Mostrando postagens de junho, 2021
  Stochastic vs Batch Gradient Descent One of the first concepts that a beginner comes across in the field of deep learning is gradient descent followed by various ways in which it can be implemented. Gradient descent is one of the most important concept used in the training of neural networks for supervised learning. Hence, it is important to understand it and the different ways in which it is to be carried out on the training sets. This post mostly deals with t h e different ways in which gradient descent is implemented on a training set. Thus, I will briefly go over the definition of the concept and then explain the advantages and disadvantages of all the possible ways. Gradient Descent This is an iterative optimization algorithm for finding the minimum of a function. The algorithm takes steps proportional to the negative gradient of the function at the current point [1]. In deep learning neural networks are trained by defining a loss function and optimizing the parameters of the ne

Unsupervised Machine Learning: What is, Algorithms, Example

 By Prof. João Cláudio Nunes Carvalho What is Unsupervised Learning? Unsupervised Learning  is a machine learning technique in which the users do not need to supervise the model. Instead, it allows the model to work on its own to discover patterns and information that was previously undetected. It mainly deals with the unlabelled data.] Unsupervised Learning Algorithms Unsupervised Learning Algorithms  allow users to perform more complex processing tasks compared to supervised learning. Although, unsupervised learning can be more unpredictable compared with other natural learning methods. Unsupervised learning algorithms include clustering, anomaly detection, neural networks, etc. Example of Unsupervised Machine Learning Let's, take an example of Unsupervised Learning for a baby and her family dog. She knows and identifies this dog. Few weeks later a family friend brings along a dog and tries to play with the baby. Baby has not seen this dog earlier. But it recognizes many features