Soft continuum arms (SCAs) are increasingly recognized for their ability to safely and effectively interact with complex, unstructured environments. Their ability to conform and apply gentle forces makes them ideal for tasks such as handling delicate objects or working in close proximity to humans [Chen et al., 2022, Zongxing et al., 2020, Banerjee et al., 2018, Chen et al., 2021, V enter and Dirven, 2017]. However, their soft and deformable nature introduces challenges for modeling and control. Learning-enabled methods, such as model-free reinforcement learning (RL), offer a promising solution by learning behaviors directly from data rather than relying on analytically derived models [Falotico et al., 2024]. Despite these advantages, one of the primary obstacles to deploying SCAs in real-world is the sim-to-real transfer, where policies trained in simulation fail to generalize well on physical systems.

Each year, the TIME100 Most Influential Companies list recognizes businesses making extraordinary impact around the world. Enter your company here today. As investors were wowed by ChatGPT and the rapid progress made by artificial intelligence in recent years, money poured into the industry. Generative AI and AI-related startups raised nearly 50 billion in 2023, according to Crunchbase, a business data provider. Already in 2024, share prices for firms that play a role in manufacturing the advanced chips required for the most powerful AI models have skyrocketed, with Nvidia, AMD, and Arm share prices up 27%, 51%, and 82% respectively.

In this paper we revisit the efficacy of knowledge distillation as a function matching and metric learning problem. In doing so we verify three important design decisions, namely the normalisation, soft maximum function, and projection layers as key ingredients. We theoretically show that the projector implicitly encodes information on past examples, enabling relational gradients for the student. We then show that the normalisation of representations is tightly coupled with the training dynamics of this projector, which can have a large impact on the students performance. Finally, we show that a simple soft maximum function can be used to address any significant capacity gap problems. Experimental results on various benchmark datasets demonstrate that using these insights can lead to superior or comparable performance to state-of-the-art knowledge distillation techniques, despite being much more computationally efficient. In particular, we obtain these results across image classification (CIFAR100 and ImageNet), object detection (COCO2017), and on more difficult distillation objectives, such as training data efficient transformers, whereby we attain a 77.2% top-1 accuracy with DeiT-Ti on ImageNet. Code and models are publicly available.

Autonomous systems, such as Unmanned Aerial Vehicles (UAVs), are expected to run complex reinforcement learning (RL) models to execute fully autonomous position-navigation-time tasks within stringent onboard weight and power constraints. We observe that reducing onboard operating voltage can benefit the energy efficiency of both the computation and flight mission, however, it can also result in on-chip bit failures that are detrimental to mission safety and performance. To this end, we propose BERRY, a robust learning framework to improve bit error robustness and energy efficiency for RL-enabled autonomous systems. BERRY supports robust learning, both offline and on-board the UAV, and for the first time, demonstrates the practicality of robust low-voltage operation on UAVs that leads to high energy savings in both compute-level operation and system-level quality-of-flight. We perform extensive experiments on 72 autonomous navigation scenarios and demonstrate that BERRY generalizes well across environments, UAVs, autonomy policies, operating voltages and fault patterns, and consistently improves robustness, efficiency and mission performance, achieving up to 15.62% reduction in flight energy, 18.51% increase in the number of successful missions, and 3.43x processing energy reduction.

It's safe to say that Pinterest doesn't exist without machine learning and A.I.,

You'll start by learning basic concepts of recommender systems, with an overview of different types of recommender engines and how they function. Next, you will see how to build recommender systems with traditional algorithms such as market basket analysis and content- and knowledge-based recommender systems with NLP. The authors then demonstrate techniques such as collaborative filtering using matrix factorization and hybrid recommender systems that incorporate both content-based and collaborative filtering techniques. This is followed by a tutorial on building machine learning-based recommender systems using clustering and classification algorithms like K-means and random forest. The last chapters cover NLP, deep learning, and graph-based techniques to build a recommender engine.

At the US Patent & Trademark Office in Alexandria, Virginia, artificial intelligence (AI) projects are expediting the patent classification process, helping detect fraud, and expanding examiners' searches for similar patents, enabling them to search through more documents in the same amount of time. And every project started with a pilot project. "Proofs of concept (PoCs) are a key approach we use to learn about new technologies, test business value assumptions, de-risk scale project delivery, and inform full production implementation decisions," says USPTO CIO Jamie Holcombe. Once the pilot proves out, he says, the next step is to determine if it can scale. Indian e-commerce vendor Flipkart has followed a similar process before deploying projects that allow for text and visual search through millions of items for customers who speak 11 different languages.

Due to their disordered structure, glasses present a unique challenge in predicting the composition-property relationships. Recently, several attempts have been made to predict the glass properties using machine learning techniques. However, these techniques have the limitations, namely, (i) predictions are limited to the components that are present in the original dataset, and (ii) predictions towards the extreme values of the properties, important regions for new materials discovery, are not very reliable due to the sparse datapoints in this region. To address these challenges, here we present a low complexity neural network (LCNN) that provides improved performance in predicting the properties of oxide glasses. In addition, we combine the LCNN with physical and chemical descriptors that allow the development of universal models that can provide predictions for components beyond the training set. By training on a large dataset (~50000) of glass components, we show the LCNN outperforms state-of-the-art algorithms such as XGBoost. In addition, we interpret the LCNN models using Shapely additive explanations to gain insights into the role played by the descriptors in governing the property. Finally, we demonstrate the universality of the LCNN models by predicting the properties for glasses with new components that were not present in the original training set. Altogether, the present approach provides a promising direction towards accelerated discovery of novel glass compositions.

Florida's short-lived climate change czar, Chief Resilience Officer Julia Nesheiwat, set a clear priority for the state: Protect the real estate market. Nesheiwat's [unpublished] January 2020 report is loaded with proposals aimed to keep Florida's most important industry, real estate, high and dry. Her plan proposes stricter building codes, but also more controversial measures, such as disclosing flood risks to home buyers, providing state-sponsored home buyouts, and requiring vulnerability studies for cities and counties. "Florida's coastal communities and regions do not have time to waste and need a partner at the highest level to help manage and prepare against impending threats," wrote Nesheiwat, who took a job with the Department of Homeland Security after six months in Florida. A case study by McKinsey echoed Nesheiwat's dire projections for much of the state, including the Florida Keys, but also many coastal areas far North of Atlantis [formerly South-Florida].

The word on the street is that artificial intelligence efforts have not been delivering the impressive results everyone has been hoping for. The payoff, however, is likely to be found in well-targeted placements in which AI is handling, in real-time, complicated tasks that would take humans days or weeks to unravel. Managing the flow of telecom traffic is one example, or keeping IT networks up and running is another. Still another, with enormous tangible business value, is the ability to keep supply chains flowing. To that end, for example, Scale AI-- a Canadian consortium of companies, universities, and research centers -- announced $29 million in new investments in AI projects, much of which is aimed at building more intelligence into supply chains.