fr
en
Practical introduction to deep learning and its architectures
Deep learning becomes usable when you understand the choices that influence its results. Connect architectures, data and training to analyse model behaviour. Develop reference points for designing experiments and evaluating performance rigorously.
- Duration
- 3 days 21 hours
- Code
- FC-FDL Code
Presentation
In data science and artificial intelligence, deep learning is a set of AI design methods. As part of newer machine learning approaches, this methodology involves creating algorithms that are highly versatile and capable of learning autonomously.
This level 1 deep learning course provides the skills needed to become familiar with different deep learning methods. These are now widely used to process images, text, audio and sequential data.
By the end of the deep learning course, you will understand the fundamental principles of deep learning models and be able to design your own models and train them effectively.
Objectives
After completing the deep learning course, you will achieve the following learning objectives:
- discover and master the principles of deep learning algorithms and their configurations;
- configure the structure of a deep learning model or create one from scratch.
Program
Deep learning basics
- Review and explanation of Python for deep learning.
- Presentation of deep learning and its current applications.
- Description of an artificial neural network system (the perceptron model).
- Definition of gradient-based backpropagation.
- Definition of a convolutional neural network.
- Good practices for optimising deep neural networks.
Recurrent neural networks
- Presentation and analysis of recurrent neural network structures.
- Presentation of LSTM and GRU cells for optimising internal structure.
Generative deep learning models
- Description of an autoencoder (autoassociator).
- Description of generative networks (GANs).
Audience
This course is intended for:
- IT professionals, such as data analysts and digital development managers;
- data scientists wishing to specialise in deep learning;
- project managers or managers wishing to specialise in data management and learn more about the importance of data;
- IT professionals wishing to learn or acquire new skills in Big Data and artificial intelligence technologies.
Prerequisites
The deep learning course requires the following prerequisites:
- sound knowledge of mathematics or data science;
- the ability to work with a programming language, particularly Python.
Teaching and assessment methods
- Initial skills assessment
- Training materials provided to participants
- Continuous assessment throughout the course
- End-of-course feedback questionnaire
- Combination of theory and practical application
- Attendance records
- Post-course follow-up evaluation
- Practical exercises
- Case study
Course highlights
Theoretical and practical training delivered in person or online; learning materials; labs covering various real-world use cases and rapid skills development.
Dates and sessions
Choose the date and delivery format that suit you.
No upcoming sessions are currently available.