Neural Network: Difference between revisions

From Tygron Support wiki
Jump to navigation Jump to search
← Older edit
Maxim@tygron.com (talk | contribs)
Tygron, Tygron_admin, Bureaucrats, Interface administrators, Administrators
6,478 edits
No edit summary
No edit summary
 
(41 intermediate revisions by 2 users not shown)
Line 1: Line 1:
A Neural Network in the {{software}} is a pre-trained network that can be used by an [[Inference Overlay]] to classify or detect patterns and features given one or more input [[Overlay]]s.
The {{software}} currently support two families of Artificial Intelligence (AI){{ref|AI}} based on neural networks. Both running on Tygron [[Cloud Computing]] servers:
Neural Networks are stored in the {{software}} as data [[item]]s with a reference to an [[ONNX]]-file (Open Neural Network Exchange format).


Input and output for neural networks is handled using data tensors. These tensors are multi-dimensional data arrays. They are automatically identified when selecting or adding a new Neural Network.
==Classic AI==
[[Region-based Convolutional Neural Network (Inference Overlay)|Region-based Convolutional Neural Network (RCNN)]] used  for Object Recognition in the [[Inference Overlay|AI Inference Overlay]].


Whether a Neural Network classifies or detects objects given an input depends on its inference model. Such a model consists ousing AI-software, such as PyTorch.  
==Generative AI==
[[Generative AI (GenAI)]] such as Large Language Models (LLM) and Diffusion Models used by [[AI Agent]]s in the [[Chat Channel]]s.


{{article end
{{article end
|seealso=*[[Inference Overlay]]
|seealso=*[[AI Agent]]
 
*[[Inference Overlay|AI Inference Overlay]]
*[[ONNX]]
*[[PyTorch]]
|references=
<references>
{{ref|AI
  |name=AI
  |author=
  |page=
  |source=
  |link=https://en.wikipedia.org/wiki/Artificial_intelligence
  |lastvisit=2026-06-29
}}
</references>
|api=*[[Api session items neuralnetworks]]
*[[Api session event editor neuralnetwork]]
}}
}}

Latest revision as of 14:35, 7 October 2026

The Tygron Platform currently support two families of Artificial Intelligence (AI)[1] based on neural networks. Both running on Tygron Cloud Computing servers:

Classic AI

Region-based Convolutional Neural Network (RCNN) used for Object Recognition in the AI Inference Overlay.

Generative AI

Generative AI (GenAI) such as Large Language Models (LLM) and Diffusion Models used by AI Agents in the Chat Channels.

See also

API Endpoints

References

  1. ↑ AI ∙ Found at: https://en.wikipedia.org/wiki/Artificial_intelligence ∙ (last visited: 2026-06-29)
Retrieved from "https://support.tygron.com/w/index.php?title=Neural_Network&oldid=94485"