Probabilistic Deep Learning in TensorFlow: The Why and How | ODSC Europe 2019

Bayesian probabilistic techniques allow machine learning practitioners to encode expert knowledge in otherwise-uninformed models and support uncertainty in model output. Probabilistic deep learning models take this further by fitting distributions rather than point estimates to each of the weights in a neural network, allowing its builder to inspect the prediction stability for any given set of input data. Following a slew of recent technical advancements, it's never been easier to apply probabilistic modeling in a deep learning context, and TensorFlow Probability offers full support for probabilistic layers as a first-class citizen in the TensorFlow 2.0 ecosystem. This video tutorial will focus on the motivation for probabilistic deep learning and the trade-offs and design decisions relevant to applying it in practice, with applications and examples demonstrated in TensorFlow Probability.

Do You Like This Video? Share Your Thoughts in Comments Below
Also, You can visit our website and choose the nearest ODSC Event to attend and experience all our Trainings and Workshops:

#ODSC #AI #DataScience

[WahranRai]

6:38 The norm function is a standardisation function, normalisation (scaling) is transforming into [0, 1], [-1, 1] etc

[youkorii]

1. Before training the network it must return the prior distribution of the outputs for any input, am I wrong?
2. If we have (1) how to show that the training procedure is using Bayes Rule to update the priors, I mean replacing X by X|y?

[cordeirojoao]

Hello,
Great video, but i believe its not complete.
Can you please let me know whats the link the rest of the video?

Thank you :)