Figure 4 | Scientific Reports

Figure 4

From: Role of non-linear data processing on speech recognition task in the framework of reservoir computing

Figure 4

Spoken digit recognition for a neural network. (a) Spoken digit gain on cross-validated test recognition rates as a function of the number of subsets \(N\) used during training for a non-linear oscillator modelled with Eqs. (2 and 3) and (b) experimental spin torque nano-oscillator driven by spin polarised current. The coloured region corresponds to the uncertainty of the recognition rate, here twice the standard deviation.

Back to article page