Stan is a probabilistic programming language for specifying statistical models. Stan provides full Bayesian inference for continuous-variable models through Markov Chain Monte Carlo methods such as the No-U-Turn sampler, an adaptive form of Hamiltonian Monte Carlo sampling. Penalized maximum likelihood estimates are calculated using optimization methods such as the limited memory Broyden-Fletcher-Goldfarb-Shanno algorithm. Stan can be called through R using the rstan package, and through Python using the pystan package.
The aim of this tutorial is to show the use of TensorFlow with KERAS for classification and prediction in Time Series Analysis. The latter just implement a Long Short Term Memory (LSTM) model (an instance of a Recurrent Neural Network which avoids the vanishing gradient problem).
Introduction The code below has the aim to quick introduce Deep Learning analysis with TensorFlow using the Keras back-end in R environment. Keras is a high-level neural networks API, developed with a focus on enabling fast experimentation and not for final products.
In this session I will try to show some utilities present in the web. One of them will help us to execute R code from the web, using an online compiler, without installing any kind of software in our computers. The other one, it can help us to solve optimization problems by a graphics way. We can draw the restrictions, the feasible region, and others elements that we can need to solve the problems.
This is our second session introducing Shiny, an R package that allows to develop interactive Apps in a familiar framework for regular R-users. During the first session we focused on the structure and workflow basics, and now, we will go further on input and output objects, reactivity, layouts and data handling.
All these functionalities will be reviewed by product of developing a Shiny App. It will provide the grades to our students and, at the same time, they will be able to explore the data set by interacting with the App.
Tensorflow has been widely used for many applications in machine learning and deep learning. However, Tensorflow is more than that, it is a general purpose computing library. Based on that, people have created a rich ecosystem for quickly developing models. In this talk, I will show how statisticians can get most of the main features in Tensorflow such as automatic differentiation, optimization, and Bayesian analysis through a simple linear regression example.
As the title reads, in this heterogeneous session we will see three topics of different interest. The first is a collection of three simple and useful one-function R packages that I use regularly in my coding workflow. The second collects some approaches to handling and performing linear regression with big data. The third brings in the freaky component: it presents tools to display graphical information in plain ASCII, from bivariate contours to messages from Yoda!