Class-incremental learning deals with sequential data streams composed of batches of classes. Various algorithms have been proposed to address the challenging case where samples from past classes cannot be stored. However, selecting an appropriate algorithm for a user-defined setting is an open problem, as the relative performance of these algorithms depends on the incremental settings. To solve this problem, we introduce an algorithm recommendation method that simulates the future data stream. Given an initial set of classes, it leverages generative models to simulate future classes from the same visual domain. We evaluate recent algorithms on the simulated stream and recommend the one which performs best in the user-defined incremental setting. We illustrate the effectiveness of our method on three large datasets using six algorithms and six incremental settings. Our method outperforms competitive baselines, and performance is close to that of an oracle choosing the best algorithm in each setting. This work contributes to facilitate the practical deployment of incremental learning.

A longstanding mystery about how salt dissolves in water has finally been solved, thanks to machine learning. Understanding the complete process of how sodium chloride, or salt, dissolves in water is important for a range of scientific disciplines, from accurate climate models to making batteries.

This article was written by Kate Crawford & Vladan Joler. Below is an extract, featuring the first three sections of this long article (21 sections total.) Link to the full article is provided at the bottom. A cylinder sits in a room. It is impassive, smooth, simple and small.

Last year Kate Crawford, a New York University professor who runs an artificial intelligence research centre, set out to study the "black box" of processes that exist around the hugely popular Amazon Echo device. Crawford did not do what you might expect when approaching AI – namely, study algorithms, computing systems and suchlike. Instead, she teamed up with Vladan Joler, a Serbian academic, to map the supply chains, raw materials, data and labour that underpin Alexa, the AI agent that Echo's users talk to. It was a daunting process – so much so that Joler and Crawford admit that their map, Anatomy of an AI System, is just a first step. The results are both chilling and challenging.