Multiplicative noise, including dropout, is widely used to regularize deep neural networks (DNNs), and is shown to be effective in a wide range of architectures and tasks. From an information perspective, we consider injecting multiplicative noise into a DNN as training the network to solve the task with noisy information pathways, which leads to the observation that multiplicative noise tends to increase the correlation between features, so as to increase the signal-to-noise ratio of information pathways. However, high feature correlation is undesirable, as it increases redundancy in representations. In this work, we propose non-correlating multiplicative noise (NCMN), which exploits batch normalization to remove the correlation effect in a simple yet effective way. We show that NCMN significantly improves the performance of standard multiplicative noise on image classification tasks, providing a better alternative to dropout for batch-normalized networks. Additionally, we present a unified view of NCMN and shake-shake regularization, which explains the performance gain of the latter.

Small base stations (SBs) of fifth-generation (5G) cellular networks are envisioned to have storage devices to locally serve requests for reusable and popular contents by \emph{caching} them at the edge of the network, close to the end users. The ultimate goal is to shift part of the predictable load on the back-haul links, from on-peak to off-peak periods, contributing to a better overall network performance and service experience. To enable the SBs with efficient \textit{fetch-cache} decision-making schemes operating in dynamic settings, this paper introduces simple but flexible generic time-varying fetching and caching costs, which are then used to formulate a constrained minimization of the aggregate cost across files and time. Since caching decisions per time slot influence the content availability in future slots, the novel formulation for optimal fetch-cache decisions falls into the class of dynamic programming. Under this generic formulation, first by considering stationary distributions for the costs and file popularities, an efficient reinforcement learning-based solver known as value iteration algorithm can be used to solve the emerging optimization problem. Later, it is shown that practical limitations on cache capacity can be handled using a particular instance of the generic dynamic pricing formulation. Under this setting, to provide a light-weight online solver for the corresponding optimization, the well-known reinforcement learning algorithm, $Q$-learning, is employed to find optimal fetch-cache decisions. Numerical tests corroborating the merits of the proposed approach wrap up the paper.

Learning from data in the quaternion domain enables us to exploit internal dependencies of 4D signals and treating them as a single entity. One of the models that perfectly suits with quaternion-valued data processing is represented by 3D acoustic signals in their spherical harmonics decomposition. In this paper, we address the problem of localizing and detecting sound events in the spatial sound field by using quaternion-valued data processing. In particular, we consider the spherical harmonic components of the signals captured by a first-order ambisonic microphone and process them by using a quaternion convolutional neural network. Experimental results show that the proposed approach exploits the correlated nature of the ambisonic signals, thus improving accuracy results in 3D sound event detection and localization.

The 31st International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems (IEA/AIE-2018) was held at Concordia University in Montreal, Canada, June 25–28, 2018. This report summarizes the The 31st International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems (IEA/AIE-2018) was held at Concordia University in Montreal, Canada, June 25–28, 2018.  IEA/AIE 2018 continued the tradition of emphasizing on applications of applied intelligent systems to solve real-life problems in all areas including engineering, science, industry, automation a robotics, business and finance, medicine and biomedicine, bioinformatics, cyberspace, and human-machine interactions.

If there's one thing Rory Armes wants audiences at Buildex Calgary to understand, it's the idea that even a small investment in big data and predictive artificial intelligence (AI) can provide actionable insights and pay solid dividends. Armes is CEO of Eight Solutions Inc., a company built on the idea that any business, large or small, can benefit from big data analytics and predictive AI. Its proprietary solution is Cumul8, a cloud-based Internet of Things platform that accepts a wide range of data from any type of monitoring device, then teases valuable conclusions from that data. "People are sometimes left with the notion that they either go all-in on costly predictive AI systems, or stay out of it altogether," says Armes. "Those unrealistic polar choices leaves them comatose." He aims to demystify the concepts around big data in a construction context, explain predictive AI and show how it can quickly demonstrate value.

Decreasing magnetic resonance (MR) image acquisition times can potentially reduce procedural cost and make MR examinations more accessible. Compressed sensing (CS)-based image reconstruction methods, for example, decrease MR acquisition time by reconstructing high-quality images from data that were originally sampled at rates inferior to the Nyquist-Shannon sampling theorem. In this work we propose a hybrid architecture that works both in the k-space (or frequency-domain) and the image (or spatial) domains. Our network is composed of a complex-valued residual U-net in the k-space domain, an inverse Fast Fourier Transform (iFFT) operation, and a real-valued U-net in the image domain. Our experiments demonstrated, using MR raw k-space data, that the proposed hybrid approach can potentially improve CS reconstruction compared to deep-learning networks that operate only in the image domain. In this study we compare our method with four previously published deep neural networks and examine their ability to reconstruct images that are subsequently used to generate regional volume estimates. We evaluated undersampling ratios of 75% and 80%. Our technique was ranked second in the quantitative analysis, but qualitative analysis indicated that our reconstruction performed the best in hard to reconstruct regions, such as the cerebellum. All images reconstructed with our method were successfully post-processed, and showed good volumetry agreement compared with the fully sampled reconstruction measures.

Artificial intelligence is pegged as the tool of the future, so it's only fitting that two Calgary students, the future generation, are organizing a conference on the technology. Grade 11 students Claire Du and Gerry Lu organized an event they're calling the AI4Youth Canada Conference. It took a lot of cold calls, bottle drive cash and organizing, but the event is set to go ahead on Sunday and is already picking up interest with more than 200 people expected to attend. "AI is going to be changing our lives as the next generation," said Du. "So, it's going to be very useful in the future for us to change AI as well." Polling their fellow students at schools, they found most teens didn't know what kind of artificial intelligence technology they encounter on a daily basis.

Multiplicative noise, including dropout, is widely used to regularize deep neural networks (DNNs), and is shown to be effective in a wide range of architectures and tasks. From an information perspective, we consider injecting multiplicative noise into a DNN as training the network to solve the task with noisy information pathways, which leads to the observation that multiplicative noise tends to increase the correlation between features, so as to increase the signal-to-noise ratio of information pathways. However, high feature correlation is undesirable, as it increases redundancy in representations. In this work, we propose non-correlating multiplicative noise (NCMN), which exploits batch normalization to remove the correlation effect in a simple yet effective way. We show that NCMN significantly improves the performance of standard multiplicative noise on image classification tasks, providing a better alternative to dropout for batch-normalized networks. Additionally, we present a unified view of NCMN and shake-shake regularization, which explains the performance gain of the latter.

There is a significant difference between automation and the use of artificial intelligence (AI) in the medtech space. Automation, within a healthcare setting, is defined as the use of hardware and software specifically programmed to save time. AI can be categorized as machine learning, meaning software and hardware working in conjunction to effectively mimic human decision-making -- just much, much faster. AI can learn outside of its programming, and the goal is for the software to make a decision of equivalent quality, compared to a human. The use of automation and AI is integral within the medtech space, as data is becoming increasingly important to manage and understand.

As all physical adaptive quantum-enhanced metrology schemes operate under noisy conditions with only partially understood noise characteristics, so a practical control policy must be robust even for unknown noise. We aim to devise a test to evaluate the robustness of AQEM policies and assess the resource used by the policies. The robustness test is performed on adaptive phase estimation by simulating the scheme under four phase noise models corresponding to the normal-distribution noise, the random telegraph noise, the skew-normal-distribution noise, and the log-normal-distribution noise. The control policies are devised either by a reinforcement-learning algorithm in the same noise condition, albeit ignorant of its properties, or a Bayesian-based feedback method that assumes no noise. Our robustness test and resource comparison can be used to determining the efficacy and selecting a suitable policy.