"machine learning results" is correct and usable in written English.
You can use it whenever you are referring to results obtained through the application of machine learning algorithms. For example, "The machine learning results showed a marked improvement in accuracy."
Graphical abstract Comparison of machine learning results obtained for various number of beta-2 AR homology models and crystal structures.
Figure 11 Diagrams for machine learning results: (upper left) Scatter plot with experimental versus predicted output values.
This indicates that using the h-index information to measure semantic similarity results in a better performance at filtering out false positives from machine learning results.
The highly flexible model structure of methods in data mining and machine learning results in models that are often difficult to interpret.
The main machine learning results reported herein are based on the correct DLS-100 solubilities, but we have also explored the effect of using the imprecise provisional data from the survey training.
The effects of the machine learning results are small, though strangely the imprecise training data led to very slightly better median machine learning classifier results (RMSE = 1.095, R2 = 0.632).
In this case it is shown that the first fifty components do only have a negligible in influence on the machine learning result and thus may be excluded from further analysis.
A second advantage of discretization is that it contributes to the interpretability of the machine-learning results, as people can better understand the connection between different ranges of values and their impact on the learned target [3, 13].
The model that includes a three-way epistatic interaction as the primary genetic effect yields a diversity of machine learning performance results with AUCs ranging from a low of 0.53 for the naïve Bayes method and a high of 0.67 for the classification tree.
A popular browser extension which correlates machine learning with results on search engines is CANTINA+ [20], while an analysis of the performance of different machine learning approaches has also been made [21].
Although it is not feasible to test every type of published machine learning algorithm, results presented do provide a baseline comparison to demonstrate whether classical machine learning tools are already sufficiently mature to justify further clinical evaluation.
