Objective Function

비용 함수(Cost function) 는 목적 함수(objective function) 의 한 종류입니다.
- 비용 함수는 모델의 오차를 최소화하기 위한 함수이며, 목적 함수로 사용됩니다.

Definition:
- An objective function in Machine Learning is a mathematical function that quantifies the performance of a model, which the learning algorithm aims to optimize (minimize or maximize) during the training process (Kronosapiens Labs, 2017).
- It provides a formal specification of the problem and guides the model towards optimal parameters (MathWorks, n.d.).
Examples:
- Mean Squared Error (MSE) for Regressionon problems: Measures the average squared difference between predicted and actual values.
- Cross-Entropy Loss for Classification problems: Quantifies the difference between predicted probability distributions and actual class labels.
- Hinge Loss for Support Vector Machines: Measures the margin violation in classification tasks.

Literature Review

Objective Functions in Machine Learning
- Source: Kronosapiens Labs Blog
Key points:
- Describes objective functions as a fundamental component of machine learning problems.
- Explains how objective functions provide a formal specification of the problem to be solved.
- Discusses the relationship between objective functions and optimization in machine learning.

Machine Learning Models
- Source: MathWorks
Key points:
- Discusses various types of machine learning models and their associated objective functions.
- Explains how objective functions are used to evaluate and optimize model performance.
- Provides examples of objective functions for different machine learning tasks.

Gradient DescentGradientDescent
- An optimization algorithm commonly used to minimize the objective function by iteratively adjusting model parameters.
Model Evaluation (Model Evaluation)ModelEvaluation
- The process of assessing a model’s performance, often using metrics derive