Bonus – Python code. Code for a simple McCulloch-Pitts neuron. Programming logical operator with McCulloch-Pitts neurons. Building a flexible perceptron with several activation functions.

Part 4 – Activation functions. Mathematical definitions of several types of activation functions. Recap of the lecture.

Part 3 – Early neuronal model: Rosenblatt’s perceptron. Intro to the work of Frank Rosenblatt. Definitions: supervised vs. unsupervised learning. The perceptron convergence theorem. First practical learning paradigm. Decreasing our mistakes. Learning as optimization: gradient descend. Vintage example: The perceptron performing face recognition.

Part 2 – Early neuronal model: The McCulloch-Pitts neuron. A brief introduction to both Warren McCulloch and Walter Pitts. Description of the biological inspiration of for the McCulloch-Pitts neuron. Mathematical description of the McCulloch-Pitts model and how it is use to process information. Implementing Boolean logic using the McCulloch-Pitts model. Limitations of the model.

Part 1 – Introduction. In the first introductory part, we talked a little bit about some historical developments of artificial intelligence. Particularly, we talked about some competitions between man and machine with examples from chess with Garry Kasparov playing against Deep Blue and the Chinese game of GO in which Lee Sedol playing against an…

Introduction: How many of us have been both dazzled and confused when we were shown an ingenious optical illusion? If you are anything like me it might initially bring surprise and childish emotions of wonder and almost magic, but in a second and more reflective moment you might then wander how did that happened? Can…