This training is a continuation of a workshop on “Machine learning” prepared by Prof. Tomasz Górecki, PhD, AMU. Deep learning is one of the fastest growing branches of artificial intelligence. It involves the creation of neural networks. A neural network is a huge number of processors connected to each other and working simultaneously. Each of them has access to local memory and is fed with large amounts of data and information about the relationships between data. Basic applications of deep learning: speech recognition, image recognition, video processing, natural language processing, text translation, movie or book recommendation systems. The training is a live workshop with a progress check and an opportunity to ask questions. Upon completion of the workshop, participants will receive an electronic certificate of completion.

Date: to be agreed with the client (2-days online workshop).

Time: 10 hours (5 hours each day with a coffee break).

Location: online.

Group: for a group larger than 3 persons.

Teacher: Tomasz Górecki, Ph.D.

Price: 445 EUR (plus VAT if applicable).

Topics:

• H2O Library
• Automated Machine Learning Models (AutoML)
• Introduction to neural networks
• Introduction to deep neural networks
• Keras Library
• Convolutional neural networks
• Recurrent networks, in particular LSTM type networks

Learning Outcomes

After completing the course, the participant will:

1. Possess practical skills in using modern tools and methods for machine learning and neural networks with the R programming language.
2. Be familiar with the capabilities of the H2O library, enabling:
1. Implementation of advanced machine learning algorithms,
2. Work in local environments and large-scale Big Data ecosystems.
3. Be able to use AutoML tools for automatic model selection and optimization, improving efficiency when working with large datasets.
4. Understand the fundamentals of neural networks, including:
1. The history and applications of neural networks,
2. Principles of building classical neural networks.
5. Be proficient in selecting hyperparameters and effectively training models, forming a solid foundation for working with more advanced architectures.
6. Understand the structure of deep neural networks, including:
1. Types of layers,
2. Unique advantages that make them some of the most effective tools in data analysis and modeling.
7. Be able to use the Keras library, which allows for:
1. Quick and intuitive design and training of models,
2. Prototyping and deploying various types of networks.
8. Be capable of creating convolutional (CNN) and recurrent (RNN) models, including:
1. Convolutional Neural Networks (CNNs), essential for image processing,
2. Recurrent Neural Networks (RNNs), with a focus on LSTM architectures, which are used for sequential data analysis (e.g., text or time series).
9. Be able to independently design, train, and deploy machine learning models and neural networks.
10. Possess skills to solve complex analytical problems in various fields, such as:
1. Data analysis,
2. Image processing,
3. Natural language processing.

Tomasz Górecki, Ph.D., D.Sc., Associate Professor

Professor at the Department of Mathematical Statistics and Data Analysis at the Faculty of Mathematics and Computer Science of Adam Mickiewicz University in Poznań, Vice-Dean for grants and cooperation with business at the Faculty of Mathematics and Computer Science of Adam Mickiewicz University in Poznań. His scientific interests include time series analysis, functional data analysis and artificial intelligence. He also deals with applications of statistical methods and machine learning in practical problems. He has been teaching probability calculus, statistics, machine learning, and artificial intelligence for over twenty years. He cooperates with many companies in the field of machine learning and artificial intelligence (Lidl, OLX, PWN, Samsung, Smartstock). He has been using R language for many years (he is a co-author of two R packages and an author of a book on R language). He cooperates with employees of Colorado State University, University of Utah, Poznan University of Technology, Poznan University of Economics and Poznan University of Life Sciences.