Difference between revisions of "Capabilities"
| Line 155: | Line 155: | ||
| .. | | .. | ||
| .. | | .. | ||
| + | |- | ||
| + | ! scope="row"| Prediction | ||
| + | | .. | ||
| + | | [[Autocomplete]] | ||
| + | | .. | ||
| + | | .. | ||
| + | | .. | ||
| + | | .. | ||
| + | | [[Predict image]] | ||
|- | |- | ||
! scope="row"| Abnormally detection | ! scope="row"| Abnormally detection | ||
| Line 177: | Line 186: | ||
* Text to Calendar - [[Scheduling]] | * Text to Calendar - [[Scheduling]] | ||
* [[Text to Image - Synthesize [[New image]] based on a description]] | * [[Text to Image - Synthesize [[New image]] based on a description]] | ||
| − | * [[ | + | * Text to Prediction - [[Autocomplete]] |
| + | * Video to Prediction - [[Predict image]] next movie frames | ||
* [[Text/Image/Video to Sentiment - Emotion detection]] | * [[Text/Image/Video to Sentiment - Emotion detection]] | ||
* [[(Speech to) Text to Process to Text (to Speech) - Chatbot, Virtual Assistants, Language Translation, Conversation Modeling]] | * [[(Speech to) Text to Process to Text (to Speech) - Chatbot, Virtual Assistants, Language Translation, Conversation Modeling]] | ||
Revision as of 20:37, 18 May 2018
| Output / Input ---> | Numeric | Text | Sound | Audio | Speech | Image | Video |
|---|---|---|---|---|---|---|---|
| Numeric | Predict real-value | .. | .. | .. | .. | .. | .. |
| Text | .. | .. | .. | .. | Recognizer & NLP | Character recognition | Recognizer & NLP |
| Sound | .. | .. | .. | .. | .. | .. | .. |
| Audio | .. | .. | .. | .. | .. | .. | .. |
| Speech | .. | Synthesize speech | .. | .. | .. | .. | .. |
| Image | .. | New image | .. | .. | .. | Reconstruction, Colorize | .. |
| Video | .. | .. | .. | .. | .. | .. | Colorize |
| Model | .. | .. | .. | .. | .. | 3D Model | 3D Model |
| Database Query | .. | .. | .. | .. | .. | Recipes | Augmented reality |
| Regression | .. | .. | .. | .. | .. | .. | .. |
| Classification (predefined) | .. | News sections | .. | .. | .. | .. | .. |
| Cluster | .. | Recommendations | .. | .. | .. | .. | .. |
| Summary | .. | Headlines | .. | .. | .. | Trailer | .. |
| Add Detail | .. | .. | .. | .. | .. | Enhancement | Enhancement |
| Calendar | .. | Scheduling | .. | .. | .. | .. | .. |
| Emotion | .. | .. | .. | .. | .. | .. | .. |
| Prediction | .. | Autocomplete | .. | .. | .. | .. | Predict image |
| Abnormally detection | Intruder | Cyber detection | Signals | .. | .. | .. | .. |
- Numeric data to Numeric data - Linear Regression - Predict real-value
- Numeric data to Abnormally detection - Intruder
- Text to Abnormally detection - Cyber detection
- Text to Speech - Synthesize speech
- Text to Classification (pre-defined classes) - News sections
- Text to Cluster - Recommendations
- Text to Abnormally detection
- Text to Text - Headlines, summaries
- Speech to Text - Speech Recognizer & NLP, Natural Language Processing (grammar, syntax and semantics), , transcripts
- Text to Calendar - Scheduling
- [[Text to Image - Synthesize New image based on a description]]
- Text to Prediction - Autocomplete
- Video to Prediction - Predict image next movie frames
- Text/Image/Video to Sentiment - Emotion detection
- (Speech to) Text to Process to Text (to Speech) - Chatbot, Virtual Assistants, Language Translation, Conversation Modeling
- (Speech to) Text to Process to Text (to Speech) - Your friend
- Sound/Audio/Image/Video to Classification (predefined classes) - SoundHound, genre
- Sound/Audio/Image/Video to Cluster - grouping related items together e.g. Pandora, birdsongs
- Sound/Audio to Abnormally detection - Signals, Transmission troubleshooting, Electronic warfare
- Image/Video to Abnormally detection
- Image/Video to Segmentation - Object recognition, Collision avoidance
- Image to Text - Digit recognition, Handwriting recognition, Optical Character recognition (OCR)
- Image to Database Query - Recipes
- Video to Database Query - Augmented reality
- 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, DeepFakes
- Image to Image - Image Reconstruction, complete obstructed image
- Image/Video to 3D Model/Image/Video
- [Image/Video to Image/Video - Colorize B/W movies and photos
- [[Image/Video to Image/Video - Image Enhancement, age regression
- Object Revelation - Drug Discovery, Planets
- Forecasting
- Reinforcement Learning - Games, Self-driving Vehicles, Drones, Robotics, Management, Finance