We Are Here To Help You With Any Questions You May Have
Deep Learning is a subfield of machine learning concerned with algorithms inspired by the structure and function of the brain called artificial neural networks.
If you are just starting out in the field of deep learning or you had some experience with neural networks some time ago, you may be confused. I know I was confused initially and so were many of my colleagues and friends who learned and used neural networks in the 1990s and early 2000s.
The leaders and experts in the field have ideas of what deep learning is and these specific and nuanced perspectives shed a lot of light on what deep learning is all about.
The quickest way to understand a machine vision system is to think of it as the ‘eyes’ of a machine. The process begins when a sensor detects the presence of a product. The sensor then activates a light source to illuminate the area and a camera to capture a razor-sharp image of the product or a part of the product. The camera, the eyes, captures digital input to determine actions.
Industry 4.0 companies use machine vision systems in different ways to improve quality, efficiency and their industrial processes.
An AI edge device has a microprocessor onboard used to process given data using a deep learning pipeline. The asset of on edge device is that it generates and processes the data onboard and only sends desired data to the end-user. Therefore, using less bandwidth and latencies compared to cloud solutions. The data used in our case is generated by professionally selected camera hardware.
Be aware! Camera hardware is not only a camera sensor, it also includes the right lens and lighting.
ATEX is an acronym for ATmospheres EXplosible. This means hazardous, or potentially explosive, environments of various categories, both gaseous (petrochemical mainly) and dusty such as flour mills, sawmills and some food processing plants.
AeyeQ offers the Augur ATEX camera that solves the challenge of including Deep learning in explosion sensitive areas.
Our hardware provides data to the software instead of images.
In general, TOPs (Tera Operations Per Second) reflect the maximal performance/throughput of a chip designed for Neural Network Inference. Be aware, more TOPs is not always related to more throughput. A lot depends on the image size and batch size used. Moreover, assigned RAM memory as important as the number of TOPs.
Augur, in ancient Rome, one of the members of a religious college whose duty it was to observe and interpret the signs (auspices) of approval or disapproval sent by the gods in reference to any proposed undertaking.