by Christian S. Perone
This weekend I gave a talk at the Machine Learning Porto Alegre Meetup about optimization methods for Deep Learning. In this material you will find an overview of first-order methods, second-order methods and some approximations of second-order methods as well about the natural gradient descent and approximations to it. I took some long nights to prepare this material, so I hope you like it! You can download the PDF of the slides by clicking on the top-right menu.
– Christian S. Perone
Softmax is a distribution over choices, it maps a vector into the probability simplex that is defined as 
In the animations below you’ll see the trajectories of the sample individual sample (from the test set) over the simplex of 3 classes (dog, cat, horse) from CIFAR-10 and using a simple shallow CNN both with Adam and SGD. Each frame is generated after 10 optimization steps and the video is from 4 epochs with CIFAR-10 dataset with only the 3 aforementioned classes.
It is not a secret that I admire the work of Karl Popper, both as a philosopher but also as a very precise historian that tried to dismiss many misunderstandings of the past.
I was reading the book The World of Parmenides, which is a collection of Popper’s essays on the Presocratic Enlightenment, and found a very interesting insight on how the epistemology of Xenophanes led naturally to a professional ethics. This link isn’t widespread nowadays, but it certainly deserves more divulgation as it is a natural consequence of the conjectural knowledge we possess.
I just published the slides of the talk below presented at the Machine Learning Porto Alegre meetup in Brazil:
* This post is in Portuguese.
Resolvi escrever esta nota sobre o estudo de prevalência de anticorpos (seroprevalence) que a UFPel está realizando no Rio Grande do Sul, pois parece haver um grande desentendimento por parte da população, principalmente por parte dos jornalistas em relação aos números reportados pelos pesquisadores da UFPel.
Short animation showing the ICU occupancy forecasting for Portugal during the COVID-19 outbreak. For more information, visit the site below:
Just posting the first early estimate for the COVID-19 
Since the generation time of a virus is very difficult to estimate, most studies rely on the serial interval which is estimated from the interval between clinical onsets. Given that most analysis use the serial interval, it is paramount to have an estimate of the precise onset dates of the symptoms.
I did a analysis for all states in Brazil using data from SIVEP-Gripe, the complete analysis is available here.
In the image above, we can see the gamma mean estimate for the delay on each state in Brazil. Below you can see the distribution for Rio Grande do Sul / RS:
