Artificial Intelligence and Machine Learning algorithms are involved in a vast variety of scientific and industrial projects, contributing to the solution of the emerging problems, from data modeling and analysis to face recognition and self-driving cars. In recent years, researchers and professionals have been engaging with artificial intelligence algorithms because they have been successfully deployed in an unusually wide range of Scientific, Technological and Business fields. Regardless of the database, their basic function is accomplished by a mathematical model describing the interactions of the variables. The relationship between independent and dependent variables is often non-linear and complex, and mathematical models are aiming at forming a generalized relationship. Their success depends on the mathematical formulation and the underlying theory, the algorithmic application, the prediction errors, as well as the generalization of the results.
- Introduction to Artificial Intelligence
- Mathematical Simulations (Inverse Problems, Interpolation Methods. Radial Basis Functions).
- Forecasts with statistics & machine learning.
- Computational analysis of text & scientific bibliography.
- Analysis of subjectivity & meaning in text.
- Regression Analysis (Linear & Nonlinear Regression. Logistic Regression. Stepwise Simulations and Promotion of Variables from Beginning and End).
- Regression analysis:
- Data Preparation, Normalization, Outliers.
- Multiple variable models. Geometric representation.
- What is a linear model and why is it widely used. Limitations.
- Model Results, R ^ 2. Coefficients, weights, p-values.
- Residuals Analysis, Heteroscedasticity, Biass.
- Significance of Variables & Importance.
- Non-linear regression
- Training, verification & test sets
- Artificial Neural Networks
- Supervised Learning, Generalized Simulations. Representation & Introduction to Learning Algorithms.
- Error Metrics & Quantitative Criteria.
- Network over-fitting and over-learning.
- Sensitivity analysis
- Simulation evaluation and interpretation of results.
- Influence of each independent variable on the dependent, keeping constant the other at median, and 25-75% percentiles.
- Conceptual interpretation of the model and conclusions.
- Special Topics
- Alternative regression methods (Ensembles, k-nearest neighborhoods, etc.)
- Optimization algorithms. Introduction to heuristics, genetic, evolutionary, global search.
- Clustering algorithms
Who Should Attend
- professionals who work on data analytics, predictions, and relevant topics
- researchers who want to analyze scientific databases with contemporary machine learning techniques
- anyone interested to understand the fundamental assumptions and hands-on implementation of machine learning algorithms
- introduction to the theoretical background of machine learning
- learn from examples regarding industrial and academic test cases
- transition from explicit statistics to state of the art, non-linear, generalized models
- the course will be held online, via an electronic platform
- the final schedule will be announced soon
- fill in the form below today and gain 50%, early-bird discount. No commitment, you can cancel anytime.