Verifying with AutoML
Last updated
Last updated
This feature is not for free.
AutoML automatically sets algorithm settings and hyperparameter tuning for training based on the core know-how of DS2.ai. In particular, it learns various AI models through the division of algorithm libraries and hyperparameter tuning suitable for training datasets, and simplifies the process of verifying artificial intelligence models and deriving optimal models.
It refers to the data set entered into the CSV-type table structure, and it is divided into category classification divided into set values such as A/B/C and continuous value classification in numerical form to obtain the necessary predictions for the situation.
You can predict grades such as A/B/F, Yes or No, or set results or discontinuous values such as specific brands.
It is a function that predicts continuous results in the form of numbers, and can be used in a way that represents the risk in a particular field as a % number, scores in a particular field, or predicts scores.
It is a process that allows computers to process and understand human language phenomena, and can be used as functions such as chatbot or translation, judgment of malicious comments, and authenticity.
By analyzing the preferences among users, you can find users with similar tendencies to the customer and recommend products, contents, classes, etc.
By training image models classified by category, you can predict which category the image belongs to.
You can learn images using data that contain labeling in the form of images and JSON, classify which objects are in the image, and distinguish the location of the objects.
Set the Training Method to High Accuracy or Faster Training Speed
Set other options for model training. (For more information, see Verifying > Training the Model for Verification > Model Training Options for Verification.)
Do you have any other questions? [email protected]