El Niño-Southern Oscillation (ENSO) is an atmospheric phenomenon, located in the tropical Pacific, that greatly affects ecosystems as well as human well-being on a large portion of the globe. We use the convLSTM introduced in a prior post to predict the Niño 3.4 Index from spatially-ordered sequences of sea surface temperatures. Today, we use the convLSTM introduced in a previous post to predict El Niño-Southern Oscillation (ENSO). ENSO refers to a changing pattern of sea surface temperatures and sea-level pressures occurring in the equatorial Pacific. From its three overall states, probably the best-known is El Niño. El Niño occurs when surface water temperatures in the eastern Pacific are higher than normal, and the strong winds that normally blow from east…

Geometric deep learning is a “program” that aspires to situate deep learning architectures and techniques in a framework of mathematical priors. The priors, such as various types of invariance, first arise in some physical domain. A neural network that well matches the domain will preserve as many invariances as possible. In this post, we present a very conceptual, high-level overview, and highlight a few applications. To the practitioner, it may often seem that with deep learning, there is a lot of magic involved. Magic in how hyper-parameter choices affect performance, for example. More fundamentally yet, magic in the impacts of architectural decisions. Magic, sometimes, in that it even works (or not). Sure, papers abound that strive to mathematically prove why,…

In forecasting spatially-determined phenomena (the weather, say, or the next frame in a movie), we want to model temporal evolution, ideally using recurrence relations. At the same time, we’d like to efficiently extract spatial features, something that is normally done with convolutional filters. Ideally then, we’d have at our disposal an architecture that is both recurrent and convolutional. In this post, we build a convolutional LSTM with torch. This post is the first in a loose series exploring forecasting of spatially-determined data over time. By spatially-determined I mean that whatever the quantities we’re trying to predict – be they univariate or multivariate time series, of spatial dimensionality or not – the input data are given on a spatial grid. For…

Often, AI researchers and engineers think of themselves as neutral and “objective”, operating in a framework of strict formalization. Fairness and absence of bias, however, are social constructs; there is no objectivity, no LaTeX-typesettable remedies, no algorithmic way out. AI models are developed based on a history and deployed in a context. In AI as in data science, the very absence of action can be of political significance. When you work in a field as intellectually-satisfying, challenging and inspiring as software design for machine learning, it is easy to focus on the technical, keeping out of sight the broader context. Some would even say it is required. How else can you keep up the necessary level of concentration? But even…

We live in a world of ever-diminishing privacy and ever-increasing surveillance - and this is a statement not just about openly-authoritarian regimes. Yet, we seem not to care that much, at least not until, for whatever reasons, we are personally affected by some negative consequence. This post wants to help increase awareness, casting a spotlight on recent history and also, letting words speak for themselves: Because nothing, to me, is less revealing than the “visions” that underly the actions. Why “the hard problem” of privacy? Inspired by the study of consciousness, where some authors posit a difference between a “hard” and an “easy” problem, it is tempting to talk about privacy – as perceived by machine learning (ML) people –…