The confusion matrix is an evaluation metric widely popular for classification problems. Evaluation terminologies like true positive, false positive, true negative, false negative, f1-score, etc; are derived from this metric. Some of them are covered in this article. Introduction When it comes to an evaluation of a classification problem, the Confusion Matrix is one of the widely popular evaluation metrics. It ...
Logistic regression algorithm explanation, use-cases, diagrams, and formulas used in development. Background Brief Logistic regression is one of the very first and popular algorithms for classification tasks. It is also a supervised machine le...
Mini-batch gradient descent is an optimization algorithm that is used to reduce an error in a model through the identification of proper weights. This article contains the definition of mini-batch gradient descent and a detailed explanation with pseudocode. Background Mini-batch gradient descent is another algorithm from the gradient descent family. It is a mix of batch and stochastic gradient descent...
Stochastic gradient descent is an optimization algorithm that is used to reduce an error in a model through the identification of proper weights. This article contains the definition of stochastic gradient descent and a detailed explanation with pseudocode. Background Stochastic gradient descent is an optimization algorithm from the gradient descent family that is better than batch gradient descent in...
Elastic net regression algorithm explanation and formulas used in development. Background Brief Elastic Net Regression is an algorithm that overcame the limitations of both ridge and lasso regression by incorporating both of...
Lasso regression algorithm explanation and formulas used in development. Background Brief Lasso regression is also known as L1 regularization and LASSO stands for Least Absolute Shrinkage and Selection Operator. It is ...
Mode is a statistical concept for finding a number that is repeated the most in the series of a number. Concept Mode is a statistical concept of finding a number that is repeated the most from the series of numbers. It is useful in understanding the ...
Median is a statistical concept for determining a middle value of all the values present in a dataset. Comparing it with the mean, we can deduce how much our data is skewed. Concept Median is a statistical concept of finding a middle value from a set of values. It is very useful to understand the skewness and distribut...
Mean or Average is a statistical concept for determining an average or a mean of all the values present in a dataset, it helps us understand how data is distributed in a sample or a population. Concept Mean or Average is used widely in machine learning starting from algorithms to evaluation and optimizations. It is simply an average of a ...
Batch Gradient descent is an algorithm for the optimization of a model to reduce a prediction error. This article contains the definition of a batch gradient descent and detailed explanation with pseudocode, formulas and diagrams. Background Batch gradient descent is one of the types of optimization algorithms from the gradient descent family. It is widely used in machine le...