Employing neural networks to classify calls

Artificial Neural Networks (ANN) are machine learning models that try to mimic the functions of a biological brain. A fundamental unit of a neural network is a structure called neuron. A neuron has one or multiple inputs and a soma: a part of the neuron that sums up the input signals that are then passed through an activation (transition) function that decides whether (and/or how) to propagate the signal to the output. There is a multitude of various transition functions that an artificial neuron can implement. These range from the basic ones such as the step function that sends a signal only if a certain threshold is exceeded through linear activation functions that do not alter the signal in any way ...

Get Practical Data Analysis Cookbook now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.