Blog

Gradient descent is an optimization algorithm used to minimize a function. Gradient descent works by iteratively moving in the direction opposite to the gradient of the function, with the step size determined by a hyperparameter called “learning rate”. Gradient descent is commonly used in machine learning to adjust the parameters of a model in order to minimize the loss function, especially in deep learning. In deep learning, gradient descent will adjust every trainable weights and biases of the model in which when these weights and biases are used, the loss function will be minimum. This article is originally published in Cantor’s Paradise and is currently behind medium paywall. If you have medium subscription, please have a look at the original version.

Most machine learning algorithms are fulfilled with mathematical things such as statistics, algebra, calculus and etc. They expect the data to be numerical such as a 2-dimensional array with rows as instances and columns as features. The problem with natural language is that the data is in the form of raw text, so that the text needs to be transformed into a vector. The process of transforming text into a vector is commonly referred to as text vectorization. It’s a fundamental process in natural language processing because none of the machine learning algorithms understand a text, not even computers. Text vectorization algorithm namely TF-IDF vectorizer, which is a very popular approach for traditional machine learning algorithms can help in transforming text into vectors. This article is originally published in Towards Data Science and is currently behind medium paywall. If you have medium subscription, please have a look at the original version.