With this course, you will learn the basics of Deep Learning and learn how to build your own Neural Network from scratch. The training content creates the opportunity to work with different data types. Therefore, after completing the training, participants will not only have a solid theoretical background, but will also be able to practically apply what they have learned in real life.
TRAINING OBJECTIVES BASIC LEVEL
- To learn the basics of Deep Learning,
- To get general information about Artificial Neural Networks and how they work; to get information about how they are used in real life,
- Designing deep learning models with Python programming language,
- Understand Pytorch Tensors and more advanced Pytorch functions,
- To learn what needs to be considered in Data Science Projects,
- Baseline Model, Gradient, Sigmoid, Non-linearity, Regularization, Binary and Multi-Class Classification, Loss Function…
TRAINING CONTENT BASIC LEVEL
- PyTorch Basics
- Deep Learning Basics
What to look for when starting a data science project?
Why does the Gradient give the direction of maximum increase?
Neural Network basics – Everything can be thought of as a function
Seriously, why are we using this Sigmoid?
Add Non-linearity to the model and why is this necessary?
Why is a normalization model helpful when training?
Pulling inputs into the same logic space
Defining loss function
Loss function vs Metric – Loss
What is a batch and why does its size matter?
Binary Classification from 0
Multi-class classification from 0
- Those who have basic math and algorithm knowledge,
- Python is suitable for anyone with coding/programming knowledge.
To have knowledge of coding/programming in Python language.
Plan this training institutionally!
This training can be planned in different durations and content specific to your organization. Please contact us for detailed rich content and planning to realize your training objectives.