¡Hola, Mundo!

Transfer learning A technique in machine learning (ML) in which knowledge learned from a task is re-used in order to boost performance on a related task. In other words, the re-use of a pre-trained model on a new problem. For example, for image classification, knowledge gained while learning to recognize cars could be applied when trying to recognize trucks. The general idea is to use the knowle..

Backpropagation Whereas Logistic Regression is made of a single layer of weights, Neural Networks are made of many layers with non-linear activation. We need to have a mechanism to update the weights of the neurons using the gradient of the loss. Such a mechanism is called Backpropagation. It propagates the gradient from the last layer to the first one. chain rule It allows you to decompose the ..

Sigmoid With only two classes, performs exactly the same operation as Softmax. Logits It refers to the stage before passing the final Sigmoid or Softmax, that is, the Raw Output of the Model. Sigmoid and Softmax receive the Logits to safely perform the operation. Softmax For multi-label available only, where one object can have multiple classes at the same time. 1. Softmax case1. 1d array. step1..

Entropy The level of uncertainty. It must range between 0 and 1. 0

TestError The error rate of the model on the test dataset. TestError=Var+Bias+e Variance It quantifies the sensitivity of the model to the training data. In other words, if we were to replace our training dataset with another one, how much would the training error rate change(how much the model's parameters would change)? A low variance means that our model is not sensitive to the training data ..