Facebook has announced a new initiative that aims to teach coding skills to more school kids. Targeting primarily underrepresented student groups -- such as Black, Latino/Hispanic, Native American and female demographics -- CodeFWD will allow teachers to apply for a free set of 15 Sphero Bolt robots upon completion of a series of curricula. Designed for English and Spanish speakers, CodeFWD is a three-step online program for 4th through 8th-grade students that doesn't require prior knowledge from them or their teachers. The first module, "I do," prepares educators to introduce programming to their classrooms. The second one, "We do," is for the teachers and students to learn together.

While data-driven design has considerable potential in contemporary control systems where precise modeling of the dynamics is intractable (e.g., systems with complex contact forces), one of the biggest hurdles to overcome for practical deployment is maintaining safe execution during the learning process. Motivated by this issue, we study the data-driven design of a controller for the constrained Linear Quadratic Regulator (LQR) problem. In constrained LQR, we design a controller for a (potentially unknown) linear dynamical system that minimizes a given quadratic cost, subject to the additional requirement that both the state and input stay within a specified safe region. This is a problem that has received much attention within the model predictive control (MPC) community. For the LQR problem with no constraints, a natural method of exploration for learning the dynamics is to excite the system by injecting white noise. When safety is not an issue, this method is effective and recently Dean et al. [1] provide an end-to-end sample complexity S. Dean, S. Tu, N. Matni, and B. Recht are with the Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, CA, 94709 USA (email: dean sarah@berkeley.edu,

We study two types of preconditioners and preconditioned stochastic gradient descent (SGD) methods in a unified framework. We call the first one the Newton type due to its close relationship to Newton method, and the second one the Fisher type as its preconditioner is closely related to the inverse of Fisher information matrix. Both preconditioners can be derived from one framework, and efficiently learned on any matrix Lie groups designated by the user using natural or relative gradient descent. Many existing preconditioners and methods are special cases of either the Newton type or the Fisher type ones. Experimental results on relatively large scale machine learning problems are reported for performance study.

As data streams become more prevalent, the necessity for online algorithms that mine this transient and dynamic data becomes clearer. Multi-label data stream classification is a supervised learning problem where each instance in the data stream is classified into one or more pre-defined sets of labels. Many methods have been proposed to tackle this problem, including but not limited to ensemble-based methods. Some of these ensemble-based methods are specifically designed to work with certain multi-label base classifiers; some others employ online bagging schemes to build their ensembles. In this study, we introduce a novel online and dynamically-weighted stacked ensemble for multi-label classification, called GOOWE-ML, that utilizes spatial modeling to assign optimal weights to its component classifiers. Our model can be used with any existing incremental multi-label classification algorithm as its base classifier. We conduct experiments with 4 GOOWE-ML-based multi-label ensembles and 7 baseline models on 7 real-world datasets from diverse areas of interest. Our experiments show that GOOWE-ML ensembles yield consistently better results in terms of predictive performance in almost all of the datasets, with respect to the other prominent ensemble models.

Abstract--Time-continuous emotion prediction has become an increasingly compelling task in machine learning. Considerable efforts have been made to advance the performance of these systems. Nonetheless, the main focus has been the development of more sophisticated models and the incorporation of different expressive modalities (e. g., speech, face, and physiology). In this paper, motivated by the benefit of difficulty awareness in a human learning procedure, we propose a novel machine learning framework, namely, Dynamic Difficulty Awareness Training (DDAT), which sheds fresh light on the research - directly exploiting the difficulties in learning to boost the machine learning process. The DDAT framework consists of two stages: information retrieval and information exploitation. In the first stage, we make use of the reconstruction error of input features or the annotation uncertainty to estimate the difficulty of learning specific information. The obtained difficulty level is then used in tandem with original features to update the model input in a second learning stage with the expectation that the model can learn to focus on high difficulty regions of the learning process. We perform extensive experiments on a benchmark database (RECOLA) to evaluate the effectiveness of the proposed framework. The experimental results show that our approach outperforms related baselines as well as other well-established time-continuous emotion prediction systems, which suggests that dynamically integrating the difficulty information for neural networks can help enhance the learning process. Time-continuous emotion prediction systems have received widespread interest in the machine learning (ML) community over the past decade [1]-[3]. One of the main reasons for this interest is the fact that time-continuous emotion predictions can analyse subtle and complex affective states of humans over time and play a central role in smart conversational agents that aim to achieve a natural and intuitive interaction between humans and machines [2], [4]-[7]. Great efforts have been made in this field, and most of them can generally be classified into two strands. Z. Zhang is with GLAM - the Group on Language, Audio & Music, Imperial College London (UK).

