首页|Researchers Submit Patent Application, “Control Of Hyperparameter Tuning Based On Machine Learning”, for Approval (USPTO 20240144102)

Researchers Submit Patent Application, “Control Of Hyperparameter Tuning Based On Machine Learning”, for Approval (USPTO 20240144102)

扫码查看
News editors obtained the following quote from the background information suppli ed by the inventors: “It has become commonplace to use AI models to perform any of a wide variety of functions. However, while some aspects of preparing an AI m odel to perform a function have become relatively well defined and understood, o ther aspects may require time consuming experimentation. For example, while ther e may be considerable information available concerning the most effective type o f AI model to use for performing some functions (e.g., visual recognition), ther e may be a relative lack of such information available for other functions such that the determination of which type of AI model to use may require some degree of trial and error experimentation. Additionally, even where the type of AI mode l that is deemed to be best for use in performing a particular function may be w ell known, there may be a relative lack of information available concerning tuni ng various configuration aspects of an implementation of that AI model to perfor m that function. Such configuration aspects are often referred to as “hyperparam eters” to distinguish them from the parameters that are learned by training. It may be that deriving the hyperparameters may also require some degree of time co nsuming trial and error experimentation.”

BusinessCapital One Services LLCCybo rgsEmerging TechnologiesMachine Learning

2024

Robotics & Machine Learning Daily News

Robotics & Machine Learning Daily News

ISSN:
年,卷(期):2024.(MAY.17)