NEW YORK - Danish toymaker Lego Group has unveiled a new robotics kit that encourages students to gain programming skills through collaborative, hands-on activities. Each set of the Spike Prime kit comes with over 500 pieces, for building a variety of creations, and is paired with lesson plans for both students and teachers. It also comes with an app that uses a drag-and-drop programming language. One of the models, called "Rain or Shine," is programmed to get data from a weather service, which then instructs a Lego robot to move its umbrella or sunglasses based on whether it is raining or sunny in a particular city. "Our intention is that every child in middle school should be able to have a very solid and valuable STEAM (Science, Technology, Engineering, Arts, Math) learning experience and ultimately to build that confidence," said Esben Staerk Joergensen, president of Lego Education.

Do you know the answer to the following problem in arithmetic? What is the sum of 1 1 1 1 1 1 1? If you said "seven," you're right. AI researchers from Google's DeepMind this week published research in which they attempted to train neural networks to solve basic problems in arithmetic, algebra and calculus. The kinds of problems on which a high school student would be typically tested.

In order to enable high-quality decision making and motion planning of intelligent systems such as robotics and autonomous vehicles, accurate probabilistic predictions for surrounding interactive objects is a crucial prerequisite. Although many research studies have been devoted to making predictions on a single entity, it remains an open challenge to forecast future behaviors for multiple interactive agents simultaneously. In this work, we take advantage of the Generative Adversarial Network (GAN) due to its capability of distribution learning and propose a generic multi-agent probabilistic prediction and tracking framework which takes the interactions among multiple entities into account, in which all the entities are treated as a whole. However, since GAN is very hard to train, we make an empirical research and present the relationship between training performance and hyperparameter values with a numerical case study. The results imply that the proposed model can capture both the mean, variance and multi-modalities of the groundtruth distribution. Moreover, we apply the proposed approach to a real-world task of vehicle behavior prediction to demonstrate its effectiveness and accuracy. The results illustrate that the proposed model trained by adversarial learning can achieve a better prediction performance than other state-of-the-art models trained by traditional supervised learning which maximizes the data likelihood. The well-trained model can also be utilized as an implicit proposal distribution for particle filtered based Bayesian state estimation.

Submissions for HCOMP-19 Are Due in June! The Seventh AAAI Conference on Human Computation and Crowdsourcing (HCOMP 2019) will be held October 28-30 at Skamania Lodge in Washington State near the Columbia Gorge River, just 45 minutes from Portland, Oregon. This year is the 10-year anniversary of the very first HCOMP workshop in Paris, and to celebrate, there will be special events, talks, and panels throughout the conference. HCOMP is the premier venue for disseminating the latest research findings on crowdsourcing and human computation. While artificial intelligence (AI) and human-computer interaction (HCI) represent traditional mainstays of the conference, HCOMP believes strongly in inviting, fostering, and promoting broad, interdisciplinary research.

While Standard gradient descent is one very popular optimisation method, its convergence cannot be proven beyond the class of functions whose gradient is globally Lipschitz continuous. As such, it is not actually applicable to realistic applications such as Deep Neural Networks. In this paper, we prove that its backtracking variant behaves very nicely, in particular convergence can be shown for all Morse functions. The main theoretical result of this paper is as follows. Theorem. Let $f:\mathbb{R}^k\rightarrow \mathbb{R}$ be a $C^1$ function, and $\{z_n\}$ a sequence constructed from the Backtracking gradient descent algorithm. (1) Either $\lim _{n\rightarrow\infty}||z_n||=\infty$ or $\lim _{n\rightarrow\infty}||z_{n+1}-z_n||=0$. (2) Assume that $f$ has at most countably many critical points. Then either $\lim _{n\rightarrow\infty}||z_n||=\infty$ or $\{z_n\}$ converges to a critical point of $f$. (3) More generally, assume that all connected components of the set of critical points of $f$ are compact. Then either $\lim _{n\rightarrow\infty}||z_n||=\infty$ or $\{z_n\}$ is bounded. Moreover, in the latter case the set of cluster points of $\{z_n\}$ is connected. Some generalised versions of this result, including an inexact version, are included. Another result in this paper concerns the problem of saddle points. We then present a heuristic argument to explain why Standard gradient descent method works so well, and modifications of the backtracking versions of GD, MMT and NAG. Experiments with datasets CIFAR10 and CIFAR100 on various popular architectures verify the heuristic argument also for the mini-batch practice and show that our new algorithms, while automatically fine tuning learning rates, perform better than current state-of-the-art methods such as MMT, NAG, Adagrad, Adadelta, RMSProp, Adam and Adamax.

A framework previously introduced in [3] for solving a sequence of stochastic optimization problems with bounded changes in the minimizers is extended and applied to machine learning problems such as regression and classification. The stochastic optimization problems arising in these machine learning problems is solved using algorithms such as stochastic gradient descent (SGD). A method based on estimates of the change in the minimizers and properties of the optimization algorithm is introduced for adaptively selecting the number of samples at each time step to ensure that the excess risk, i.e., the expected gap between the loss achieved by the approximate minimizer produced by the optimization algorithm and the exact minimizer, does not exceed a target level. A bound is developed to show that the estimate of the change in the minimizers is non-trivial provided that the excess risk is small enough. Extensions relevant to the machine learning setting are considered, including a cost-based approach to select the number of samples with a cost budget over a fixed horizon, and an approach to applying cross-validation for model selection. Finally, experiments with synthetic and real data are used to validate the algorithms.

STEM has a bit of an image problem: Despite efforts to make it colorful and friendly, it's still intimidating to a lot of students. When there are parents shoving electronics kits at them while offering no help and teachers insisting that learning to code is fundamental to their future career prospects, some kids end up completely turned off. But now Lego Education has a new $330 kit, Spike Prime, aimed at building coding literacy and overcoming the confidence problem that drives many kids away from STEM before they reach high school. Instead of pointing students toward more complex projects, Spike Prime is about basic knowledge and practicality. As Esben Stærk Jørgensen, the president of Lego Education, said during a press event in New York today, Spike Prime is not about learning to code so much as it is coding to learn.

An artificial intelligence has gone to the top of its class after passing an English exam. Though it can't beat more able human students, it achieved the best mark yet for a machine. Hai Zhao at Shanghai Jiao Tong University in China and his colleagues trained their AI on more than 25,000 English reading comprehension tests. Each contained a 200 to 300-word story followed by a series of related multiple-choice questions.

Memories of middle school likely conjure up all sorts of thoughts and emotions. "Productive STEM learning" is probably low on the list. But on Tuesday, Lego is introducing a new coding and robotics set called Spike Prime that it hopes will break through with a notoriously distracted audience. Lego has already dabbled in this world with its Lego Mindstorms line. But those kits can potentially intimidate at the 11- to 14-year-old level, both in complexity and design.

Which Face Is Real? was developed by Jevin West and Carl Bergstrom from the University of Washingtion as part of the Calling Bullshit Project. It acts as a sort of game that anyone can play. Visitors to the site have a choice of two images, one of which is real and the other of which is a fake generated by StyleGAN. The project was implemented by Jevin and Carl as a course that will teach its students how to identify misinformation. Our aim in this course is to teach you how to think critically about the data and models that constitute evidence in the social and natural sciences.