Gradient descent is an optimisation algorithm used in machine learning and deep learning to adjust the parameters of a model to minimise the cost or loss function.
The goal of gradient descent is to find the values of the model parameters that minimise the cost function, i.e. those that produce the most accurate predictions. To do this, the algorithm uses the information provided by the gradient of the cost function at each iteration of the training process.
At each iteration, the gradient descent adjusts the values of the model parameters in the opposite direction to the gradient of the cost function, in order to decrease the prediction error. The learning rate is a hyperparameter of the algorithm that determines the step size at each iteration, and can be adjusted to obtain a trade-off between convergence speed and accuracy of the result.
Gradient descent is used in various machine learning and deep learning algorithms, such as linear regression, logistic regression, neural networks, among others.
The content of this article synthesizes part of the chapter "Concept and brief history of Artificial Intelligence" of the thesis Generation of Artificial [...]
Read More »To know how semantic technology works, the first thing you need to know is that it is responsible for helping artificial intelligence systems [...]
Read More »After the revolutions led by coal, electricity, and then electronics, society is now witnessing a fourth revolution in the energy sector.
Read More »The banking sector has undergone considerable transformations over the past 10 years. Especially as banking has become more integrated and [...]
Read More »