Experiment execution – screen showcase

(draft, will be updated soon)

In this article we’ll show how experiment execution looks like in the console output.
The purpose is to make you aware what’s going on and what is what, once you started the experiment.

 

The experiment execution process may be divided into two main parts:

  • Preparation
  • FVERefers to Feature Vector Extraction model, that may have one or more Feature Vector Providers, which is implementation wrapper for particular document semantic similarity computation model.... model execution

Preparation

In this part, the program performs all operations producing resources, that are later required for all FVERefers to Feature Vector Extraction model, that may have one or more Feature Vector Providers, which is implementation wrapper for particular document semantic similarity computation model.... models in the experiment setup. Contains several phases, where some are performed in parallel threads, some in the main thread

Pipeline machine – content pre-processing

 

Lemma Table construction

 

Chunks detection and Phrase table construction

 

FVERefers to Feature Vector Extraction model, that may have one or more Feature Vector Providers, which is implementation wrapper for particular document semantic similarity computation model.... model execution

  •  n-th case of k-fold execution, where n ∈ (0→k)

Main experiment loop

 

Cloud Matrix construction

 

Classifiers training process

 

Experiment report generation

Reporting – the final step for an experiment

Final remarks

Merging the Category Semantic Cloud

Meaning of sounds:

When imbWBIWeb Business Intelligence libraries of imbVeles Framework. Console Tool beeps, that is usually a bad sign. The only regular situation when you should hear short beep is when Pipeline Machine displays its status report. After that stage of experiment execution, every beep is an evil beep :).

Spread the love