We study the misclassification error for community detection in general heterogeneous stochastic block models (SBM) with noisy or partial label information. We establish a connection between the misclassification rate and the notion of minimum energy on the local neighborhood of the SBM. We develop an optimally weighted message passing algorithm to reconstruct labels for SBM based on the minimum energy flow and the eigenvectors of a certain Markov transition matrix. The general SBM considered in this paper allows for unequal-size communities, degree heterogeneity, and different connection probabilities among blocks. We focus on how to optimally weigh the message passing to improve misclassification.

In this paper, we propose and study opportunistic bandits - a new variant of bandits where the regret of pulling a suboptimal arm varies under different environmental conditions, such as network load or produce price. When the load/price is low, so is the cost/regret of pulling a suboptimal arm (e.g., trying a suboptimal network configuration). Therefore, intuitively, we could explore more when the load is low and exploit more when the load is high. Inspired by this intuition, we propose an Adaptive Upper-Confidence-Bound (AdaUCB) algorithm to adaptively balance the exploration-exploitation tradeoff for opportunistic bandits. We prove that AdaUCB achieves $O(\log T)$ regret with a smaller coefficient than the traditional UCB algorithm. Furthermore, AdaUCB achieves $O(1)$ regret when the exploration cost is zero if the load level is below a certain threshold. Last, based on both synthetic data and real-world traces, experimental results show that AdaUCB significantly outperforms other bandit algorithms, such as UCB and TS (Thompson Sampling), under large load fluctuations.

Facebook and Microsoft are today introducing Open Neural Network Exchange (ONNX) format, a standard for representing deep learning models that enables models to be transferred between frameworks. When developing learning models, engineers and researchers have many AI frameworks to choose from. At the outset of a project, developers have to choose features and commit to a framework. We developed ONNX together with Microsoft to bridge this gap and to empower AI developers to choose the framework that fits the current stage of their project and easily switch between frameworks as the project evolves. Enabling interoperability between different frameworks and streamlining the path from research to production will help increase the speed of innovation in the AI community.

Today's consumers are pickier than ever. They want customized, personalized and unique products over standardized ones and prefer local, smaller producers over large-scale global manufacturers. At the same time, they also expect locally-produced products to be as cheap and reliable as those industrially produced. Factories, power plants, and manufacturing centers around the world must rely on automation, machine learning, computer vision, and other fields of AI to meet these rising demands and transform the way we make, move, and market things. Since the industrial revolution, factories have been optimized to mass produce a few products rapidly and cheaply to satisfy global demand.

Earlier this year, Bill Gates, founder of Microsoft and the richest man on Earth, wrote an essay online at "The blog of Bill Gates," to college students graduating worldwide in 2017. One is artificial intelligence (AI). We have only begun to tap into all the ways it will make people's lives more productive and creative. The second is energy, because making it clean, affordable, and reliable will be essential for fighting poverty and climate change." The third field he mentioned was biosciences.

Under this Mazda3 is a next-gen platform/powertrain. But future models will still be DIY-drives, says the company. The talk of the motor industry at the moment is the inevitable march towards autonomous cars. How much can cars do, how fast can we get make them do it? Make that most of the motor industry.

Chinese tech and gaming giant Tencent Holdings Ltd. [HKG:0700] is ready to invest heavily in emerging technologies, such as artificial intelligence, cloud computing and Big Data, founder Pony Ma said in a speech to Tsinghua University's School of Economics and Management on Sept. 8. "I feel that we are ready to invest in several basic fields," said Ma, who Forbes' ranks as the eighth richest man in tech worldwide. We will work with a range of sectors, academics and researchers via Internet Plus and other means." Internet plus is used to refer to the application of the internet and other information technology to traditional industries. All future technologies will be inseparable from these three areas, he added. "When they are combined, we will have a role to play.

The Soil Moisture Active Passive (SMAP) mission has delivered valuable sensing of surface soil moisture since 2015. However, it has a short time span and irregular revisit schedule. Utilizing a state-of-the-art time-series deep learning neural network, Long Short-Term Memory (LSTM), we created a system that predicts SMAP level-3 soil moisture data with atmospheric forcing, model-simulated moisture, and static physiographic attributes as inputs. The system removes most of the bias with model simulations and improves predicted moisture climatology, achieving small test root-mean-squared error (<0.035) and high correlation coefficient >0.87 for over 75\% of Continental United States, including the forested Southeast. As the first application of LSTM in hydrology, we show the proposed network avoids overfitting and is robust for both temporal and spatial extrapolation tests. LSTM generalizes well across regions with distinct climates and physiography. With high fidelity to SMAP, LSTM shows great potential for hindcasting, data assimilation, and weather forecasting.

Computing partition function is the most important statistical inference task arising in applications of Graphical Models (GM). Since it is computationally intractable, approximate methods have been used to resolve the issue in practice, where mean-field (MF) and belief propagation (BP) are arguably the most popular and successful approaches of a variational type. In this paper, we propose two new variational schemes, coined Gauged-MF (G-MF) and Gauged-BP (G-BP), improving MF and BP, respectively. Both provide lower bounds for the partition function by utilizing the so-called gauge transformation which modifies factors of GM while keeping the partition function invariant. Moreover, we prove that both G-MF and G-BP are exact for GMs with a single loop of a special structure, even though the bare MF and BP perform badly in this case. Our extensive experiments, on complete GMs of relatively small size and on large GM (up-to 300 variables) confirm that the newly proposed algorithms outperform and generalize MF and BP.

We generalize a support vector machine to a support spinor machine by using the mathematical structure of wedge product over vector machine in order to extend field from vector field to spinor field. The separated hyperplane is extended to Kolmogorov space in time series data which allow us to extend a structure of support vector machine to a support tensor machine and a support tensor machine moduli space. Our performance test on support spinor machine is done over one class classification of end point in physiology state of time series data after empirical mode analysis and compared with support vector machine test. We implement algorithm of support spinor machine by using Holo-Hilbert amplitude modulation for fully nonlinear and nonstationary time series data analysis.