Machine Learning (ML) increasingly informs the allocation of opportunities to individuals and communities in areas such as lending, education, employment, and beyond. Such decisions often impact their subjects' future characteristics and capabilities in an a priori unknown fashion. The decision-maker, therefore, faces exploration-exploitation dilemmas akin to those in multi-armed bandits. Following prior work, we model communities as arms. To capture the long-term effects of ML-based allocation decisions, we study a setting in which the reward from each arm evolves every time the decision-maker pulls that arm. We focus on reward functions that are initially increasing in the number of pulls but may become (and remain) decreasing after a certain point. We argue that an acceptable sequential allocation of opportunities must take an arm's potential for growth into account. We capture these considerations through the notion of policy regret, a much stronger notion than the often-studied external regret, and present an algorithm with provably sub-linear policy regret for sufficiently long time horizons. We empirically compare our algorithm with several baselines and find that it consistently outperforms them, in particular for long time horizons.

Effectively predicting molecular interactions has the potential to accelerate molecular dynamics by multiple orders of magnitude and thus revolutionize chemical simulations. Graph neural networks (GNNs) have recently shown great successes for this task, overtaking classical methods based on fixed molecular kernels. However, they still appear very limited from a theoretical perspective, since regular GNNs cannot distinguish certain types of graphs. In this work we close this gap between theory and practice. We show that GNNs with directed edge embeddings and two-hop message passing are indeed universal approximators for predictions that are invariant to global rotation and translation, and equivariant to permutation. We then leverage these insights and multiple structural improvements to propose the geometric message passing neural network (GemNet). We demonstrate the benefits of the proposed changes in multiple ablation studies. GemNet outperforms previous models on the COLL and MD17 molecular dynamics datasets by 34 % and 40 %, performing especially well on the most challenging molecules.

While Moore's law has driven exponential computing power expectations, its nearing end calls for new avenues for improving the overall system performance. One of these avenues is the exploration of new alternative brain-inspired computing architectures that promise to achieve the flexibility and computational efficiency of biological neural processing systems. Within this context, neuromorphic intelligence represents a paradigm shift in computing based on the implementation of spiking neural network architectures tightly co-locating processing and memory. In this paper, we provide a comprehensive overview of the field, highlighting the different levels of granularity present in existing silicon implementations, comparing approaches that aim at replicating natural intelligence (bottom-up) versus those that aim at solving practical artificial intelligence applications (top-down), and assessing the benefits of the different circuit design styles used to achieve these goals. First, we present the analog, mixed-signal and digital circuit design styles, identifying the boundary between processing and memory through time multiplexing, in-memory computation and novel devices. Next, we highlight the key tradeoffs for each of the bottom-up and top-down approaches, survey their silicon implementations, and carry out detailed comparative analyses to extract design guidelines. Finally, we identify both necessary synergies and missing elements required to achieve a competitive advantage for neuromorphic edge computing over conventional machine-learning accelerators, and outline the key elements for a framework toward neuromorphic intelligence.

The Robot Teleoperativo is a new robotics result achieved at IIT-Istituto Italiano di Tecnologia and combining the rugged locomotion of HyQReal robot with dexterous and powerful manipulation assured by a new robotic arm, controlled by immersive VR visualization and haptic teleoperation. It represents a significant contribution to the state-of-the-art robotics dedicated to intervention on unstructured, difficult terrain environments, requiring powerful capabilities. The human operator can always be in control, not being replaced by the robot but substituted and assisted by it, in the case of situations where humans may be exposed to risks for their health, such as disaster response or emergency in nuclear, marine, chemical, oil-&-gas, environments. In a new video, researchers show the achieved results: the Robot Teleoperativo is able to open doors, access fire equipment, gather precious items, navigate in the dark, and walk over difficult terrain. The video was showed during the international conference ICRA 2021, on May 31st.

As data accessibility and analysis capabilities have rapidly advanced in recent years, new digital platforms driven by artificial intelligence (AI) and machine learning (ML) are increasingly finding practical applications in industry. "Data are so readily available now. Several years ago, we didn't have the manipulation capability, the broad platform or cloud capacity to really work with large volumes of data. We've got that now, so that has been huge in making AI more practical," says Paige Morse, industry marketing director for chemicals at Aspen Technology, Inc. (Bedford, Mass.; www.aspentech.com). While AI and ML have been part of the digitalization discussion for many years, these technologies have not seen a great deal of practical application in the chemical process industries (CPI) until relatively recently, says Don Mack, global alliance manager at Siemens Industry, Inc. (Alpharetta, Ga.; www.industry.usa.siemens.com). "In order for AI to work correctly, it needs data. Control systems and historians in chemical plants have a lot of data available, but in many cases, those data have just been sitting dormant, not really being put to good use. However, new digitalization tools enable us to address some use cases for AI that until recently just weren't possible." This convergence of technologies, from smart sensors to high-performance computing and cloud storage, along with advances in data science, deep learning and access to free and open-source software, have enabled the field of industrial AI to move beyond pure research to practical applications with business benefits, says Samvith Rao, chemical and petroleum industry manager at MathWorks (Natick, Mass.; www.mathworks.com).

