Assessing model quality
We have emphasized the importance of data over algorithms, and we have seen which strategies to follow in the data quality process.
Once we are sure that the data is reliable and complete, we must feed it to the algorithms selected for the implementation of our AI solutions, submitting the results obtained to the model quality process.
The model quality process involves all the phases of algorithm deployment.
In fact, it is essential to monitor the performance of our algorithms, in order to constantly perform the fine tuning of the hyperparameters.
By hyperparameters, we mean all the parameters that the algorithm receives from the outside (that is, parameters that are not set or updated in consequence of the learning ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access