A.I. image generators are divisive. But few can deny that they have gotten really good. Within seconds, you can type in a prompt to make a photorealistic image of Donald Trump getting arrested or turn your strangest idea into something tangible. Over the coming years, A.I. companies will release even more advanced models that will remind us that this is just the beginning. At least one of these tools will be different in an important way: It will be prohibited from seeing 80 million of the images that helped teach its predecessors to draw and paint.

With increased availability of next-generation technology and data mining tools, insurance company use of external consumer data sets and artificial intelligence (AI) and machine learning (ML)-enabled analytical models is rapidly expanding and accelerating. Insurers have initially targeted key business areas such as underwriting, pricing, fraud detection, marketing distribution and claims management to leverage technical innovations to realize enhanced risk management, revenue growth and improved profitability. At the same time, regulators worldwide are intensifying their focus on the governance and fairness challenges presented by these complex, highly innovative tools – specifically, the potential for unintended bias against protected classes of people. In the United States, the Colorado Division of Insurance recently issued a first-in-the-nation draft regulation to support the implementation of a 2021 law passed by the state's legislature.1 This law (SB21-169) prohibits life insurers from using external personal data and information sources (ECDIS), or employing algorithms and models that use ECDIS, where the resulting impact of such use is unfair discrimination against consumers on the basis of race, color, national or ethnic origin, religion, sex, sexual orientation, disability, gender identity or gender expression.2

Physics-informed neural networks have emerged as an alternative method for solving partial differential equations. However, for complex problems, the training of such networks can still require high-fidelity data which can be expensive to generate. To reduce or even eliminate the dependency on high-fidelity data, we propose a novel multi-fidelity architecture which is based on a feature space shared by the low- and high-fidelity solutions. In the feature space, the projections of the low-fidelity and high-fidelity solutions are adjacent by constraining their relative distance. The feature space is represented with an encoder and its mapping to the original solution space is effected through a decoder. The proposed multi-fidelity approach is validated on forward and inverse problems for steady and unsteady problems described by partial differential equations.

Publicly available collections of drug-like molecules have grown to comprise 10s of billions of possibilities in recent history due to advances in chemical synthesis. Traditional methods for identifying ``hit'' molecules from a large collection of potential drug-like candidates have relied on biophysical theory to compute approximations to the Gibbs free energy of the binding interaction between the drug to its protein target. A major drawback of the approaches is that they require exceptional computing capabilities to consider for even relatively small collections of molecules. Hyperdimensional Computing (HDC) is a recently proposed learning paradigm that is able to leverage low-precision binary vector arithmetic to build efficient representations of the data that can be obtained without the need for gradient-based optimization approaches that are required in many conventional machine learning and deep learning approaches. This algorithmic simplicity allows for acceleration in hardware that has been previously demonstrated for a range of application areas. We consider existing HDC approaches for molecular property classification and introduce two novel encoding algorithms that leverage the extended connectivity fingerprint (ECFP) algorithm. We show that HDC-based inference methods are as much as 90 times more efficient than more complex representative machine learning methods and achieve an acceleration of nearly 9 orders of magnitude as compared to inference with molecular docking. We demonstrate multiple approaches for the encoding of molecular data for HDC and examine their relative performance on a range of challenging molecular property prediction and drug-protein binding classification tasks. Our work thus motivates further investigation into molecular representation learning to develop ultra-efficient pre-screening tools.

Since the late 1950s, when the first artificial satellite was launched, the number of Resident Space Objects has steadily increased. It is estimated that around one million objects larger than one cm are currently orbiting the Earth, with only thirty thousand larger than ten cm being tracked. To avert a chain reaction of collisions, known as Kessler Syndrome, it is essential to accurately track and predict debris and satellites' orbits. Current approximate physics-based methods have errors in the order of kilometers for seven-day predictions, which is insufficient when considering space debris, typically with less than one meter. This failure is usually due to uncertainty around the state of the space object at the beginning of the trajectory, forecasting errors in environmental conditions such as atmospheric drag, and unknown characteristics such as the mass or geometry of the space object. Operators can enhance Orbit Prediction accuracy by deriving unmeasured objects' characteristics and improving non-conservative forces' effects by leveraging data-driven techniques, such as Machine Learning. In this survey, we provide an overview of the work in applying Machine Learning for Orbit Determination, Orbit Prediction, and atmospheric density modeling.

Noname manuscript No. (will be inserted by the editor) Abstract We study multi-modal few-shot object detection novel classes present in few-shot visual examples, which are (FSOD) in this paper, using both few-shot visual examples then used to learn the text classifier. Knowledge distillation and class semantic information for detection, which are is introduced to learn the soft prompt generator without using complementary to each other by definition. Most of the previous human prior knowledge of class names, which may not works on multi-modal FSOD are fine-tuning-based be available for rare classes. Our insight is that the few-shot which are inefficient for online applications. Moreover, support images naturally include related context information these methods usually require expertise like class names to and semantics of the class. We comprehensively evaluate the extract class semantic embedding, which are hard to get proposed multi-modal FSOD models on multiple few-shot for rare classes. Our approach is motivated by the highlevel object detection benchmarks, achieving promising results. Specifically, we combine the few-shot visual classifier and text classifier learned via meta-learning and 1 Introduction prompt-based learning respectively to build the multi-modal classifier and detection models. In addition, to fully exploit Object detection is one of the most fundamental tasks the pre-trained language models, we propose meta-learningbased in computer vision. Recently, deep learning-based methods cross-modal prompting to generate soft prompts for [39, 38, 32, 3] have achieved great progress in this field.

