Sentence examples for runtime learning from inspiring English sources

Fig. 5 Recognition accuracy during runtime learning.

Basically, our method deals with a trade-off between flexibility and accuracy in order to allow for runtime learning.

and sensors (high frame rate, low frame rate), and outperformed other methods that are capable of runtime learning on the challenging MSR-Action3D dataset.

Horizontal axis: input instances, vertical axis: average recognition accuracy (percentage) Fig. 6 Total number of instances in the ATs during runtime learning.

Horizontal axis: input instances, vertical axis: average number of instances in the ATs Fig. 7 Classification time for one instance during runtime learning.

Compared to the state-of-the-art methods that are not capable of runtime learning, our performance is slightly inferior.

Open image in new window Fig. 4 Learning runtime in seconds for one iteration over the whole training set (in log-y scale) over Yahoo! dataset with different latent dimensions.

In order to compare the runtime of various models, we do experiment on Yahoo! dataset for one full iteration over whole training set. Figure 4 shows that the learning runtime of RPFM is faster than that of Multiverse and COT with increasing the dimensionality, however, slower than that of FM which is obvious because RPFM generates an ensemble which reduces the prediction error.

In this paper, we present a Petri net-based approach that facilitates making structural changes at runtime to units of learning specified in IMS Learning Design IMS LDD).

There is a range of HAR-based applications that require learning new actions in runtime.

We have also successfully demonstrated the flexibility of our approach, which allows performing HAR with very few training instances, while learning new actions at runtime.