We introduce and analyze a parallel sequential Monte Carlo methodology for the numerical solution of optimization problems that involve the minimization of a cost function that consists of the sum of many individual components. The proposed scheme is a stochastic zeroth order optimization algorithm which demands only the capability to evaluate small subsets of components of the cost function. It can be depicted as a bank of samplers that generate particle approximations of several sequences of probability measures. These measures are constructed in such a way that they have associated probability density functions whose global maxima coincide with the global minima of the original cost function. The algorithm selects the best performing sampler and uses it to approximate a global minimum of the cost function. We prove analytically that the resulting estimator converges to a global minimum of the cost function almost surely and provide explicit convergence rates in terms of the number of generated Monte Carlo samples. We show, by way of numerical examples, that the algorithm can tackle cost functions with multiple minima or with broad "flat" regions which are hard to minimize using gradient-based techniques.

Much of the information in the guide has been gathered via our work with students, faculty, and universities. In particular, Google would like to express our profound gratitude to our outstanding volunteer faculty advisors: Laleh Behjat, University of Calgary; Judith Gal-Ezer, Open University of Israel; Mia Minnes, University of California San Diego; Sathya Narayanan, California State University Monterey Bay; and S. Monisha Pulimood, The College of New Jersey. They gave substantial input to the design and content, and helped us keep the needs of their faculty peers and students front and center.

We study the extent to which we can infer users' geographical locations from social media. Location inference from social media can benefit many applications, such as disaster management, targeted advertising, and news content tailoring. The challenges, however, lie in the limited amount of labeled data and the large scale of social networks. In this paper, we formalize the problem of inferring location from social media into a semi-supervised factor graph model (SSFGM). The model provides a probabilistic framework in which various sources of information (e.g., content and social network) can be combined together. We design a two-layer neural network to learn feature representations, and incorporate the learned latent features into SSFGM. To deal with the large-scale problem, we propose a Two-Chain Sampling (TCS) algorithm to learn SSFGM. The algorithm achieves a good trade-off between accuracy and efficiency. Experiments on Twitter and Weibo show that the proposed TCS algorithm for SSFGM can substantially improve the inference accuracy over several state-of-the-art methods. More importantly, TCS achieves over 100x speedup comparing with traditional propagation-based methods (e.g., loopy belief propagation).

StartupBlink, a Swiss interactive platform for startups, has released its 2019 Ecosystem Ranking Report, with Canada holding on to the third position, boasting five cities in the top 100 startup ecosystems globally. "Canada's major strength lies in the distribution of strong startup hubs scattered throughout the country." Along with Canada, the US, UK, and Israel all held on to the top four spots for countries with the strongest startup ecosystems. However, Canada's typical tech hubs fell in the rankings compared to 2017. This year, Toronto ranked 15, after dropping four spots, while Vancouver dropped six places to 24.

General approach for time series classification is splitting time series to equal size Multivariate time series classification is a high segments using a fixed-length sliding window and extracting value and well-known problem in machine learning handcrafted features from the segments for classification community. Feature extraction is a main step tasks. The features are usually statistical measurements or in classification tasks. Traditional approaches employ features extracted from another domain such Fourier and handcrafted features for classification while Wavelet domain (Jiang & Yin, 2015; Ravi et al., 2017; Lin convolutional neural networks (CNN) are able et al., 2003). In multivariate time series classification, commonly, to extract features automatically. In this paper, information is extracted separately from each variate, we use dilated convolutional neural network for and the features are concatenated for the classification task multivariate time series classification.

Guiding the design of neural networks is of great importance to save enormous resources consumed on empirical decisions of architectural parameters. This paper constructs shallow sigmoid-type neural networks that achieve 100% accuracy in classification for datasets following a linear separability condition. The separability condition in this work is more relaxed than the widely used linear separability. Moreover, the constructed neural network guarantees perfect classification for any datasets sampled from a separable probability distribution. This generalization capability comes from the saturation of sigmoid function that exploits small margins near the boundaries of intervals formed by the separable probability distribution.

C100, a non-profit that connects the Canadian and Silicon Valley startup ecosystems, has accepted 27 companies into the the 2019 cohort of its 48Hrs in the Valley program. The competitive annual program, which is referral-only, pairs Canadian companies with a mentor, then brings them to Silicon Valley for two days of meetings with investors and executives. This year's cohort will run from May 7 to 9. It includes eight firms from Toronto; five from Montreal and one from Laval, Que.; six from Vancouver; two apiece from Calgary and Ottawa; and one each from Halifax, Kitchener, Ont. and Waterloo. The program has been running since 2010. So far, over 250 companies have participated, many of which have gone on to raise money soon after their Silicon Valley visits.

One of the fundamental challenges to realize massive Multiple-Input Multiple-Output (MIMO) communications is the accurate acquisition of channel state information for a plurality of users at the base station. This is usually accomplished in the UpLink (UL) direction profiting from the time division duplexing mode. In practical base station transceivers, there exist inevitably nonlinear hardware components, like signal amplifiers and various analog filters, which complicates the calibration task. To deal with this challenge, we design a deep neural network for channel calibration between the UL and DownLink (DL) directions. During the initial training phase, the deep neural network is trained from both UL and DL channel measurements. We then leverage the trained deep neural network with the instantaneously estimated UL channel to calibrate the DL one, which is not observable during the UL transmission phase. Our numerical results confirm the merits of the proposed approach, and show that it can achieve performance comparable to conventional approaches, like the Agros method and methods based on least squares, that however assume linear hardware behavior models. More importantly, considering generic nonlinear relationships between the UL and DL channels, it is demonstrated that our deep neural network approach exhibits robust performance, even when the number of training sequences is limited.

On Wednesday, the Alberta government announced a $100 million investment, over a period of five years, to attract more artificial intelligence-based high-tech companies to Alberta. The five-year plan will support both Alberta Innovates and the Alberta Machine Intelligence Institute (Amii) to leverage partnerships with Alberta's research universities, while also creating jobs. In addition, Alberta will undertake a significant campaign to market Alberta's tech talent to the world in order to attract new investment. Since 2002, Alberta has invested $42 million in AI research at the University of Alberta and Amii. "Businesses around the world are turning to machine learning and artificial intelligence as key drivers of innovation across every industry sector."

The provincial government is putting $100 million toward a five-year plan to entice high-tech companies specializing in artificial intelligence (AI) to invest in Alberta. The province believes the funding will net 5,600 high-skill jobs, more than 100 new companies and dozens of new multi-national offices and labs in the province, Premier Rachel Notley said Wednesday at an announcement in Calgary. "High tech is the future and we making it happen right here in Alberta," she said. An initial investment of $27 million in the Alberta Machine Intelligence Institute (Amii) will see the non-profit set up a new program to support companies looking to build up their in-house AI capacity. The provincial funding, combined with $25 million from Ottawa, will also allow the Edmonton-based Amii to establish a new Calgary office, a release said.