Filter

Introduction to machine learning

Machine Learning has seen a tremendous growth in recent years. The ever increasing amount of information collected by enterprises and organisations has emphasized the need to create intelligent software built on top of the collected data.

The use of neural networks and deep learning has been a major contributor to the success in this new field of software development. Historical data is used to train models that learns to identify complex patterns which can be used to analyse future events.

The fast development in this area has created a vast amount of possibilities for enterprises and organisations to create innovative solutions that solves and automates complex tasks. Today, machine learning is applied in numerous applications ranging from translation of text, classification of fraud and self driving cars.

In this course you will get a practical introduction to the field of neural networks. You’ll learn theory, potential use cases and how to implement neural networks in code. During this course you will receive a practical introduction to machine learning and an understanding of a very exciting field that keeps growing faster and faster.

You will learn

  • Theoretical introduction to neural networks and their use cases
  • Implementing neural networks
  • Tensorflow - one of the largest frameworks for machine learning
  • Introduction to a wide range of tools used in machine learning

Software used

The course primarily uses Python, Tensorflow and Jupyter

Setup

The course mixes theory with practical implementations. As the course is finished you will receive a copy of all course materials.

    Target audience

    Programmers that is looking for a introduction to machine learning.

    Prerequisites

    You should be comfortable programing. The course uses Python but previous experience with the language is not required.

    Course summary Introduction

    • Introduction to machine learning
    • Introduction to supervised, unsupervised and reinforcement learning
    • Regression & classification using machine learning
    • Loss functions & gradient descent

    Tensorflow

    • Introduction to Tensorflow

    Neural networks

    • Introduction to neural networks and their applications
    • Layers, neurons, activation functions and regularisation
    • Transfer learning

    Image analysis using Neural Networks

    • Introduction to convolutional neural networks
    • Image classification using neural networks
    • Sliding-window and object-detection

    Neural networks and text analysis

    • Introduction to Natural Language Processing(NLP)
    • Representing text in neural networks
    • Semantic analysis using neural networks

    Related articles

    • New courses this spring

      Now we are launching 5 new courses! Machine learning, React, Docker, Scrum or .NET no matter what you want to broaden yourself in, we have it.

      Read more

    Course info

    Course code: T101
    Duration: 2 days
    Price: 21 500 SEK
    Language: English Swedish

    Course schedule

    Gothenburg
    10 DecBook now
    Stockholm
    17 SepBook now
    Malmö

    Teachers

    Niklas SilfverströmNiklas Silfverström

    Share

    Contact us for details

    +46 40 61 70 720
    info@edument.se


    All prices excluding VAT