Neural Networks
Artificial Neural Networks (ANNs) are a type of machine learning model loosely inspired by the biological structure of the brain. They are used in machine learning to be trained on data in order to analyze new data.
A neural network is made up of multiple layers of neurons. The first layer is known as the input layer, the last layer as the output layer, and the layers in between as the hidden layers. An example of the purpose of the neural network layers is with digit recognition from the mnist data set.
The first layer of the network will receive the 784 pixels of the digit’s image as input. In the following hidden layers, the shapes and lines making up the digit will be broken up continuously and passed on to the following layer where the model will update its weights and biases for each neuron in the layer. Finally, based on the input from the last hidden layer, the output layer will output the digit that has been recognized.
- Neural networks take longer to train than algorithms do and are better for unsupervised learning because of their more robust structures.
- Additionally, it is optimal to train neural networks with fewer attributes.
Principle Component Analysis (PCA) is a method that reduces the dimensionality of a data set consisting of many attributes whilst retaining the variation in the dataset. This method is used to limit a dataset to only a few features for training.