A building operation is also called “training” a model, and the model is said to “learn” from the training data.
Models are often trained to identify the set of features, algorithms, and hyper-parameters that create the best model for their problem. Before arriving at the ideal model, it is not uncommon to train hundreds of models that do not make the cut.
A model that seeks to identify the customers who are likely to respond to a promotion must be trained by analyzing the characteristics of many customers who are known to have responded or not responded to a promotion in the past.
- MobileNet - Classify images with labels from the ImageNet database.
- PoseNet - Realtime pose detection. Blog post here.
A record of a trained model to build the history will be like:
- Who trained the model
- Start and end time of the training job
- Full model configuration (features used, hyper-parameter values, etc.)
- Reference to training and test data sets
- Distribution and relative importance of each feature
- Model accuracy metrics
- Standard charts and graphs for each model type (e.g. ROC curve, PR curve, and confusion matrix for a binary classifier)
- Full learned parameters of the model
- Summary statistics for model visualization