Increased market for cloud computing 3.5.1.2. Growth associated with artificial intelligence and cognitive computing 3.5.2.

Increased market for cloud computing 3.5.1.2. Growth associated with artificial intelligence and cognitive computing 3.5.2.

The neural network (NN)-based direct uncertainty quantification (UQ) methods have achieved the state of the art performance since the first inauguration, known as the lower-upper-bound estimation (LUBE) method. However, currently-available cost functions for uncertainty guided NN training are not always converging and all converged NNs are not generating optimized prediction intervals (PIs). Moreover, several groups have proposed different quality criteria for PIs. These raise a question about their relative effectiveness. Most of the existing cost functions of uncertainty guided NN training are not customizable and the convergence of training is uncertain. Therefore, in this paper, we propose a highly customizable smooth cost function for developing NNs to construct optimal PIs. The optimized average width of PIs, PI-failure distances and the PI coverage probability (PICP) are computed for the test dataset. The performance of the proposed method is examined for the wind power generation and the electricity demand data. Results show that the proposed method reduces variation in the quality of PIs, accelerates the training, and improves convergence probability from 99.2% to 99.8%.

This paper deals with distributed finite-sum optimization for learning over networks in the presence of malicious Byzantine attacks. To cope with such attacks, most resilient approaches so far combine stochastic gradient descent (SGD) with different robust aggregation rules. However, the sizeable SGD-induced stochastic gradient noise makes it challenging to distinguish malicious messages sent by the Byzantine attackers from noisy stochastic gradients sent by the 'honest' workers. This motivates us to reduce the variance of stochastic gradients as a means of robustifying SGD in the presence of Byzantine attacks. To this end, the present work puts forth a Byzantine attack resilient distributed (Byrd-) SAGA approach for learning tasks involving finite-sum optimization over networks. Rather than the mean employed by distributed SAGA, the novel Byrd- SAGA relies on the geometric median to aggregate the corrected stochastic gradients sent by the workers. When less than half of the workers are Byzantine attackers, the robustness of geometric median to outliers enables Byrd-SAGA to attain provably linear convergence to a neighborhood of the optimal solution, with the asymptotic learning error determined by the number of Byzantine workers. Numerical tests corroborate the robustness to various Byzantine attacks, as well as the merits of Byrd- SAGA over Byzantine attack resilient distributed SGD.

A brain-computer interface (BCI) system usually needs a long calibration session for each new subject/task to adjust its parameters, which impedes its transition from the laboratory to real-world applications. Domain adaptation, which leverages labeled data from auxiliary subjects/tasks (source domains), has demonstrated its effectiveness in reducing such calibration effort. Currently, most domain adaptation approaches require the source domains to have the same feature space and label space as the target domain, which limits their applications, as the auxiliary data may have different feature spaces and/or different label spaces. This paper considers different set domain adaptation for BCIs, i.e., the source and target domains have different label spaces. We introduce a practical setting of different label sets for BCIs, and propose a novel label alignment (LA) approach to align the source label space with the target label space. It has three desirable properties: 1) LA only needs as few as one labeled sample from each class of the target subject; 2) LA can be used as a preprocessing step before different feature extraction and classification algorithms; and, 3) LA can be integrated with other domain adaptation approaches to achieve even better performance. Experiments on two motor imagery datasets demonstrated the effectiveness of LA.

Local partners specialising in artificial intelligence AI, machine learning and automation may want to get ready for a wave of public sector work as the federal government moves to boost its automated decision making capabilities. On 9 October, Australia's Minister for Industry, Science and Technology Karen Andrews and Education Minister Dan Tehan jointly announced that the government would spend $31.8 million to establish a research centre to investigate responsible, ethical, and inclusive automated decision making. The new Centre of Excellence for Automated Decision-Making and Society will be based at RMIT University in Melbourne, and will bring together national and international experts from the humanities, and the social and technological sciences in its efforts to develop a sound basis upon which to build out automated decision making across government. While the controversy around the government's much maligned automated debt collection scheme may have left a bad taste in the public's collective mouth when it comes to automation in public services, Tehan is confident that automated decision making technology can be a force for good in the public sector. "Our Government is funding research into automated decision making to ensure this technology provides the best possible outcomes for society and industry," Tehan said in a statement.

