To our knowledge, the proposed algorithm is the fastest single-image super-resolution algorithm when both training and test time are considered.
Naturally, these approaches require the speaker transforms or augmented features to be present at both training and test time.
The hybrid input representation can considerably save both training and decoding time while still achieving slightly better recognition accuracy.
We do not resort to any object bounding-box and part annotation on both training and testing time, only image labels are used.
Furthermore, both training and classification times are approximately eight times faster on all folds.
The developed model was reasonably accurate in simulating both training and test time-dependent growth curves as affected by temperature and pH.
Both training and test times of NGN and NN, yet in some cases significantly different, had similar values (<6 min) for HD, IF and BC problems (Figure 1E).
When samples acquired in controlled scenarios are used for both phases, the average convergence time is 30 s, while when samples acquired in random scenarios are used for both training and testing, the convergence time increases with 10 s.
Similarly to the intra-subject methodology, when the samples acquired in the controlled scenario are used for both training and testing, the maximum time needed to compute the 16PF predicted traits was 33 s, while when samples acquired in random scenarios are used, the time to converge is 12 s higher.
In terms of execution time, the hybrid models took less time for both training and testing than the Type-2 Fuzzy Logic, but more time than Functional Networks and Support Vector Machines.
