At first glance, this is a natural summary, inheriting both the statistical amenability of the sample mean (Shalev-Shwartz and Ben-David, 2014) and the wide arsenal of optimization algorithms designed specifically for finite sum objectives (Le Roux et al., 2012; Defazio et al., 2014; Johnson and Zhang, 2013; Reddi et al., 2016). However, as modern learning systems are deployed in critical domain applications such as energy planning (Guigues and Sagastizábal, 2013), materials engineering (Yeh, 2006), and financial regulation (He et al., 2022), safe and reliable performance in "worst-case" scenarios is paramount. This imperative can be modeled by alternate risk measures (statistical functionals of the loss distribution), particularly those that encapsulate the behavior of the distribution's upper tail.

As sharing images in an instant message is a crucial factor, there has been active research on learning a image-text multi-modal dialogue model. However, training a well-generalized multi-modal dialogue model is challenging because existing multi-modal dialogue datasets contain a small number of data, limited topics, and a restricted variety of images per dialogue. In this paper, we present a multi-modal dialogue dataset creation pipeline that involves matching large-scale images to dialogues based on CLIP similarity. Using this automatic pipeline, we propose a large-scale multi-modal dialogue dataset, DialogCC, which covers diverse real-world topics and various images per dialogue. With extensive experiments, we demonstrate that training a multi-modal dialogue model with our dataset can improve generalization performance. Additionally, existing models trained with our dataset achieve state-of-the-art performance on image and text retrieval tasks. The source code and the dataset will be released after publication.

AMP Robotics uses automation and artificial intelligence (AI) to sort materials within waste streams. We asked CEO Matanya Horowitz how this works, how data can be utilised and the ways automated sorting could impact the packaging industry. AMP Robotics developed an AI platform (AMP Neuron) to distinguish recyclable materials from waste. How did you come up with the idea? Ever since I was a child I've been interested in robotics and the origins of intelligence.

The dramatic increase in using of Artificial Intelligence (AI) and traditional machine learning methods in different fields of science becomes an essential asset in the development of the chemical industry, including pharmaceutical, agro biotech, and other chemical companies. However, the application of AI in these fields is not straightforward and requires excellent knowledge of chemistry. Thus, there is a strong need to train and prepare a new generation of scientists who have skills both in machine learning and in chemistry and can advance medicinal chemistry, which is the prime goal of the AIDD proposal. Research WPs include sixteen topics selected to cover the key innovative directions in machine learning in chemistry. Fellows employed will be supervised by academics who have excellent complementary expertise and contributed some of the fundamental AI algorithms which are used billions of times per day in the world, and leading EU Pharma companies who are in charge of new medicine and public health.

Density based representations of atomic environments that are invariant under Euclidean symmetries have become a widely used tool in the machine learning of interatomic potentials, broader data-driven atomistic modelling and the visualisation and analysis of materials datasets.The standard mechanism used to incorporate chemical element information is to create separate densities for each element and form tensor products between them. This leads to a steep scaling in the size of the representation as the number of elements increases. Graph neural networks, which do not explicitly use density representations, escape this scaling by mapping the chemical element information into a fixed dimensional space in a learnable way. We recast this approach as tensor factorisation by exploiting the tensor structure of standard neighbour density based descriptors. In doing so, we form compact tensor-reduced representations whose size does not depend on the number of chemical elements, but remain systematically convergeable and are therefore applicable to a wide range of data analysis and regression tasks.

Valuing mineral assets is a challenging task that is highly dependent on the supply (geological) uncertainty surrounding resources and reserves, and the uncertainty of demand (commodity prices). In this work, a graph-based reasoning, modeling and solution approach is proposed to jointly address mineral asset valuation and mine plan scheduling and optimization under supply and demand uncertainty in the "mining complex" framework. Three graph-based solutions are proposed: (i) a neural branching policy that learns a block-sampling ore body representation, (ii) a guiding policy that learns to explore a heuristic selection tree, (iii) a hyper-heuristic that manages the value/supply chain optimization and dynamics modeled as a graph structure. Results on two large-scale industrial mining complexes show a reduction of up to three orders of magnitude in primal suboptimality, execution time, and number of iterations, and an increase of up to 40% in the mineral asset value.

Construction defects are costly for the economy. The cost of defect elimination is between 2% and 12.4% of the total cost of construction [1] and much time and effort is required to inspect construction sites and document defects [2]. Automating the inspection of construction projects would free up resources and may even enable more frequent inspections, leading to more efficient construction projects. The progress in CV and ML may enable the complete automation of this process in the future. Although deep learning is applied to many different fields, research into image-based defect detection using deep learning is still limited in the construction industry, despite its large size, and focuses on security, progress, and productivity. In contrast, there appear to be relatively few publications on methods utilized for object detection in quality assurance in construction. So far, the research into detecting defects has been mainly limited to defects occurring in the maintenance phase of infrastructure facilities such as roads, bridges, and sewer systems.

Tree-based machine learning algorithms provide the most precise assessment of the feasibility for a country to export a target product given its export basket. However, the high number of parameters involved prevents a straightforward interpretation of the results and, in turn, the explainability of policy indications. In this paper, we propose a procedure to statistically validate the importance of the products used in the feasibility assessment. In this way, we are able to identify which products, called explainers, significantly increase the probability to export a target product in the near future. The explainers naturally identify a low dimensional representation, the Feature Importance Product Space, that enhances the interpretability of the recommendations and provides out-of-sample forecasts of the export baskets of countries. Interestingly, we detect a positive correlation between the complexity of a product and the complexity of its explainers.

In this paper the implementation of piezoelectrics to a state-of-the-art wafer gripper is investigated. The objective is to propose and validate a solution method, which includes a mechanical design and control system, to achieve at least 5% damping for two eigenmodes of a wafer gripper. This objective serves as a 'proof of concept' to show the possibilities of implementing a state-of-the-art damping method to an industrial application, which in turn can be used to dampen different thin structures. The coupling relation between the piezoelectrics and their host structure were used to design the placement of the piezoelectric patches, together with modal analysis data of the a state-of-the-art wafer gripper. This data had been measured through an experimental setup. Active damping has been succesfully implemented onto the wafer gripper where positive position feedback (PPF) is used as a control algorithm to dampen two eigenmodes.

Pavement Distress Recognition (PDR) is an important step in pavement inspection and can be powered by image-based automation to expedite the process and reduce labor costs. Pavement images are often in high-resolution with a low ratio of distressed to non-distressed areas. Advanced approaches leverage these properties via dividing images into patches and explore discriminative features in the scale space. However, these approaches usually suffer from information loss during image resizing and low efficiency due to complex learning frameworks. In this paper, we propose a novel and efficient method for PDR. A light network named the Kernel Inversed Pyramidal Resizing Network (KIPRN) is introduced for image resizing, and can be flexibly plugged into the image classification network as a pre-network to exploit resolution and scale information. In KIPRN, pyramidal convolution and kernel inversed convolution are specifically designed to mine discriminative information across different feature granularities and scales. The mined information is passed along to the resized images to yield an informative image pyramid to assist the image classification network for PDR. We applied our method to three well-known Convolutional Neural Networks (CNNs), and conducted an evaluation on a large-scale pavement image dataset named CQU-BPDD. Extensive results demonstrate that KIPRN can generally improve the pavement distress recognition of these CNN models and show that the simple combination of KIPRN and EfficientNet-B3 significantly outperforms the state-of-the-art patch-based method in both performance and efficiency.