Existing foundation models are trained on copyrighted material. Deploying these models can pose both legal and ethical risks when data creators fail to receive appropriate attribution or compensation. In the United States and several other countries, copyrighted content may be used to build foundation models without incurring liability due to the fair use doctrine. However, there is a caveat: If the model produces output that is similar to copyrighted data, particularly in scenarios that affect the market of that data, fair use may no longer apply to the output of the model. In this work, we emphasize that fair use is not guaranteed, and additional work may be necessary to keep model development and deployment squarely in the realm of fair use. First, we survey the potential risks of developing and deploying foundation models based on copyrighted content. We review relevant U.S. case law, drawing parallels to existing and potential applications for generating text, source code, and visual art. Experiments confirm that popular foundation models can generate content considerably similar to copyrighted material. Second, we discuss technical mitigations that can help foundation models stay in line with fair use. We argue that more research is needed to align mitigation strategies with the current state of the law. Lastly, we suggest that the law and technical mitigations should co-evolve. For example, coupled with other policy mechanisms, the law could more explicitly consider safe harbors when strong technical tools are used to mitigate infringement harms. This co-evolution may help strike a balance between intellectual property and innovation, which speaks to the original goal of fair use. But we emphasize that the strategies we describe here are not a panacea and more work is needed to develop policies that address the potential harms of foundation models.

The rising use of artificial intelligence and machine learning technologies to power intelligent systems has led to a growing desire for automating, accelerating, and enhancing decision-making processes in safety-critical applications. These technologies offer decision-makers the ability to gain an information and decision-making advantage at the speed of machines. However, in safety-constrained decision-making, it is crucial to estimate and factor in the level of certainty and doubt associated with each classification decision[3]. In such scenarios, even small chances of risky outcomes may have a significant impact on classification decisions, regardless of the most probable predicted outcome, and safety-critical applications need to be sensitive to such tail probabilities [1], [2]. Furthermore, in the(multi-class) classification decision setting when model-assigned probabilities are close to uniformly distributed, we have cause to doubt the model's prediction, even if it is accurate. Moreover, from a theoretical view of probability, we have cause to doubt the model architecture if the greatest predicted probability is arbitrarily close to the second greatest probability. An intuitive score that can capture this sense of certainty and doubt about our predictions is desirable.

The usage and impact of deep learning for cleaner production and sustainability purposes remain little explored. This work shows how deep learning can be harnessed to increase sustainability in production and product usage. Specifically, we utilize deep learning-based computer vision to determine the wear states of products. The resulting insights serve as a basis for novel product-service systems with improved integration and result orientation. Moreover, these insights are expected to facilitate product usage improvements and R&D innovations. We demonstrate our approach on two products: machining tools and rotating X-ray anodes. From a technical standpoint, we show that it is possible to recognize the wear state of these products using deep-learning-based computer vision. In particular, we detect wear through microscopic images of the two products. We utilize a U-Net for semantic segmentation to detect wear based on pixel granularity. The resulting mean dice coefficients of 0.631 and 0.603 demonstrate the feasibility of the proposed approach. Consequently, experts can now make better decisions, for example, to improve the machining process parameters. To assess the impact of the proposed approach on environmental sustainability, we perform life cycle assessments that show gains for both products. The results indicate that the emissions of CO2 equivalents are reduced by 12% for machining tools and by 44% for rotating anodes. This work can serve as a guideline and inspire researchers and practitioners to utilize computer vision in similar scenarios to develop sustainable smart product-service systems and enable cleaner production.

An additive manufacturing (AM) process, like laser powder bed fusion, allows for the fabrication of objects by spreading and melting powder in layers until a freeform part shape is created. In order to improve the properties of the material involved in the AM process, it is important to predict the material characterization property as a function of the processing conditions. In thermoelectric materials, the power factor is a measure of how efficiently the material can convert heat to electricity. While earlier works have predicted the material characterization properties of different thermoelectric materials using various techniques, implementation of machine learning models to predict the power factor of bismuth telluride (Bi2Te3) during the AM process has not been explored. This is important as Bi2Te3 is a standard material for low temperature applications. Thus, we used data about manufacturing processing parameters involved and in-situ sensor monitoring data collected during AM of Bi2Te3, to train different machine learning models in order to predict its thermoelectric power factor. We implemented supervised machine learning techniques using 80% training and 20% test data and further used the permutation feature importance method to identify important processing parameters and in-situ sensor features which were best at predicting power factor of the material. Ensemble-based methods like random forest, AdaBoost classifier, and bagging classifier performed the best in predicting power factor with the highest accuracy of 90% achieved by the bagging classifier model. Additionally, we found the top 15 processing parameters and in-situ sensor features to characterize the material manufacturing property like power factor. These features could further be optimized to maximize power factor of the thermoelectric material and improve the quality of the products built using this material.