Across the University of Iowa campus, researchers are using artificial intelligence, machine learning, and big data to tackle pressing issues related to healthcare, space exploration, and public health, including the COVID-19 pandemic. For more than 30 years, this research has been made possible through expertise as well as logistical and financial support from the UI College of Engineering. "Our ability to collaborate across disciplines, departments, and colleges demonstrates that the cutting-edge research done in our College of Engineering is tremendously important to the work of our entire campus," said Harriet Nembhard, dean of the College of Engineering. "These partnerships exist in ways one might expect such as in medical imaging in the UI Carver College of Medicine and injury prevention in the College of Public Health but we also support work in the Tippie College of Business, the College of Liberal Arts and Sciences, and the College of Education." In all, the Iowa Initiative for Artificial Intelligence, funded by the Office of the Provost, Colleges of Engineering, Liberal Arts and Sciences, Medicine, Business, and Education, as well as several UI departments and research centers leads 27 active projects across campus, many of which involve engineering researchers.

Recommender systems trained in a continuous learning fashion are plagued by the feedback loop problem, also known as algorithmic bias. This causes a newly trained model to act greedily and favor items that have already been engaged by users. This behavior is particularly harmful in personalised ads recommendations, as it can also cause new campaigns to remain unexplored. Exploration aims to address this limitation by providing new information about the environment, which encompasses user preference, and can lead to higher long-term reward. In this work, we formulate a display advertising recommender as a contextual bandit and implement exploration techniques that require sampling from the posterior distribution of click-through-rates in a computationally tractable manner. Traditional large-scale deep learning models do not provide uncertainty estimates by default. We approximate these uncertainty measurements of the predictions by employing a bootstrapped model with multiple heads and dropout units. We benchmark a number of different models in an offline simulation environment using a publicly available dataset of user-ads engagements. We test our proposed deep Bayesian bandits algorithm in the offline simulation and online AB setting with large-scale production traffic, where we demonstrate a positive gain of our exploration model.

In this paper, we propose the Adaptive Physics-Informed Neural Networks (APINNs) for accurate and efficient simulation-free Bayesian parameter estimation via Markov-Chain Monte Carlo (MCMC). We specifically focus on a class of parameter estimation problems for which computing the likelihood function requires solving a PDE. The proposed method consists of: (1) constructing an offline PINN-UQ model as an approximation to the forward model; and (2) refining this approximate model on the fly using samples generated from the MCMC sampler. The proposed APINN method constantly refines this approximate model on the fly and guarantees that the approximation error is always less than a user-defined residual error threshold. We numerically demonstrate the performance of the proposed APINN method in solving a parameter estimation problem for a system governed by the Poisson equation.

Domain adaptation approaches aim to exploit useful information from the source domain where supervised learning examples are easier to obtain to address a learning problem in the target domain where there is no or limited availability of such examples. In classification problems, domain adaptation has been studied under varying supervised, unsupervised and semi-supervised conditions. However, a common situation when the labelled samples are available for a subset of target domain classes has been overlooked. In this paper, we formulate this particular domain adaptation problem within a generalized zero-shot learning framework by treating the labelled source domain samples as semantic representations for zero-shot learning. For this particular problem, neither conventional domain adaptation approaches nor zero-shot learning algorithms directly apply. To address this generalized zero-shot domain adaptation problem, we present a novel Coupled Conditional Variational Autoencoder (CCVAE) which can generate synthetic target domain features for unseen classes from their source domain counterparts. Extensive experiments have been conducted on three domain adaptation datasets including a bespoke X-ray security checkpoint dataset to simulate a real-world application in aviation security. The results demonstrate the effectiveness of our proposed approach both against established benchmarks and in terms of real-world applicability.

Learning from demonstration is widely used as an efficient way for robots to acquire new skills. However, it typically requires that demonstrations provide full access to the state and action sequences. In contrast, learning from observation offers a way to utilize unlabeled demonstrations (e.g., video) to perform imitation learning. One approach to this is behavioral cloning from observation (BCO). The original implementation of BCO proceeds by first learning an inverse dynamics model and then using that model to estimate action labels, thereby reducing the problem to behavioral cloning. However, existing approaches to BCO require a large number of initial interactions in the first step. Here, we provide a novel theoretical analysis of BCO, introduce a modification BCO*, and show that in the semi-supervised setting, BCO* can concurrently improve both its estimate for the inverse dynamics model and the expert policy. This result allows us to eliminate the dependence on initial interactions and dramatically improve the sample complexity of BCO. We evaluate the effectiveness of our algorithm through experiments on various benchmark domains. The results demonstrate that concurrent training not only improves over the performance of BCO but also results in performance that is competitive with state-of-the-art imitation learning methods such as GAIL and Value-Dice.

