Difference between revisions of "Capabilities"
| Line 16: | Line 16: | ||
* [[Image/Video to Abnormally detection]] | * [[Image/Video to Abnormally detection]] | ||
* [[Image/Video to Segmentation - Object recognition, Collision avoidance]] | * [[Image/Video to Segmentation - Object recognition, Collision avoidance]] | ||
| − | * [[Image/Video to Text - Captioning]] | + | * [[Image/Video to Text - Captioning, Real-time sign language]] |
* [[Generate Text - Synthesize test data, Software code, Scripts]] | * [[Generate Text - Synthesize test data, Software code, Scripts]] | ||
* [[Generate Sound/Audio - Synthesize songs]] | * [[Generate Sound/Audio - Synthesize songs]] | ||
Revision as of 16:56, 14 May 2018
- Text to Speech - Synthesize speech
- Text to Classification (pre-defined classes) - News sections
- Text to Cluster - grouping related items together without labeling them, e.g. grouping patient records with similar symptoms without knowing their symptoms
- Text to Regression
- Text to Abnormally detection
- Text to Text - Headlines, summaries
- (Text to) Natural Language Processing (grammar, syntax and semantics)
- Text to Calendar
- Text to Image/Video - Synthesize new images bases on a description
- Text/Video to Prediction - Autocomplete, Future image
- Text/Image/Video to Sentiment - Emotion detection
- Speech to Text - Speech recognition, transcript
- (Speech to) Text to Process to Text (to Speech) - Chatbot, Virtual Assistants, Language Translation, Conversation Modeling
- Sound/Audio/Image/Video to Classification (predefined classes) - SoundHound, genre
- Sound/Audio/Image/Video to Cluster - grouping related items together e.g. Pandora, birdsongs
- Image/Video to Abnormally detection
- Image/Video to Segmentation - Object recognition, Collision avoidance
- Image/Video to Text - Captioning, Real-time sign language
- Generate Text - Synthesize test data, Software code, Scripts
- Generate Sound/Audio - Synthesize songs
- Generate Image/Video - Art/Image/Actors generation from scratch
- Image/Video to Image/Video - Image enhancement, age regression
- Object Revelation - Drug Discovery, Planets
- Reinforcement Learning - Games, Vehicles, Drones, Robotics, Management, Finance
