by Christian S. Perone
Just sharing some slides I presented at the PyData Lisbon on July 2019 about the talk “Uncertainty Estimation in Deep Learning“:
A few months ago I made a post about Randomized Prior Functions for Deep Reinforcement Learning, where I showed how to implement the training procedure in PyTorch and how to extract the model uncertainty from them.
Using the same code showed earlier, these animations below show the training of an ensemble of 40 models with 2-layer MLP and 20 hidden units in different settings. These visualizations are really nice to understand what are the convergence differences when using or not bootstrap or randomized priors.
This is a training session without bootstrapping data or adding a randomized prior, it’s just a naive ensembling:
This is the ensemble but with the addition of the randomized prior (MLP with the same architecture, with random weights and fixed):
$$Q_{\theta_k}(x) = f_{\theta_k}(x) + p_k(x)$$
The final model \(Q_{\theta_k}(x)\) will be the k model of the ensemble that will fit the function \(f_{\theta_k}(x)\) with an untrained prior \(p_k(x)\):
This is a ensemble with the randomized prior functions and data bootstrap:
This is an ensemble with a fixed prior (Sin) and bootstrapping:
Not a lot of people working with the Python scientific ecosystem are aware of the NEP 18 (dispatch mechanism for NumPy’s high-level array functions). Given the importance of this protocol, I decided to write this short introduction to the new dispatcher that will certainly bring a lot of benefits for the Python scientific ecosystem.
If you used PyTorch, TensorFlow, Dask, etc, you certainly noticed the similarity of their API contracts with Numpy. And it’s not by accident, Numpy’s API is one of the most fundamental and widely-used APIs for scientific computing. Numpy is so pervasive, that it ceased to be only an API and it is becoming more a protocol or an API specification.