Machine Learning EN

Machine Learning: Top questions pt. 2

As we saw in the previous article, machine learning has become an opportunity for revolution and innovation in the insurance industry. That is why, as a continuation of this special series of articles, here is part 2.

Shall we begin?

What is a classifier in machine learning?

It is a system that inputs a vector of discrete or continuous feature values and outputs a single discrete value, the class.

What is a multilayer perceptron (MLP) in machine learning?

It is a kind of feed-forward artificial neural network. An MLP consists of at least three layers of nodes: an input layer, a hidden layer, and an output layer. 

Except for the input nodes, each node is a neuron using a nonlinear activation function. The MLP uses a supervised learning technique called backpropagation for training. 

This is how its multiple layers and nonlinear activation can distinguish data that are not linearly separable.

What is backpropagation?

It is a widely used algorithm for training feedforward neural networks (The pre-feedforward neural network was the first and simplest form of artificial neural network devised), which calculates the gradient of the loss function with respect to the network weights for a single input-output, updating the weights to minimize the loss (gradient descent).

Why use a convolutional neural network instead of an MLP when dealing with images?

Convolutional neural network (CNN): the current favorite of computer vision algorithms: 

  • Weights are smaller (shared and with less waste).
  • Easier to train than MLP (computationally cheaper).
  • It can be deeper, because the layers are sparsely connected rather than fully connected.

What is inductive machine learning?

Inductive machine learning involves the process of learning. For example, where a system, from a set of observed instances, attempts to induce a general rule.

What are the most popular machine learning algorithms and their approaches? And what are test and training sets all about?

Learn about this and much more in our next article!

Deja una respuesta

Tu dirección de correo electrónico no será publicada. Los campos obligatorios están marcados con *