Introduction to Deep Learning Training
Level
IntermediateDuration
40h / 5 daysDate
Individually arrangedPrice
Individually arrangedIntroduction to Deep Learning Training
Deep Learning is one of the essential parts of machine learning. It is based on artificial neural networks and creates algorithms that mimic the functioning of the human brain. With today’s vast amounts of data—from social media, search engines, e-commerce platforms, to streaming services like Netflix or HBO—there is a growing need for specialists who can process and analyze it.
What You Will Learn
- The fundamentals of Deep Learning and neural networks
- Types of deep learning and its applications, hardware platforms, programming environments, and cloud usage
- Basics of TensorFlow: structure, data types, data operations, Gradient Tape, and SGD
- How to build artificial neural networks with tf.keras, understand theory and practical modeling
- Skills in building fully connected networks, evaluating model quality, and tuning models
- Advanced Deep Learning techniques: low-level network building, regularization, TensorBoard, parameter analysis, TensorFlow callbacks
- Saving and loading models for practical use
Who is this training for?
People starting their journey with Deep Learning or wishing to expand their Data Science knowledge-
Programmers, data analysts, business analysts, marketers, designers, and anyone whose work can benefit from machine learning
Training Program
-
Introduction
- Types and possibilities of deep learning
- Hardware platforms and environments
- Cloud computing opportunities
- TensorFlow basics:
- Structure
- Data types
- Operations
- Gradient Tape
- Stochastic Gradient Descent (SGD)
-
Artificial Neural Networks with
tf.keras
- Theory and inspiration behind neurons and layers
- Flexibility of neural networks
- Types of neural network models
-
Modeling
- Building fully connected networks in
tf.keras - Solving simple problems
- Evaluating model quality
- Model tuning
-
Extension
- Low-level network building
- Regularization techniques
- TensorBoard
- Model parameter analysis
- TensorFlow callbacks
- Saving and loading models
