Udemy
    •  
    •  
    •  
    •  
    •  
    •  
    •  
    •  
Turn what you know into an opportunity and reach millions around the world.
Learn More
Your cart is empty.
Keep shopping
Systems Engineering Neural Networks
Rating: 3.5 out of 5(14 ratings)
953 students

Systems Engineering Neural Networks

Machine learning with a "system" approach
Created byAlessandro Migliaccio, GIOVANNI IANNONE
Last updated 3/2023
English
English

What you'll learn

  • Understand the basic of machine learning
  • Set up a simple neural network
  • Understand the basics of systems engineering
  • Put machine learning in a system context

Course content

4 sections • 13 lectures • 30m total length

  • Introduction1:14

    Navigate a two-hour course on systems engineering neural networks, linking philosophy and technology, exploring machine learning in the system lifecycle, with applications, resources, exercises, and INCOSE certification references.

  • How Machine learning can improve your work.
  • The structure of the course1:47

    Explore the basics of machine learning, the system thinking approach, and the philosophy of artificial neural networks, with practical exercises to reflect on learning and apply to your own project.

  • Machine Learning overview4:15

    Explore how machine learning fits with neural networks within a systemic approach to modeling reality, covering deep learning, neural networks, and the role of weights, biases, and transfer functions.

  • What are neural networks used for?
  • What problems neural networks can solve?
  • The essence of the system approach1:37

    Master complexity with systems engineering, applying risk management, verification and validation, and a clear system architecture that spans software and hardware components and AI interfaces.

  • Neural network and the system approach
  • Philosophy of Artificial Neural Network2:49

    Represent reality through neural networks by translating observations into mathematical laws to understand complexity and connect systems engineering, system architecture and modeling across the lifecycle.

  • Reflection

Requirements

  • College level education
  • An interest for systems engineering and AI

Description

Systems Engineering and Artificial Neural Networks? In appearance strange bedfellows, but deceitfully so. Over our lives, we spend a long time thinking about making the right decisions, but we hardly stop and think about how we do it. We do know that our brain processes millions of data simultaneously, and sometimes we do not even realize that a “synaptic journey” has taken place. Every day, we deal with problems that can be seen as optimizing complex “systems”.

According to IBM “Machine learning is a branch of artificial intelligence (AI) and computer science which focuses on the use of data and algorithms to imitate the way that humans learn, gradually improving its accuracy.”

Naturally, this short course cannot cover all the contents of the reference material, but will cover the key topics such as the definition and engineering of neural networks. Then it will progress to the system thinking approach, with questions to help you reflect on what you have learned and apply what you've learned to your own project. So what do you need to follow this course? Thirst for knowledge, resourcefulness because the subject is complex, and it requires you to be proactive and go online to fill the gaps by reading articles and other resources, and even follow other online courses on the same topic. And of course, a great deal of patience because, as said, the subject requires some time to be fully mastered.


Who this course is for:

  • Students
  • Programmers
  • Engineers
  • Professionals

Report abuse