| Author: | Francesco Lelli |
| Learning Line: | Genetic Algorithms |
| Course: | AI1: Introduction to Neural Networks |
| Week: | 7 |
| Competencies: | Understand and be able to use neural network dynamics and factors that influence their performance |
| BoKS: | 3aS4 The student is able to distinguish supervised, unsupervised and reinforced learning Machine Learning, and is able to develop specific learning strategies for specific business contexts. |
| Learning Goals: | Genetic Algorithms and more practical aspects |
Artificial neural networks (ANN) or simply “neural networks” are computing systems inspired by “classical biological” neural networks that are in animal brains. Typically an ANN “learn” to perform tasks by considering examples, without being programmed with task-specific rules.
By now you should be able to implement the “hello world” of Neural Networks. In thinking to what is missing in these lectures I would say that an introduction to genetic algorithms is probably the most important part. In a nutshell is a technique for optimizing a particular model that is inspired by biological evolution theories. When we design a neural network we usually make a lot of assumption on its characteristics such as, for example, type of activation of the neurons, hidden layers, type of connections, way of back-propagate the feedback etc. As these aspects could be considered features of a particular network, a genetic algorithm approach could help in finding the optimal configuration of these parameters.
This video introduce genetic algorithms that we will see in the coming lecture
More details are available in the following book:
A second aspect that is missing is the notion of “deep learning” that is a particular way of dealing with backprogation of a neural network without the need of having a train dataset and using a larger set of layers. This will be material for the coming classes.
This is week 7 of AI1: Introduction to Neural Networks, link to the all material of the course: