Deep Learning with Python

Course description:

The course aims to introduce participants to the world of deep learning, using the Python programming language and the TensorFlow library. The course explores fundamental concepts of neural networks, such as activation functions, parameter optimization, and prevention of overfitting.

Participants will learn to build and optimize deep learning models, as well as apply them in practical situations. The course also covers ways to reduce overfitting and put into practice the knowledge gained to solve classic problems in the field of machine learning.

Prerequisites:

Basic programming knowledge in Python (data structures and flow control).
Fundamentals of linear algebra and differential calculus.
An understanding of fundamental machine learning concepts.
Experience with Python libraries for machine learning, such as NumPy, Pandas, and Scikit-learn.
Basic knowledge of neural networks.

Who is it for:

The course is aimed at IT professionals, researchers, students and enthusiasts interested in deep learning and developing solutions based on neural networks. Previous knowledge of Python programming and machine learning is an advantage, but not mandatory. The course is suitable for those who want to delve deeper into the field of artificial intelligence and understand how deep learning techniques can be applied to solve complex problems in a variety of fields, such as data analysis, image recognition, natural language processing, and other related fields.

What will you learn:

The concept and functioning of neural networks and their theoretical basis.
The main concepts and terms used in the context of neural networks.
Strategies and techniques for optimising the parameters of neural networks to achieve the desired performance.
Use of Tensorflow framework and practical application for building a neural network-based application. Various methods for reducing overfitting and their importance in the context of neural networks.
How to apply the knowledge gained in the course to solve practical problems related to neural networks.

Course module structure

• What are neural networks and what underlies them
• Basic concepts of neural networks
• How to optimize parameters of some neural networks
• Getting to know Tensorflow and making a practical application
• Main ways to reduce overfitting
• Putting into practice the accumulated knowledge

Certification:

Certificate of completion.

€ 840

DURATION: 2 days
SKILL LEVEL: Associate
LECTURES: 6 lessons

Course description:

Prerequisites:

Basic programming knowledge in Python (data structures and flow control).
Fundamentals of linear algebra and differential calculus.
An understanding of fundamental machine learning concepts.
Experience with Python libraries for machine learning, such as NumPy, Pandas, and Scikit-learn.
Basic knowledge of neural networks.

Who is it for:

What will you learn:

The concept and functioning of neural networks and their theoretical basis.
The main concepts and terms used in the context of neural networks.
Strategies and techniques for optimising the parameters of neural networks to achieve the desired performance.
Use of Tensorflow framework and practical application for building a neural network-based application. Various methods for reducing overfitting and their importance in the context of neural networks.
How to apply the knowledge gained in the course to solve practical problems related to neural networks.