Graph convolutional network (GCN) provides a powerful means for graph-based semi-supervised tasks. However, as a localized first-order approximation of spectral graph convolution, the classic GCN can not take full advantage of unlabeled data, especially when the unlabeled node is far from labeled ones. To capitalize on the information from unlabeled nodes to boost the training for GCN, we propose a novel framework named Self-Ensembling GCN (SEGCN), which marries GCN with Mean Teacher - another powerful model in semi-supervised learning. SEGCN contains a student model and a teacher model. As a student, it not only learns to correctly classify the labeled nodes, but also tries to be consistent with the teacher on unlabeled nodes in more challenging situations, such as a high dropout rate and graph collapse. As a teacher, it averages the student model weights and generates more accurate predictions to lead the student. In such a mutual-promoting process, both labeled and unlabeled samples can be fully utilized for backpropagating effective gradients to train GCN. In three article classification tasks, i.e. Citeseer, Cora and Pubmed, we validate that the proposed method matches the state of the arts in the classification accuracy.

We are bringing you four challenges to choose from–sustainability, games, health and inclusivity. Now you can be inspired to create machine learning projects with AWS DeepLens and make a difference at the same time! Use these challenges to gain machine learning experience with fun, collaborative, and inspiring projects. In addition, you'll be making a positive impact on improving people's lives and supporting non-profit organizations that benefit our society. You are invited to enter a single challenge or as many of them as you want.

For the last century or so, K-12 education has primarily aimed to prepare high school graduates for work in manufacturing and similar fields. Recent years have seen schools shift away from that historical model toward the idea of "School 2.0," recognizing changes in the labor market. These moves have been largely due to increasing automation of those jobs and a greater need for skilled workers in growing fields like computer science, hence a greater focus on coding and other STEM skills. Artificial intelligence's projected growth highlights the need for that shift, as it threatens to change the face of the workforce even more drastically. The major players in self-driving car development, for example, are now eyeing automated big rigs, and fully automated restaurants have existed in the U.S. since at least 2015 -- a move that would disrupt a popular first job option for high school teens.

For the next installment of our interview series with leaders who are transforming the role of the chief human resource officer, David Reimer, the CEO of Merryck & Co. Americas, and I sat down recently with Diane Gherson of IBM. Her insights and perspectives provide a clear window into how technology is fundamentally changing the HR function. Stay tuned for more interviews with other HR leaders. What are your thoughts on the phrase "strategic HR?" What does it mean to you? A. In the old days, strategic meant taking the business strategy and translating that into what it meant for the various functional groups you might have in HR, and to a certain extent, how you would allocate your resources. But then it became much more about actually sitting at the strategy table and focusing more on, given our talent, the things that will give us a competitive advantage.

Buffy the Vampire Slayer was the first show on American television to use the word "Google" as a transitive verb. It was 2002, in the fourth episode of the show's seventh and final season. Buffy, Willow, Xander and the gang are trying to help Cassie, a high school student who cryptically says she's going to die next week. In Buffy's dining room, they search through hard copies of Cassie's medical records and find nothing noteworthy. Willow, tapping away on a thick white iBook, turns to Buffy and asks, "Have you Googled her yet?"