Neural Network: Difference between revisions
Jump to navigation
Jump to search
Created page with "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 Overlays." |
No edit summary |
||
| (21 intermediate revisions by 2 users not shown) | |||
| Line 1: | Line 1: | ||
The {{software}} currently support three types of neural networks running on Tygron [[GPU Cluster]]s: | |||
* RCNN: [[Region-based Convolutional Neural Network (Inference Overlay)|Region-based Convolutional Neural Network]] used in the [[Inference Overlay|AI Inference Overlay]]. | |||
* LLM: [[Large Language Model (LLM)|Large Language Model ]] used in the [[Chat Channel]]s. | |||
* EMBEDDING: Embedding model used for AI assisted data search. | |||
Latest revision as of 15:51, 2 July 2026
The Tygron Platform currently support three types of neural networks running on Tygron GPU Clusters:
- RCNN: Region-based Convolutional Neural Network used in the AI Inference Overlay.
- LLM: Large Language Model used in the Chat Channels.
- EMBEDDING: Embedding model used for AI assisted data search.