To provide a systematic study of the performance of NAS algorithms on a macro search space, we release Blox - a benchmark that consists of 91k unique models trained on the CIFAR-100 dataset. The dataset also includes runtime measurements of all the models on a diverse set of hardware platforms.

Neural architecture search (NAS) has been successfully used to design numerous high-performance neural networks. However, NAS is typically compute-intensive, so most existing approaches restrict the search to decide the operations and topological structure of a single block only, then the same block is stacked repeatedly to form an end-to-end model. Although such an approach reduces the size of search space, recent studies show that a macro search space, which allows blocks in a model to be different, can lead to better performance. To provide a systematic study of the performance of NAS algorithms on a macro search space, we release Blox - a benchmark that consists of 91k unique models trained on the CIFAR-100 dataset. The dataset also includes runtime measurements of all the models on a diverse set of hardware platforms. We perform extensive experiments to compare existing algorithms that are well studied on cell-based search spaces, with the emerging blockwise approaches that aim to make NAS scalable to much larger macro search spaces.

Robots will replace teachers by 2027. That's the bold claim that Anthony Seldon, a British education expert, made at the British Science Festival in September. Seldon may be the first to set such a specific deadline for the automation of education, but he's not the first to note technology's potential to replace human workers. Whether the "robots" take the form of artificially intelligent (AI) software programs or humanoid machines, research suggests that technology is poised to automate a huge proportion of jobs worldwide, disrupting the global economy and leaving millions unemployed. But just which jobs are on the chopping block is still a subject of debate.

DAVID VOGT'S son loves Lego. As they played together one day, the robotics professor had an idea: could he teach a robot to put the blocks together? "We thought it would be funny to make a robot that could do the same thing I am doing with my son," says Vogt, who is at the Freiburg University of Mining and Technology in Germany. So Vogt and his colleagues brought an industrial robot arm to the lab. Like a child playing for the first time, the robot – equipped with a Kinect depth camera – observed two experienced humans wearing motion tracking tags as they built a Lego rocket.

As the Internet-based crowdsourcing services become more and more popular, learning from multiple teachers or sources has received more attention of the researchers in the machine learning area. In this setting, the learning system is dealing with samples and labels provided by multiple teachers, who in common cases, are non-expert. Their labeling styles and behaviors are usually diverse, some of which are even detrimental to the learning system. Thus, simply putting them together and utilizing the algorithms designed for single-teacher scenario would be not only improper, but also damaging. The problem calls for more specific methods. Our work focuses on a case where the teachers are composed of good ones and irresponsible ones. By irresponsible, we mean the teacher who takes the labeling task not seriously and label the sample at random without inspecting the sample itself. This behavior is quite common when the task is not attractive enough and the teacher just wants to finish it as soon as possible. Sometimes, the irresponsible teachers could take a considerable part among all the teachers. If we do not take out their effects, our learning system would be ruined with no doubt. In this paper, we propose a method for picking out the good teachers with promising experimental results. It works even when the irresponsible teachers are dominating in numbers.