This image shows a traditional water meter that's been converted into a web API, using a cheap ESP32 camera and machine learning to understand the dials and numbers. I expect there are going to be billions of devices like this deployed over the next decade, not only for water meters but for any older device that has a dial, counter, or display. I've already heard from multiple teams who have legacy hardware that they need to monitor, in environments as varied as oil refineries, crop fields, office buildings, cars, and homes. Some of the devices are decades old, so until now the only option to enable remote monitoring and data gathering was to replace the system entirely with a more modern version. This is often too expensive, time-consuming, or disruptive to contemplate.

Researchers have switched on the world's fastest AI supercomputer, delivering nearly four exaFLOPS of AI performance for more than 7,000 researchers. Perlmutter, officially dedicated today at the National Energy Research Scientific Computing Centre (NERSC), is a supercomputer that will help piece together a 3D map of the universe, probe subatomic interactions for green energy sources, and much more. The supercomputer is made up of 6,159 NVIDIA A100 Tensor Core GPUs, which makes it the largest A100-powered system in the world. Over two dozen applications are getting ready to be among the first to use the system based at Lawrence Berkeley National Lab. In one project, the supercomputer will help assemble the largest 3D map of the visible universe to date.

Recently, the combination of robust one-dimensional convolutional neural networks (1-D CNNs) and Raman spectroscopy has shown great promise in rapid identification of unknown substances with good accuracy. Using this technique, researchers can recognize a pure compound and distinguish it from unknown substances in a mixture. The novelty of this approach is that the trained neural network operates automatically without any pre- or post-processing of data. Some studies have attempted to extend this technique to the classification of pure compounds in an unknown mixture. However, the application of 1-D CNNs has typically been restricted to binary classifications of pure compounds. Here we will highlight a new approach in spectral recognition and quantification of chemical components in a multicomponent mixture. Two 1-D CNN models, RaMixNet I and II, have been developed for this purpose. The former is for rapid classification of components in a mixture while the latter is for quantitative determination of those constituents. In the proposed method, there is no limit to the number of compounds in a mixture. A data augmentation method is also introduced by adding random baselines to the Raman spectra. The experimental results revealed that the classification accuracy of RaMixNet I and II is 100% for analysis of unknown test mixtures; at the same time, the RaMixNet II model may achieve a regression accuracy of 88% for the quantification of each component.

In adversarial data collection (ADC), a human workforce interacts with a model in real time, attempting to produce examples that elicit incorrect predictions. Researchers hope that models trained on these more challenging datasets will rely less on superficial patterns, and thus be less brittle. However, despite ADC's intuitive appeal, it remains unclear when training on adversarial datasets produces more robust models. In this paper, we conduct a large-scale controlled study focused on question answering, assigning workers at random to compose questions either (i) adversarially (with a model in the loop); or (ii) in the standard fashion (without a model). Across a variety of models and datasets, we find that models trained on adversarial data usually perform better on other adversarial datasets but worse on a diverse collection of out-of-domain evaluation sets. Finally, we provide a qualitative analysis of adversarial (vs standard) data, identifying key differences and offering guidance for future research.

Non-intrusive load monitoring (NILM) is a well-known single-channel blind source separation problem that aims to decompose the household energy consumption into itemised energy usage of individual appliances. In this way, considerable energy savings could be achieved by enhancing household's awareness of energy usage. Recent investigations have shown that deep neural networks (DNNs) based approaches are promising for the NILM task. Nevertheless, they normally ignore the inherent properties of appliance operations in the network design, potentially leading to implausible results. We are thus motivated to develop the dual Deep Neural Networks (dual-DNN), which aims to i) take advantage of DNNs' learning capability of latent features and ii) empower the DNN architecture with identification ability of universal properties. Specifically in the design of dual-DNN, we adopt one subnetwork to measure power ratings of different appliances' operation states, and the other subnetwork to identify the running states of target appliances. The final result is then obtained by multiplying these two network outputs and meanwhile considering the multi-state property of household appliances. To enforce the sparsity property in appliance's state operating, we employ median filtering and hard gating mechanisms to the subnetwork for state identification. Compared with the state-of-the-art NILM methods, our dual-DNN approach demonstrates a 21.67% performance improvement in average on two public benchmark datasets.