DATA SCIENCE MASTER

Start by learning the coding fundamentals in Python. You will understand Object Oriented programming and confidently work with Python data structures: lists, dictionaries, sets, tuples, and more.

• Introduction to programing: Basic coding concepts.
• Variables, loops, sequences. Code Editor: Visual Studio Code.
• Functions and complex data.

• File management and parsing.
• Introduction to orientation to objects.
• Modules and external libraries.

Introduces the basic concepts in Artificial Intelligence (AI) and the basic mathematical concepts in algebra and statistics that are key to understand the rest of the topics in the course.

The module starts with the basic concepts in AI, history, evolution and state-of-the-art in AI, together with customer examples.

Finally the key concepts in algebra and statistics will be taught with the focus on its applications to AI.

• Introduction and key mathematical concepts for AI.
• Linear Algebra.

• Probability and Statistics for Machine Learning.
• Exploratory analysis (correlation, variance analysis, descriptive statistics).

This module covers the key libraries in Python and the basics in R.

The module consists in learning data access, preprocessing and exploratory analysis to understand the content of the data.

The focus for Python will be around variables, simple data structure, conditional lists, dictionaries and functions with the focus in analysis and cleaning of data.

• Data manipulation and Analysis (databases, sql, no sql, apis, webservices, scripting).

• Data preprocessing (cleaning and manipulation). Main libraries in Python y R (panda, numpy).

We ill cover the visualization of data using Python and R libraries. The main libraries will be used together with a grafo visualization.

This module also includes 3D graphics and how to create them with Python.

At the end of the module additional knowledge will be provided around key open source and commercial tools which do not require programming.

• Visualization introduction and Graph analytics.
• Maps & Time Series.

• Comercial and opensource data visualization tools.

We will cover supervised learning. This type of learning requires human intervention for the creation of labels in the historical data.

In this way the machine will be able to predict a result based on this data.

An industry case will be developed to apply your knowledge.

Classification:

• Probabilistic model (Naive Bayes & Logistic Regression)
• K-NN , Decision trees & Random forest
• Linear and non-linear regression.
• Resampling Methods, cross validation.
• Overfitting & Bias.

Applying classification techniques for a Health data set.

We will cover the unsupervised machine learning methods which focus on historical data that have not been labeled. The objective is to find patterns and structures hidden in the data. A common example is the customer segmentation with similar attributes for marketing campaigns.

In this module the main techniques of unsupervised learning will be used with special focus on clustering, dimensionality reduction and association rules.

• Introduction to Unsupervised. Clustering and latent variable models.
• Dimensionality reduction and Anomaly decision.

Applied dimensionality reduction and its effect on the classification techniques.

You will learn the basic principles of Deep Learning together with the knowledge of key algorithms. You will understand the concept of a neural network and the behaviour of data when applying these kind of methodologies.

We will go over the Densely Connected Network, convolutional neural network (CNN) and recurrent neural network (RNN).

You will learn about the unsupervised neural network and the autoencoder concepts, GANs and Boltzman machines.

• Deep Learning introduction.
• How to build a neural network.
• Densely connected network.

• Convolutional neural network (CNN).
• Recurrent neural network (RNN).
• Reinforcement learning.
• Generative Adversarial Network (GANs).

The last module encompasses the life cycle of AI in real projects. From the access to data, preprocessing and analysis training to its deployment in production.

Additionally, trendy topics in AI will be included in this module such as ethics, regulation and the future challenges.

Finally, this module examines the key tools in the market around AI with a focus in the life cycle usage.

• AI life cycle.
• Biases, regulation and future trends.

• AI commercial frameworks (IBM, BIGML...).