a trigamma function that is defined by a second derivative of a logarithm of a gamma function, and a0, a1, . . . , a2n-1, b1, . . . , b2n-1 are fixed values independent of the time t, and
computing the fitting curve defined by the following formula, using the fixed values a0,a1, . . . , a2n-l, b1, . . . , b2n-1,y(t)=a0+∑q=12n-1aqcosqπnt+∑q=12n-1bqsinqπnt where cos (qπt/n) and sin(qπt/n) are oscillating functions output from the plurality of oscillating RNN circuits. |