Deep learning is the driver of developments in the field of artificial intelligence. However, practical implementation often still lags years behind the scientific knowledge. There is therefore a lot of potential for a competitive advantage. TensorFlow 2 is by some margin the most popular framework in industrial development for deep learning and therefore the first choice.
Dates and Booking
-- Description
A Technical Overview with TensorFlow
-- Agenda
-
Introduction to neuronal networks with TensorFlow 2: Regression, classification, metrics, and regularization
-
Supervised deep learning: Applications of deep learning on structured data, image data, and time series
-
Unsupervised deep learning: Autoencoder and embedding
-
Deep reinforcement learning: Modelling, algorithms, and applications
-- Happy Participants
100% of all participants would recommend this training.
-- Your Benefits
Overview of the most important topics in the field of deep learning
Implementation of deep learning with TensorFlow 2
Gain the skills to develop neuronal networks
Learn to select the right form of deep learning and implement it
-- Audience
Developers, data engineers, data scientists. The course assumes an understanding of the fundamental ideas of machine learning and basic knowledge of the programming/scripting. Experience with methods of classic machine learning is helpful but not essential.
-- Training Objectives
Introduction to neuronal networks with TensorFlow 2
Supervised deep learning
Unsupervised deep learning
Deep reinforcement learning
-- Your Trainers
Oliver Zeigermann
Machine Learning und Frontend-Architektur
-- Technical Information and Books
Machine Learning – kurz & gut: Einführung mit Python, Pandas und Scikit-Learn
Der kompakte Schnelleinstieg in Machine Learning und Deep Learning O’Reilly, 2. Auflage, April 2021, zusammen mit Chi Nhan Nguyen ISBN: 978-3960091615
Machine Learning Lösungen entwerfen (Architektur-Spicker Nr. 10)
Machine Learning (kurz ML) wird häufig mystifiziert. Tatsächlich eröffnet es ganz neue Möglichkeiten. Dabei unterscheiden sich Herangehensweise und Werkzeuge deutlich von klassischer Softwareentwicklung. Dieser Spicker führt unaufgeregt in das Thema ML ein und weist den Weg in eigene Experimente. Download & Infos