M. Pell (The Microsoft Garage): Surfacing The Invisible Deceptively powerful and stunningly beautiful, this monumental leap forward in conveying the invisible effectively has always been right there in front of us, waiting to be unlocked, hiding in plain sight. All it took was the convergence of human ingenuity, artificial intelligence, and the rise of a medium capable of magic.

LONG BEACH, CALIFORNIA--Every time you talk, your body moves in sync, whether it's something as subtle as eyes widening or more extreme movements like flailing arms. Now, researchers have designed an artificial intelligence that knows how you're going to move based purely on the sound of your voice. Researchers collected 144 hours of video of 10 people speaking, including a nun, a chemistry teacher, and five TV show hosts (Conan O'Brien, Ellen DeGeneres, John Oliver, Jon Stewart, and Seth Meyers). They used an existing algorithm to produce skeletal figures representing the positions of the speakers' arms and hands. They then trained their own algorithm with the data, so it would predict gestures based on fresh audio of the speakers.

For many, artificial intelligence, or AI, may seem like a new and possibly overwhelming concept. The reality is that AI is already being applied in industry and, for many of us, in our daily lives as well. A better understanding of AI can help you make informed decisions now that will impact the future of your learners. In Teaching AI, you'll learn what AI is, how it works and how to use it to better prepare students in a world with increased human-computer interaction. Michelle Zimmerman has taught students from ages 3-16.

In a commonly-used version of the Simple Assembly Line Balancing Problem (SALBP-1) tasks are assigned to stations along an assembly line with a fixed cycle time in order to minimize the required number of stations. It has traditionally been assumed that the total work needed for each product unit has been partitioned into economically indivisible tasks. However, in practice, it is sometimes possible to divide particular tasks in limited ways at additional time penalty cost. Despite the penalties, task division where possible, now and then leads to a reduction in the minimum number of stations. Deciding which allowable tasks to divide creates a new assembly line balancing problem, TDALBP (Task Division Assembly Line Balancing Problem). We propose a mathematical model of the TDALBP, an exact solution procedure for it and present promising computational results for the adaptation of some classical SALBP instances from the research literature. The results demonstrate that the TDALBP sometimes has the potential to significantly improve assembly line performance.

Computational simulations with different fidelity have been widely used in engineering design. A high-fidelity (HF) model is generally more accurate but also more time-consuming than an low-fidelity (LF) model. To take advantages of both HF and LF models, multi-fidelity surrogate models that aim to integrate information from both HF and LF models have gained increasing popularity. In this paper, a multi-fidelity surrogate model based on support vector regression named as Co_SVR is developed by combining HF and LF models. In Co_SVR, a kernel function is used to map the map the difference between the HF and LF models. Besides, a heuristic algorithm is used to obtain the optimal parameters of Co_SVR. The proposed Co_SVR is compared with two popular multi-fidelity surrogate models Co_Kriging model, Co_RBF model, and their single-fidelity surrogates through several numerical cases and a pressure vessel design problem. The results show that Co_SVR provides competitive prediction accuracy for numerical cases, and presents a better performance compared with the Co_Kriging and Co_RBF models and single-fidelity surrogate models.

Aggregated data is commonplace in areas such as epidemiology and demography. For example, census data for a population is usually given as averages defined over time periods or spatial resolutions (city, region or countries). In this paper, we present a novel multi-task learning model based on Gaussian processes for joint learning of variables that have been aggregated at different input scales. Our model represents each task as the linear combination of the realizations of latent processes that are integrated at a different scale per task. We are then able to compute the cross-covariance between the different tasks either analytically or numerically. We also allow each task to have a potentially different likelihood model and provide a variational lower bound that can be optimised in a stochastic fashion making our model suitable for larger datasets. We show examples of the model in a synthetic example, a fertility dataset and an air pollution prediction application.

We study the problem of recovering the structure underlying large Gaussian graphical models. In high-dimensional problems it is often too costly to store the entire sample covariance matrix. We propose a new input model in which one can query single entries of the sample covariance matrix. We present computationally efficient algorithms for structure recovery in Gaussian graphical models with low query and computational complexity. Our algorithms work in a regime of tree-like graphs and, more generally, for graphs of small treewidth. Our results demonstrate that for large classes of graphs, the structure of the corresponding Gaussian graphical models can be determined much faster than even computing the empirical covariance matrix.

Among the extensions of twin support vector machine (TSVM), some scholars have utilized K-nearest neighbor (KNN) graph to enhance TSVM's classification accuracy. However, these KNN-based TSVM classifiers have two major issues such as high computational cost and overfitting. In order to address these issues, this paper presents an enhanced regularized K-nearest neighbor based twin support vector machine (RKNN-TSVM). It has three additional advantages: (1) Weight is given to each sample by considering the distance from its nearest neighbors. This further reduces the effect of noise and outliers on the output model. (2) An extra stabilizer term was added to each objective function. As a result, the learning rules of the proposed method are stable. (3) To reduce the computational cost of finding KNNs for all the samples, location difference of multiple distances based k-nearest neighbors algorithm (LDMDBA) was embedded into the learning process of the proposed method. The extensive experimental results on several synthetic and benchmark datasets show the effectiveness of our proposed RKNN-TSVM in both classification accuracy and computational time. Moreover, the largest speedup in the proposed method reaches to 14 times.

Existing graph-based methods for extractive document summarization represent sentences of a corpus as the nodes of a graph or a hypergraph in which edges depict relationships of lexical similarity between sentences. Such approaches fail to capture semantic similarities between sentences when they express a similar information but have few words in common and are thus lexically dissimilar. To overcome this issue, we propose to extract semantic similarities based on topical representations of sentences. Inspired by the Hierarchical Dirichlet Process, we propose a probabilistic topic model in order to infer topic distributions of sentences. As each topic defines a semantic connection among a group of sentences with a certain degree of membership for each sentence, we propose a fuzzy hypergraph model in which nodes are sentences and fuzzy hyperedges are topics. To produce an informative summary, we extract a set of sentences from the corpus by simultaneously maximizing their relevance to a user-defined query, their centrality in the fuzzy hypergraph and their coverage of topics present in the corpus. We formulate a polynomial time algorithm building on the theory of submodular functions to solve the associated optimization problem. A thorough comparative analysis with other graph-based summarization systems is included in the paper. Our obtained results show the superiority of our method in terms of content coverage of the summaries.

Non-Autoregressive Transformer (NAT) aims to accelerate the Transformer model through discarding the autoregressive mechanism and generating target words independently, which fails to exploit the target sequential information. Over-translation and under-translation errors often occur for the above reason, especially in the long sentence translation scenario. In this paper, we propose two approaches to retrieve the target sequential information for NAT to enhance its translation ability while preserving the fast-decoding property. Firstly, we propose a sequence-level training method based on a novel reinforcement algorithm for NAT (Reinforce-NAT) to reduce the variance and stabilize the training procedure. Secondly, we propose an innovative Transformer decoder named FS-decoder to fuse the target sequential information into the top layer of the decoder. Experimental results on three translation tasks show that the Reinforce-NAT surpasses the baseline NAT system by a significant margin on BLEU without decelerating the decoding speed and the FS-decoder achieves comparable translation performance to the autoregressive Transformer with considerable speedup.