| Author: | Francesco Lelli |
| Learning Line: | What is a Perceptron and how you can use it |
| Course: | AI1: Introduction to Neural Networks |
| Week: | 2 |
| Competencies: | Understand and implement a Perceptron |
| BoKS: | 3aK1 The student understands a supervised learning process and its components. She knows how to apply such a strategy in a specific (business) context. |
| Learning Goals: | Getting familiar with the notion of Perceptron and how you can use it |
In a 1958 press conference organized by the US Navy, Rosenblatt made statements about the perceptron that caused a heated controversy among the fledgling AI community; based on Rosenblatt’s statements, The New York Times reported the perceptron to be “the embryo of an electronic computer that [the Navy] expects will be able to walk, talk, see, write, reproduce itself and be conscious of its existence.
Unfortunatelly it was quickly proved that perceptrons could not be trained to recognize many classes of patterns
Nevertheless perceprons are the basic building block of neural networks. In short, they are algorithms for supervised learning of binary classifiers. A binary classifier is a function which can decide whether or not an input, represented by a vector of numbers, belongs to some specific class
This video presents the perceptron, a simple model of an individual neuron, and the simplest type of neural network. The manner in which perceptrons define a linear decision boundary is shown, as well as the mechanics of the perceptron learning algorithm.
This video present a more practical view on how you can use a perceptron and when a non linear approach is more appropriate then a linear one. In short, why it is useful!
Back-propagation calculus
You are also invited in getting familiar with the following code:
We will discuss it in detail during the classes
This is week 2 of AI1: Introduction to Artificial Intelligence, link to the all material of the course: