Machine Learning and Deep Learning are considered cutting-edge techniques to achieve a deeper understanding of real-world problems, finding new patterns and relations and converting data into actionable insights. These techniques can be used to build systems to support decision making, predict maintenance of equipment or automate the visual inspection of production outputs, delivering tangible solutions with a short-term impact.
> Professionals starting or consolidating a career as Data Scientists, Data Analysts or Machine Learning Engineers;
> Professionals from Engineering, Informatics, or related fields, looking forward to learning more on how to use Machine Learning tools to develop predictive models, make automatic classifications and categorizations and support decisions;
> Students from the areas of Engineering, Informatics, or related fields interested in complementing their training on Machine Learning methods or in following a future career as Data Scientists.
> Deepen the knowledge in Machine Learning and Deep Learning;
> Enable participants to experiment with machine learning and deep learning methods through hands-on exercises;
> Get acquainted with open-source tools (either publicly available or developed at Fraunhofer Portugal AICOS), so that knowledge can be applied immediately;
> Prepare participants to employ machine learning and deep learning methods on their own projects.
> Introduction to Machine Learning
> Data Gathering, Cleaning and Preprocessing
> Main Unsupervised Learning methods
> Unsupervised Learning Exercise with Python
> Main Supervised Learning methods
> Supervised Learning Exercise with Python
> Introduction to Deep Learning
> Supervised Deep Learning
> Unsupervised Deep Learning
> Exercise in Keras
Registration is done online at registration-form.
> 150€ for students
> 300€ for professionals
Classes will take place online and have between 10 and 30 students. Registration is only confirmed after payment is done by bank transfer to the following account PT50 0035 0328 0001 9909 5308 9. In the unlikely case that not enough registrations are received, we will reimburse all prospective students who registered. If you have any questions, please email email@example.com.