We consider the classical problem of sequential probability assignment under logarithmic loss while competing against an arbitrary, potentially nonparametric class of experts. We obtain tight bounds on the minimax regret via a new approach that exploits the self-concordance property of the logarithmic loss. We show that for any expert class with (sequential) metric entropy $\mathcal{O}(\gamma^{-p})$ at scale $\gamma$, the minimax regret is $\mathcal{O}(n^{p/(p+1)})$, and that this rate cannot be improved without additional assumptions on the expert class under consideration. As an application of our techniques, we resolve the minimax regret for nonparametric Lipschitz classes of experts.

Heterogeneous Domain Adaptation (HDA) addresses the transfer learning problems where data from the source and target domains are of different modalities (e.g., texts and images) or feature dimensions (e.g., features extracted with different methods). It is useful for multi-modal data analysis. Traditional domain adaptation algorithms assume that the representations of source and target samples reside in the same feature space, hence are likely to fail in solving the heterogeneous domain adaptation problem. Contemporary state-of-the-art HDA approaches are usually composed of complex optimization objectives for favourable performance and are therefore computationally expensive and less generalizable. To address these issues, we propose a novel Cross-Domain Structure Preserving Projection (CDSPP) algorithm for HDA. As an extension of the classic LPP to heterogeneous domains, CDSPP aims to learn domain-specific projections to map sample features from source and target domains into a common subspace such that the class consistency is preserved and data distributions are sufficiently aligned. CDSPP is simple and has deterministic solutions by solving a generalized eigenvalue problem. It is naturally suitable for supervised HDA but has also been extended for semi-supervised HDA where the unlabeled target domain samples are available. Extensive experiments have been conducted on commonly used benchmark datasets (i.e. Office-Caltech, Multilingual Reuters Collection, NUS-WIDE-ImageNet) for HDA as well as the Office-Home dataset firstly introduced for HDA by ourselves due to its significantly larger number of classes than the existing ones (65 vs 10, 6 and 8). The experimental results of both supervised and semi-supervised HDA demonstrate the superior performance of our proposed method against contemporary state-of-the-art methods.

Not even the best quantum computers or AI from the past and present can help us in predicting the future. The dichotomy of a world under lockdown is that it is also in flux. Nothing is fixed anymore, not your corner office overlooking the city you love, not the position of a country that wants to be the AI superpower of the world. We honestly do not know what the future looks like. Who would have thought that a pandemic will make the world start adopting AI technologies like there is no tomorrow?

Udemy Coupon - Master Python Programming: The Complete Python Bootcamp 2020, Python 100% Hands-on, Hundreds of Python Coding Challenges and Quizzes, Complete Python E-Book. Created by Andrei Dumitrescu, Crystal Mind Academy Students also bought Python 3 Programming: Beginner to Pro Masterclass Docker Essentials for Python Developers Master statistics & machine learning: intuition, math, code Advanced Web Scraping with Python using Scrapy & Splash Neural Networks in Python from Scratch: Complete guide Python Tkinter Masterclass - Learn Python GUI Programming Preview this Course GET COUPON CODE Description ***Fully updated for 2020*** This Python course covers every major Python topic, including Object-Oriented Programming, Decorators, Working with Excel, Working with Databases, Web Scraping, Data Science with Pandas, Data Visualization with Plotly, Network Automation and many more! Course Updates: Update: July, 2020 - NEW Section: Sending Emails with Python (SMTPLIB) Update: June, 2020 - NEW Section: Async IO in Python (async/await, aiohttp, aiofiles, asyncssh) Update: April, 2020 - FIVE NEW Sections of Coding Challenges with Solutions: Data Structures, Flow Control, Functions, Working with Text, CSV and Excel Files. At the end of this course you will MASTER all the Python 3 key concepts starting from scratch and you'll be in the top Python Programmers. Welcome to this practical Python Programming course for learning Python, the most in-demand programming languages across the job market in 2020.

Analyttica TreasureHunt LEAPS is a Data Science Learning & Practice platform. It's innovative application focused courses & hands-on learning techniques, enable users to build their own models with pre-loaded datasets. Our programs facilitate interactions with industry expert & mentors. Get certified & stay ahead of the competition. Learn Data Science & Machine Learning from Zero to Hero in 29 Weeks: Big Bang Data Science Solutions has developed an ecosystem training program to boost your Data Science career to the next level.