You may have noticed that the slides of the last lecture (Neural Networks and Deep Learning) have been uploaded since Saturday night. I only wanted to point out that I added a few things here and there, as well as a simple example of iterative perceptron learning to indicate the difference between the perceptron example and the polynomial fitting example. In the first case, the model is fixed and we iteratively learn the parameters of the model, whereas in the second case, we change the model, gradually increasing the model complexity (the degree of the polynomial), showing the performance of the best parameters for each of these models. Check out all the material included therein and make sure to spend sometime on using the online ML playground to try different problems, data sets, features, hyperparameters, etc.