What is AI & Deep Learning?

MV.MINDNET - Deep Learning Platform from MABRI.VISION

What does artificial intelligence mean?

The term artificial intelligence (AI) or AI (artificial intelligence) is not clearly defined.
A definition fails simply because the concept of intelligence is not clear. The term artificial intelligence (AI) was created in the 1950s and is therefore historically shaped and subject to many influences.
The term reflects the vision and the "big picture". AI touches on several technical and scientific disciplines and is often used (including by us) as a catchy marketing term. When people talk about AI in measurement technology or image processing, they usually mean machine learning (ML, machine learning) or "deep learning" (DL, deep learning).
The terms build on each other as follows. Artificial Intelligence (AI) Machine Learning (ML) Deep Learning (DL)

 

Historical course

Although artificial intelligence is often referred to as a trend, it is by no means a new phenomenon. As early as the 1950s, scientists shared the belief that the process of thinking is not limited to the human brain. After research on the topic stalled, especially in the 80s, technology companies like Google gave the field a new boom in the 2000s. Today artificial intelligence is an integral part of our everyday life.

What does machine learning (ML) mean?

In image processing, there are basically two different ways to deal with a problem:

Rules based programming

  • Manual formulation and programming of rules after the results are calculated or defined

Machine learning

  • Train a model on data
  • Independent learning of patterns from the data
  • Classifying or estimating result quantities

Which approach is better depends on the application and must be carefully assessed or systematically determined. Rule-based approaches, especially in measurement technology and image processing, are well suited to making decisions based on clear measurement features and rules. If the rules are not known or can only be systematically extracted from images with great effort, a machine learning process may be the better approach. Machine learning processes are typically used in image processing for difficult segmentation tasks, in character recognition (OCR / OCV), pattern and anomaly recognition, object and image recognition and image classification. In modern applications, both approaches are usually combined in a meaningful way.

Machine learning (ML) learning techniques

Roughly speaking, there are 3 different learning methods for machine learning.

Deep learning vs. machine learning

Modern AI applications are based almost exclusively on deep artificial neural networks (ANN). The special thing about the networks is that they can also perform complex tasks and manual feature extraction can be completely dispensed with. An ANN is therefore able to independently perform complex tasks.

  • Deep learning is a branch of machine learning
  • DL methods are based on artificial neural networks with several intermediate layers

Artificial Neural Networks (ANN)

Deep learning methods are based on artificial neural networks.
These networks are inspired by the (biological) neural networks, i.e. part of a nervous system. Artificial neural networks are built in layers. A layer or level consists of several artificial neurons. There are several hidden levels between an entrance and exit level. The structure is given the name "deep" neural network because of these hidden levels.

Convolutional Neural Network (CNN)

So-called "convolutional neural networks" (CNN) are mostly used in image processing. These networks, inspired by the visual cortex, are made up of several feature maps. These feature maps correspond to the levels of an artificial neural network and are generated by convolution. The convolution operators produce different characteristics / features, such as edges. In image processing, a CNN should be able to generalize features and represent them in ever higher abstraction lines.

Source: LeCun, Yann, et al. “Gradient-based learning applied to document recognition.” Proceedings of the IEEE 86.11 (1998): 2278-2324

Source: Lee, Honglak, et al. “Unsupervised learning of hierarchical representations with convolutional deep belief networks.” Communications of the ACM 54.10 (2011): 95-103.

MV.MINDNET, the deep learning platform from MABRI.VISION, combines the latest technology and practice-oriented solutions.

Why MABRI.VISION

MABRI.VISION builds and develops high-quality machine vision solutions and modular inspection systems for your production processes. Our modular system enables us to provide solutions for your inspection tasks quickly and efficiently.

Innovative solutions - our passion!

Innovative solutions - our passion!

Innovation is the foundation for continuous growth in modern industry. At MABRI.VISION we live this anew every day. The focus is always on the benefits and requirements of our customers. We are passionate about implementing inspection processes that range from AI-based computer vision solutions to 100% inline component measurement for sophisticated products. We use the latest generations of the most advanced technologies for our measurement technology. With this philosophy we want to make production processes more efficient and dynamic.

AI, processing, control - one software platform

AI, processing, control - one software platform

With the goals of Industry 4.0 and a continuous improvement process, the demands on inspection automation, interfaces and efficient evaluation algorithms are increasing. We at MABRI.VISION have recognized this trend and are going one step further. Our software team develops modular software platforms that combine all the components of modern inspection systems. If necessary, we can expand evaluation algorithms with neural networks, map fast interfaces to system controls and integrate audit trails, batch reports, progress graphs or databases as required.

A strong team, always there for you.

A strong team, always there for you.

As our customer, you are always at the forefront. Our team of experts in vision, construction, software development, electrics, assembly and support is always there for you. With modern company processes and IT solutions, speed is a key goal. With our service solutions through to 24/7 support, we support your production with efficient solutions.

End-to-end solutions, everything from a single source.

End-to-end solutions, everything from a single source.

You think in terms of processes, we think in terms of solutions: that's why we offer our customers turnkey inspection systems that can be seamlessly integrated into your production processes. Our experts advise on planning and design at the beginning of a project. If technologies need to be evaluated, we carry out feasibility studies and inline tests. At MABRI.VISION we offer system construction, programming and automation from a single source. We can optimize complex evaluations and inspections directly with the system control and all customer interfaces.

Contact.

Do you need more information about a specific product or application? Use the MABRI.VISION contact form below or call us.