From the course: Choosing the Right ML Approach for Your Business Case with ISO/IEC 25053:2022

Unlock this course with a free trial

Join today to access over 25,300 courses taught by industry experts.

ML optimization methods (Clauses 6.5.4-6.5.4.8)

ML optimization methods (Clauses 6.5.4-6.5.4.8)

From the course: Choosing the Right ML Approach for Your Business Case with ISO/IEC 25053:2022

Start my 1-month free trial Buy for my team

ML optimization methods (Clauses 6.5.4-6.5.4.8)

“

- When you drive a car, the expected degree of change of direction of your front wheels is like an output function. This is based on the degree of which you turn your steering wheel, which is like an input function. When the expectation of the degree of the turning of the wheel doesn't match the output of the wheel's turning, you know you need to get alignment work done. In like manner, you also expect a particular degree of accuracy in the target variable or output from your machine learning based on its input. When the expectation isn't met, you address the misalignment with optimization to improve the accuracy of models and reduce the risk of error. In most cases, the optimization is designed to address a loss or a cost function. This mathematical function measures the difference between a model's predicted output and the actual true output. It is a critical concept in machine learning as it quantifies the error made by a model in its predictions. This guides the optimization…

Contents