Deep neural networks (DNNs) have succeeded in many different perception tasks, e.g., computer vision, natural language processing, reinforcement learning, etc. The high-performed DNNs heavily rely on intensive resource consumption. For example, training a DNN requires high dynamic memory, a large-scale dataset, and a large number of computations (a long training time); even inference with a DNN also demands a large amount of static storage, computations (a long inference time), and energy. Therefore, state-of-the-art DNNs are often deployed on a cloud server with a large number of super-computers, a high-bandwidth communication bus, a shared storage infrastructure, and a high power supplement. Recently, some new emerging intelligent applications, e.g., AR/VR, mobile assistants, Internet of Things, require us to deploy DNNs on resource-constrained edge devices. Compare to a cloud server, edge devices often have a rather small amount of resources. To deploy DNNs on edge devices, we need to reduce the size of DNNs, i.e., we target a better trade-off between resource consumption and model accuracy. In this dissertation, we studied four edge intelligence scenarios, i.e., Inference on Edge Devices, Adaptation on Edge Devices, Learning on Edge Devices, and Edge-Server Systems, and developed different methodologies to enable deep learning in each scenario. Since current DNNs are often over-parameterized, our goal is to find and reduce the redundancy of the DNNs in each scenario.

Early identification of emergent topics is of eminent importance due to their potential impacts on society. There are many methods for detecting emerging terms and topics, all with advantages and drawbacks. However, there is no consensus about the attributes and indicators of emergence. In this study, we evaluate emerging topic detection in the field of artificial intelligence using a new method to evaluate emergence. We also introduce two new attributes of collaboration and technological impact which can help us use both paper and patent information simultaneously. Our results confirm that the proposed new method can successfully identify the emerging topics in the period of the study. Moreover, this new method can provide us with the score of each attribute and a final emergence score, which enable us to rank the emerging topics with their emergence scores and each attribute score.

We consider the problem of modeling heterogeneous materials where micro-scale dynamics and interactions affect global behavior. In the presence of heterogeneities in material microstructure it is often impractical, if not impossible, to provide quantitative characterization of material response. The goal of this work is to develop a Bayesian framework for uncertainty quantification (UQ) in material response prediction when using nonlocal models. Our approach combines the nonlocal operator regression (NOR) technique and Bayesian inference. Specifically, we use a Markov chain Monte Carlo (MCMC) method to sample the posterior probability distribution on parameters involved in the nonlocal constitutive law, and associated modeling discrepancies relative to higher fidelity computations. As an application, we consider the propagation of stress waves through a one-dimensional heterogeneous bar with randomly generated microstructure. Several numerical tests illustrate the construction, enabling UQ in nonlocal model predictions. Although nonlocal models have become popular means for homogenization, their statistical calibration with respect to high-fidelity models has not been presented before. This work is a first step towards statistical characterization of nonlocal model discrepancy in the context of homogenization.

In this work, we present a framework that enables a vehicle to autonomously localize a target based on noisy range measurements computed from RSSI data. To achieve the mission objectives, we develop a control scheme composed of two main parts: an estimator and a motion planner. At each time step, new estimates of the target's position are computed and used to generate and update distribution functions using Bernstein polynomials. A metric of the efficiency of the estimator is derived based on the Fisher Information Matrix. Finally, the motion planning problem is formulated to react in real time to new information about the target and improve the estimator's performance.

Deep generative models have demonstrated effectiveness in learning compact and expressive design representations that significantly improve geometric design optimization. However, these models do not consider the uncertainty introduced by manufacturing or fabrication. Past work that quantifies such uncertainty often makes simplifying assumptions on geometric variations, while the "real-world", "free-form" uncertainty and its impact on design performance are difficult to quantify due to the high dimensionality. To address this issue, we propose a Generative Adversarial Network-based Design under Uncertainty Framework (GAN-DUF), which contains a deep generative model that simultaneously learns a compact representation of nominal (ideal) designs and the conditional distribution of fabricated designs given any nominal design. This opens up new possibilities of 1)~building a universal uncertainty quantification model compatible with both shape and topological designs, 2)~modeling free-form geometric uncertainties without the need to make any assumptions on the distribution of geometric variability, and 3)~allowing fast prediction of uncertainties for new nominal designs. We can combine the proposed deep generative model with robust design optimization or reliability-based design optimization for design under uncertainty. We demonstrated the framework on two real-world engineering design examples and showed its capability of finding the solution that possesses better performances after fabrication.

