Supervised learning comparison

MoA into one of the known MoAs of the GEP Compendium with a single experiment. Arahidopsis plants are sprayed with the respective compound and the isolated and labeled RNA is analyzed on the Arahidopsis chip. Subsequently, the resulting expression profile is compared with those in the compendium. This comparison is done by supervised learning algorithms like Support Vector Machine (SVM) [15] or Analysis of Variance (ANOVA) [16]. When the new expression profile groups together with profiles of a specific MoA in the compendium there is an utmost probability that the corresponding compound has the same MoA (Fig. 33.4). If necessary, the MoA can be verified by classical methods such as enzyme assays or supplementation tests, if available. 

In supervised learning, the network is presented with a set of input and desired output data. A teacher is assumed to be present during this learning. A comparison is made between the predicted output and the desired output and the error signal is calculated. This error signal is then used to modify the synaptic weights in several steps and thus improved performance is... 

For supervised training a set of desired outputs is needed, so the network learns by direct comparison of its outputs against the set of expected values on the other hand, unsupervised training does not count with a set of defined outputs, the only available information is the correlation that might exists in input data. With the latter procedure it is expected that the network creates categories from these correlations and be able to output values according to the input category. 

---