Introduction to Deep Learning

At the end of the course, you will earn a Certificate of Completion from Spirit in Projects.

Do you enjoy analytical thinking, have a keen interest in algorithms, data and neural networks, and wish to explore the vast potential of Deep Learning? If you’re curious about the latest advancements in this fascinating field, then this training is just the right opportunity for you. Together, we will teach systems to perform tasks automatically and throughout the course we will design and implement functions to bring these ideas to life.

Advising

Objectives

  • Understand methods of machine learning
  • Learn the structure and functioning of neural networks
  • Apply deep learning for training neural networks
  • Understand and implement applications in pattern recognition, image and text processing, and object detection
  • Utilize tools and platforms for deep learning

Target groups:

Business Analyst, Requirements Engineer, Usability Expert, Scrum Master, AI Expert, Project Manager, Project Director, Demand Manager, Portfolio Manager, IT Project Director, Test Manager, Tester, Test Automation Specialist, Test Engineer, Enterprise Architect, System Architect, Software Architect, Software Designer, Software Developer, Product Owner and for all who are ready to explore the possibilities.

Show dates and times

Syllabus

1. Understanding machine learning and AI 

  • Defining machine learning (ML) 
  • Difference between ML, AI and data science 

2. Exploring methodologies 

  • Key differences from traditional software development 
  • Core components of machine learning  

3. Prerequisites for effective machine learning  

  • Data requirements 
  • Predictability criteria 

4. Learning approaches in machine learning

  • Supervised learning
  • Unsupervised learning
  • Reinforcement learning

5. Model types in machine learning 

  • Decision Tree
  • Neural Networks
  • Regression analysis

6. The essence of deep learning 

  • What is an artificial neural network? 
  • Deep Learning and its benefits  
  • Simple deep neural networks 
  • Convolutional neural networks (CNNs) 
  • Generative adversarial networks (GAN) 
  • Transformer models 

7. ML platforms and technologies 

  • Google TensorFlow
  • Meta Pytorch
  • Repositories
  • Programming languages for machine learning 

Advising after course completion

Spirit in Projects