After the "Machine Learning ANN intermediate: Backpropagation"course it's time to put our knowledge in practice with image recognition. Together with Recurrent Neural Networks, ConvNets are the real tools you will use. We will learn its parts and public libraries you can use.

After the "Machine Learning ANN intermediate: Backpropagation"course it's time to put our knowledge in practice with handwriting and speech recognition . Together with Convolutional Neural Networks, RNNs are the real tools you will use. We will learn its parts and public libraries you can use.

This is an intermediate course where, using what we learnt on the "Machine Learning Introduction to ANN" course, we will extend our knowledge of learning algorithms programming Backpropagation and several of its optimizations. For this course the students need to not be scared of partial derivatives and statistical errors. Is a "mathsy" course.

This is an introductory course. With a practical example the participant will learn what is an Artificial Neural Network and what means to "learn" on this environment as well as the importance of feature selection and an introduction to Genetic Algorithms. No need for mathematical experience and only basic coding skills needed.

This is an introductory course. With a practical example the participant will learn what a Recomender System does, which is it's goal and an overview of the several main approaches you can take. No fear for mathematical tools needed since we will work with matrix operations,but no need of previous knowledge and only basic coding skills needed.