There is a discrepancy in the quality of education worldwide, and it shouldn't come as a surprise that artificial intelligence (AI) education isn't an exception. While some students enjoy small classrooms with fancy electronic whiteboards and qualified instructors, others don't even have electricity. The world is digitally and economically divided, especially in the case of AI education. There are numerous barriers preventing students from acquiring AI skills besides a foundation in mathematics. Many underserved communities lack resources.

Here's everything our readers were most obsessed with in 2019. Purchases you make through our links may earn us a commission. As we head into the new year, we think it's fun to look at all the wonderful products that we bought in 2019. This year brought some incredible releases like Disney, Apple AirPods Pro, and the all-new Kindle--and honestly, some of these things were apart of what really make the year great. So we decided to roundup 100 of the most popular products that people bought over and over again. Whether it was a massive sale (looking at you Black Friday) or one of the hottest product people couldn't stop talking about (*cough* weighted blankets *cough*), our readers found something that caught their eyes. From robot vacuums to wireless headphones to streaming services, these are the most popular products that people couldn't stop buying in 2019. Everyone become obsessed with Disney in 2019. Although it was just released in November, the new streaming service Disney became the most popular product of the year. With it came nostalgia for the Disney classics, new original shows and movies, and plenty of Baby Yoda content. Seriously, if you're a fan of Marvel, Disney Princesses, Star Wars, Pixar, and all things Disney, you might want to consider following suit and getting a subscription for yourself. We still love the tried-and-true Instant Pot Duo. It's no surprise here--our readers were all about that Instant Pot life this year. The Duo 6 Quart, a.k.a. the most popular model out there, was far and away the biggest seller this year, and in no small part because of the deals that ran on it during Prime Day and Black Friday, respectively. If you were one of the lucky ducks who nabbed it when it was just $50, good on you. But you can still get it for a pretty good price right now, too. Nobody really wants to vacuum, but they also don't want to spend a fortune on a robot vacuum to do their dirty work. That's why the Eufy 11S was so popular this year. It's the best affordable robot vacuum we've ever tested because it balances great cleaning powering and a reasonable price. Our readers loved scooping it up--especially when it was on sale as it is right now.

Accurate short-term load forecasting is essential for efficient operation of the power sector. Predicting load at a fine granularity such as individual households or buildings is challenging due to higher volatility and uncertainty in the load. In aggregate loads such as at grids level, the inherent stochasticity and fluctuations are averaged-out, the problem becomes substantially easier. We propose an approach for short-term load forecasting at individual consumers (households) level, called {\em Forecasting using Matrix Factorization} (\textsc{FMF}). \textsc{FMF} does not use any consumers' demographic or activity patterns information. Therefore, it can be applied to any locality with the readily available smart meters and weather data. We perform extensive experiments on three benchmark datasets and demonstrate that \textsc{FMF} significantly outperforms the computationally expensive state-of-the-art methods for this problem. We achieve up to $26.5 \%$ and $24.4 \%$ improvement in \textsc{RMSE} over Regression Tree and Support Vector Machine, respectively and up to $36 \%$ and $73.2 \%$ improvement in \textsc{MAPE} over Random Forest and Long Short-Term Memory neural network, respectively.

Forecasting influenza-like illness (ILI) is of prime importance to epidemiologists and health-care providers. Early prediction of epidemic outbreaks plays a pivotal role in disease intervention and control. Most existing work has either limited long-term prediction performance or lacks a comprehensive ability to capture spatio-temporal dependencies in data. Accurate and early disease forecasting models would markedly improve both epidemic prevention and managing the onset of an epidemic. In this paper, we design a cross-location attention based graph neural network (Cola-GNN) for learning time series embeddings and location aware attentions. We propose a graph message passing framework to combine learned feature embeddings and an attention matrix to model disease propagation over time. We compare the proposed method with state-of-the-art statistical approaches and deep learning models on real-world epidemic-related datasets from United States and Japan. The proposed method shows strong predictive performance and leads to interpretable results for long-term epidemic predictions.