What happens to a neural network when its size goes to infinity? Despite the strangeness of the question, the answer turns out to be a fascinating one: the network converges to a so-called Gaussian Process (GP). In this article we overview some recent, notable results exploring the connections between the two, most importantly the neural tangent kernel (NTK). We also introduce a JAX library, Neural Tangents, to compute the predictions of such a…
In the age of the 'big ones' (TensorFlow, PyTorch, ...), introducing and studying a new machine learning library might seem counterproductive. Yet JAX, a brand new research project by Google, has several features that make it interesting to a large audience. Firstly, it looks like a NumPy wrapper, making the transition from this library almost immediate. Secondly, it makes efficiency one of its strengths, thanks to the transparent use of XLA, a linear algebra accelerator originall…
PyTorch is a brand new framework for deep learning, mainly conceived by the Facebook AI Research (FAIR) group, which gained significant popularity in the ML community due to its ease of use and efficiency.
This is the first of a series of tutorials devoted to this framework, starting with the basic building blocks up to more advanced models and techniques to develop deep neural networks. In this first tutorial, we are introducing the two main PyTorch elements: variables and gradients.
A well-known development practice for data scientists involves the definition of machine learning pipelines (aka workflows) to execute a sequence of typical tasks: data normalization, imputation of missing values, outlier elicitation, dimensionality reduction, classification. Scikit-learn provides a pipeline module to automate this process. In this tutorial we will introduce this module, with a particular focus on:
- Creating the pipeline;