TF . Probability
for HyperParameters
TensorFlow & Deep Learning SG
10 October 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
- TensorFlow Probability
- Mathematics
- Notebook 1 : Model fitting
- Notebook 2 : Hyperparameter Search
- Wrap-up
TF . probability
- Open source library on top of TensorFlow
- Knows all about Probabilities and Distributions
-
- ... and build models from them
- Modelling "the right way"
-
- (i.e. mathematician approved)
Mathematics 1
- A line has the equation :
- $$y=m.x+c$$
- Or (for neural networks) :
- $$y=w.x+b$$
Mathematics 2
- A normal distribution looks like :
- $$\mathcal{N}(\mu, \sigma^2) :: P(x) \sim e^{-\frac{(x-\mu)^2}{2\sigma^2}}$$
Probabilistic Modelling
- Fitting some points with model(s)
- Notebook 1
Hyperparameter Search
- More Gaussian Processes
- ( and a CNN for CIFAR10 )
- Notebook 2
Wrap-up
- Only a glimpse of what can be done
- Warning : Mathematics!
- Wider scope than "just" Deep Learning
* Please add a star... *
Deep Learning
MeetUp Group
Deep Learning : Jump-Start Workshop
Deep Learning
Developer Course
- QUESTIONS -
Martin @
RedDragon . AI