Neural Network: Difference between revisions

Latest revision as of 15:51, 2 July 2026

The Tygron Platform currently support three types of neural networks running on Tygron GPU Clusters:

@@ 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 three types of neural networks running on Tygron [[GPU Cluster]]s:
-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.
+* RCNN: [[Region-based Convolutional Neural Network (Inference Overlay)|Region-based Convolutional Neural Network]] used 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 using AI-software, such as PyTorch.
+* LLM: [[Large Language Model (LLM)|Large Language Model ]] used in the [[Chat Channel]]s.
-{{article end
+* EMBEDDING: Embedding model used for AI assisted data search.
-|seealso=*[[Inference Overlay]]
-|seealso=*[[ONNX]]
-}}