• Services
    • Scout it
      • Business & strategy
      • Technology management
    • Invent it
      • Proposition management
      • Feasibility & IP development
    • Create it
      • Strategic design
      • Demonstrators & prototypes
    • Scale it
      • Go-to-market
      • Industrialization & production
    • Fund it
  • Solutions
    • MyStartUp
    • MyFutureProduct
    • MyInnovationFactory
    • MyTalent
  • Markets
    • Smart city, home & mobility
    • Smart FMCG & consumer
    • Smart industry & chemicals
    • Smart life sciences
    • Smart space & security
  • Technology
    • Robotics & autonomy
    • Cooling, heating & fluidics
    • IoT & smart sensors
    • Technology portfolio
  • Labs
    • Strategic innovation
      • InnoLab
      • DesignLab
      • OpenLab
    • Digital innovation
      • AILab
      • DigitalLab
      • EmbeddedLab
    • Product innovation
      • FabLab
      • MechLab
      • PhysicsLab
      • OpticsLab
  • Insights
    • Perspectives
    • Webinars
    • Blog
    • Trainings
    • Innovation Day
    • Awards
  • About
    • Who we are
    • Companies
  • News
  • Contact
  • Jobs
Verhaert Masters in InnovationVerhaert Masters in Innovation
Verhaert Masters in InnovationVerhaert Masters in Innovation
  • Insights
        • Inspiration to innovate

        • Webinars
        • Blog
        • Perspectives
        • Toolboxes
        • Awards
  • Offering
        • Services

        • Your innovation highway

        • Funding

        • Your gateway to funding

        • Solutions

        • Your integrated innovation blueprint

        • Scout it
          • Business & strategy
          • Technology management
        • Invent it
          • Proposition management
          • IP management & feasibility
        • Create it
          • Strategic design
          • Demonstrators & prototypes
        • Scale it
          • Go-to-market
          • Industrialization & production
        • Subsidy applications
        • MyStartUp
          • Boost your venture
          • Find your incubation program
        • MyInnovationFactory
          • Adjacent innovation for corporates
        • MyInnovationTalent
          • Boost your innovation talents
        • MyFutureProduct
          • Make your product smart & future-proof
  • Markets
        • Smart Space & Security

        • Microgravity
          Earth observation
          Navigation
          Exploration
          Security
        • Smart FMCG

        • Dispensers
          Cooling & heating
          Servers
          Smart packaging
          Vending equipment
        • Smart Life Sciences

        • MedTech
          BioTech
          HealthTech
          Ophthalmic
        • Smart Industry

        • Mobility & logistics
          Chemical & material
          Home, building & construction
          Manufacturing & equipment
          Energy
  • Capabilities
        • Strategic innovation

        • OpenLab
        • DesignLab
        • InnoLab
        • Digital innovation

        • DigitalLab
        • EmbeddedLab
        • AILab
        • Product innovation

        • MechLab
        • PhysicsLab
        • FabLab
        • High-tech innovation

        • OpticsLab
  • Technologies
        • Technologies to boost your innovation

        • Technology portfolio
        • IoT & sensors
        • Robotics & autonomy
        • Cooling, heating & fluidics
  • About us
        • Independent pioneering European innovation factory

        • News
        • Who we are
        • Companies
  • Jobs
  • Contact

The difference between Machine & Deep Learning

12 August 2020 Posted by Jochem Grietens Digital innovation, Perspectives

What’s the difference between Machine Learning & Deep Learning? And when to choose one or the other?

Banner - Perspective - The difference between Machine & Deep Learning


More classical Machine Learning techniques often require feature engineering. This means that someone uses their knowledge to list relevant features in the data. The upside is that you need less data because you utilize expert knowledge, the downside is the additional work and risk of no creating the right features. These features are then fed to the Machine Learning algorithm for training. The more features you select, the more computational power you need. If you don’t have unlimited power, consider the following:

  • Use as few features as possible.
  • Focus on minimum redundancy of features yet maximum relevance in the output (Correlation Based Feature Selection).
  • Good feature subsets contain features highly correlated with the classification, yet uncorrelated to each other (Correlation Based Feature Selection).

Visual - Difference machine and deep learning 1

Deep Learning is a more advanced technique within Machine Learning. It needs larger data sets and more computation power, but it offers automatic improvement and a high accuracy level.

In Deep Learning the task of finding relevant features is part of the algorithm and is automated. Deep Learning requires more data but less a priori knowledge and searches for the most optimal features, whereas with feature engineering we can not assume that the features are optimal.

In the example below, a Machine Learning algorithm detects a car from a picture. The algorithm learns from analyzing lots of car images marked as ‘car’ and other images marked as ‘not car’. Next, you can show other pictures to your algorithm and it will tell you if it’s a car or not. The example shows an additional feature extraction step for the feature-based “Machine Learning” that has to be performed by experts and programmers. The Deep Learning algorithm clearly incorporates that into its neural network.

Visual - Difference machine and deep learning 2

However, the algorithm won’t tell you how it came to its conclusion. You can test the algorithm to see if it consistently gives the right answers and after that you can decide to trust it or not. This process of validation is an important one and should be performed with care.

This is very similar to teaching a human to execute a task: you teach, test and give a diploma that says ‘this person has got this task covered’. You don’t analyze how their brain translates the question into the answer.

There are techniques that attempt to visualize how a Deep Learning algorithm interprets images in its internal workings, as shown below. It’s like trying to “read the mind of the neural network”. Visual - Visualization deep learning algorithm

Source: Medium.com


Download the perspective

Tags: Artificial intelligenceMachine & deep learning
Share
4

About Jochem Grietens

Coordinator AILab

You also might be interested in

The perfect brew. The perfect serve. The perfect product.

The perfect brew. The perfect serve. The perfect product.

Dec 1, 2021

In this webinar we discuss further premiumization & personalization of products & how AI will help identify the unidentified parameters.

Visit us at Advanced Engineering 2022, join our keynote session or book a meeting

Visit us at Advanced Engineering 2022, join our keynote session or book a meeting

Apr 22, 2022

Digitally-driven business model innovation will become the new battleground, putting[...]

Machine learning as catalyst for learning robots

Machine learning as catalyst for learning robots

May 19, 2021

In robotics 3 key challenges are addressed with AI: perception, planning and navigation, and robot control.

OTHER CONTENT
  • Tackling 3 big hurdles of digital transformation in the logistics industry
  • Intrapreneurship as an innovation strategy
  • Organizing a scalable engine for innovation
NEWSLETTER



Verhaert Masters in Innovation is a pioneering innovation group helping companies and entrepreneurs to innovate, creating new products, businesses and services.

Verhaert icon LinkedIn Verhaert icon Facebook Verhaert icon SlideShare Verhaert icon YouTube Verhaert icon Twitter

SERVICES
SOLUTIONS
MARKETS
TECHNOLOGY
LABS
ACADEMY
ABOUT
NEWS
JOBS
CONTACT

© 2022 Verhaert New Products & Services NV • BE 0439.039.420 • Privacy policy • Terms of use

Prev Next