NSL
(Neural Structured Learning)
TensorFlow & Deep Learning SG
12 November 2019
About Me
- Machine Intelligence / Startups / Finance
-
- Moved from NYC to Singapore in Sep-2013
- 2014 = 'fun' :
-
- Machine Learning, Deep Learning, NLP
- Robots, drones
- Since 2015 = 'serious' :: NLP + deep learning
-
- & GDE ML; TF&DL co-organiser
- & Papers...
- & Dev Course...
About Red Dragon AI
- Google Partner : Deep Learning Consulting & Prototyping
- SGInnovate/Govt : Education / Training
- Products :
-
- Conversational Computing
- Natural Voice Generation - multiple languages
- Knowledgebase interaction & reasoning
Outline
whoami
= DONE
- Neural Structured Learning
-
- Outline
- Quick walkthrough (concrete graph)
- Synthetic graphs
- Notebook : Adversarial robustness
- Wrap-up
Neural Structured Learning
Outline
- Have a regular classification task
- Examples are also related :
-
- .. to each other (labelled)
- .. to unlabelled examples
Relations via Graph
- Enhance internal representation with graph hints
Losses via Graph
- Enhance internal representation with mathematics
Benefits of NSL
- Reduce labelled data required
- Make use of loose relationships
- Clusters aid interpretability
NSL Building
- Standard classification model
- Encode graph relationships
-
- Wrap original model ⇒ Graph-aware
- Train Graph-aware version
- Use model (no performance penalty)
Neural Structured Learning
'Straight' Application
- Known graph (given explicitly):
-
- Dataset of 2708 scientific publications :
-
- Classified into seven classes
- 1433 unique words to learn over
- Citation network = 5429 links
Neural Structured Learning
'Synthetic' Application
- Create graph on the fly:
-
- Augment the IMDB dataset :
-
- 25,000 reviews for training
- 25,000 reviews for testing
- Create graph of nearest neighbours
- ... defined by document embedding
Deep Learning
MeetUp Group
Deep Learning : Jump-Start Workshop
Deep Learning
Developer Course
- QUESTIONS -
Martin @
RedDragon . AI