Sometimes we invent them by accident, like with Silly Putty. But far more often, making useful materials is a tedious and expensive process of trial and error. Scientists at the U.S. Department of Energy's (DOE) Argonne National Laboratory have recently demonstrated an automated process for identifying and exploring promising new materials by combining machine learning (ML) -- a type of artificial intelligence -- and high performance computing. The new approach could help accelerate the discovery and design of useful materials. Using the single element carbon as a prototype, the algorithm predicted the ways in which atoms order themselves under a wide range of temperatures and pressures to make up different substances.

The onshoring and buildout of dozens of fabs, many costing tens of billions of dollars, is beginning to spill over into other areas that are critical for chip manufacturing. Materials, in particular, which often gets little attention outside of chip manufacturing, witnessed a big spike in September 2022. In fact, seven materials companies covered in this report made up more than a third of the month's total reported investments, with three of the companies garnering more than $200 million. Other investment targets were sputtering equipment and evaporation materials for deposition, high-purity polycrystalline silicon, fluorine-containing electronic gases, and silicon carbide. In the AI hardware arena, numerous startups are focusing on in-memory and near-memory compute, reducing the volume of data that needs to be moved back and forth between memory and processing elements. Novel architectures also are appearing, such as one that uses sparse mathematics.

Global AI-powered Order-to-Cash platform, Sidetrade, announced an acceleration to its North America offensive strategy with plans to invest $24 million and add 110 full-time jobs in Calgary over the next three years. Just one year since the launch of its North America operations, Sidetrade has exceeded expectations with 58% of its new bookings now from the North America market. The SaaS provider has been recognized by Gartner as one of just three Leaders in the 2022 Magic Quadrant for Invoice to Cash applications. Sidetrade is now accelerating its expansion into North America by investing $24 million in the next three years and hiring in the region. Brad Parry, President and CEO of Calgary Economic Development, said: "Sidetrade's expansion in Calgary as its North American headquarters speaks to the city's leading business environment and the exciting momentum in our tech and innovation ecosystem. Alberta and Calgary are centres for AI excellence with highly skilled talent, and as a global leader in AI, Sidetrade joins a growing roster of multinational companies that call Calgary home, where bright minds with big ideas are solving global challenges."

LivePerson, a global leader in customer engagement solutions, announced the appointment of Chief Marketing Officer Ruth Zive, who will be introduced to customers as the host of the company's next Executive Community event in San Francisco on October 20. These signature events bring customer care, marketing, and sales VIPs from the world's top brands together to exchange ideas with peers who work with LivePerson to transform customer engagement through Conversational AI. "I've been following LivePerson closely from the sidelines -- impressed by its market presence, roster of top tier enterprise customers, and winning platform -- and can think of no better time to meet customers than during this flagship event," said Zive. "I'm energized to join this team, composed of the industry's best talent, to help catalyze LivePerson's next stage of growth." Zive will oversee LivePerson's global marketing organization, including digital and demand generation, field marketing and sales development, vertical and product marketing, branding, and internal and external communications. Her priority is to grow scalable, measurable, and predictable world-class demand generation while driving operational rigor. In joining LivePerson, Zive becomes a three-time enterprise software CMO.

SaaS companies SiteZeus and Spatial.ai have teamed up to offer growing brands a cutting-edge customer segmentation platform: SiteZeus Market, powered by PersonaLive. Equipped with unprecedented insights, marketers across all industries can now craft highly tailored campaigns and deploy them efficiently. The end result: an increased return on every marketing dollar spent. This new technology empowers companies to truly understand their customers by transcending the limitations of traditional demographic data and surveys. A brand can now identify, analyze, and target its top customer groups based on their real-time social media activity, online behaviors, and in-store visitation patterns.