Robotic legs have bimodal operations: swing phases when the leg needs to move quickly in the air (high-speed, low-force) and stance phases when the leg bears the weight of the system (low-speed, high-force). Sizing a traditional single-ratio actuation system for such extremum operations leads to oversized heavy electric motor and poor energy efficiency, which hinder the capability of legged systems that bear the mass of their actuators and energy source. This paper explores an actuation concept where a hydrostatic transmission is dynamically reconfigured using valves to suit the requirements of each phase of a robotic leg. An analysis of the mass-delay-flow trade-off for the switching valve is presented. Then, a custom actuation system is built and integrated on a robotic leg test bench to evaluate the concept. Experimental results show that 1) small motorized ball valves can make fast transitions between operating modes when designed for this task, 2) the proposed operating principle and control schemes allow for seamless transitions, even during an impact with the ground and 3) the actuator characteristics address the needs of a leg bimodal operation in terms of force, speed and compliance.

Quantum Machine Learning continues to be a highly active area of interest within Quantum Computing. Many of these approaches have adapted classical approaches to the quantum settings, such as QuantumFlow, etc. We push forward this trend and demonstrate an adaption of the Classical Convolutional Neural Networks to quantum systems - namely QuCNN. QuCNN is a parameterised multi-quantum-state based neural network layer computing similarities between each quantum filter state and each quantum data state. With QuCNN, back propagation can be achieved through a single-ancilla qubit quantum routine. QuCNN is validated by applying a convolutional layer with a data state and a filter state over a small subset of MNIST images, comparing the back propagated gradients, and training a filter state against an ideal target state.

We study training of Graph Neural Networks (GNNs) for large-scale graphs. We revisit the premise of using distributed training for billion-scale graphs and show that for graphs that fit in main memory or the SSD of a single machine, out-of-core pipelined training with a single GPU can outperform state-of-the-art (SoTA) multi-GPU solutions. We introduce MariusGNN, the first system that utilizes the entire storage hierarchy -- including disk -- for GNN training. MariusGNN introduces a series of data organization and algorithmic contributions that 1) minimize the end-to-end time required for training and 2) ensure that models learned with disk-based training exhibit accuracy similar to those fully trained in memory. We evaluate MariusGNN against SoTA systems for learning GNN models and find that single-GPU training in MariusGNN achieves the same level of accuracy up to 8x faster than multi-GPU training in these systems, thus, introducing an order of magnitude monetary cost reduction. MariusGNN is open-sourced at www.marius-project.org.

The superior performance of deep learning relies heavily on a large collection of sample data, but the data insufficiency problem turns out to be relatively common in global electricity markets. How to prevent overfitting in this case becomes a fundamental challenge when training deep learning models in different market applications. With this in mind, we propose a general framework, namely Knowledge-Augmented Training (KAT), to improve the sample efficiency, and the main idea is to incorporate domain knowledge into the training procedures of deep learning models. Specifically, we propose a novel data augmentation technique to generate some synthetic data, which are later processed by an improved training strategy. This KAT methodology follows and realizes the idea of combining analytical and deep learning models together. Modern learning theories demonstrate the effectiveness of our method in terms of effective prediction error feedbacks, a reliable loss function, and rich gradient noises. At last, we study two popular applications in detail: user modeling and probabilistic price forecasting. The proposed method outperforms other competitors in all numerical tests, and the underlying reasons are explained by further statistical and visualization results.

Many physical processes such as weather phenomena or fluid mechanics are governed by partial differential equations (PDEs). Modelling such dynamical systems using Neural Networks is an active research field. However, current methods are still very limited, as they do not exploit the knowledge about the dynamical nature of the system, require extensive prior knowledge about the governing equations or are limited to linear or first-order equations. In this work we make the observation that the Method of Lines used to solve PDEs can be represented using convolutions which makes convolutional neural networks (CNNs) the natural choice to parametrize arbitrary PDE dynamics. We combine this parametrization with differentiable ODE solvers to form the NeuralPDE Model, which explicitly takes into account the fact that the data is governed by differential equations. We show in several experiments on toy and real-world data that our model consistently outperforms state-of-the-art models used to learn dynamical systems.

IN BRIEF America's Pacific Northwest National Laboratory is looking into how AI technologies can be used to create a "Digital Police Officer" or "D-PO" in the future. Freedom-of-information requests filed by the Electronic Frontier Foundation show the US Department of Energy-funded lab envisions cops may one day be able to partner up with a virtual crime-fighting assistant. D-PO would be capable of, for instance, tapping into facial recognition systems to alert a police officer on patrol to a suspect nearby, and can even offer advice on how best to apprehend the suspect. The EFF warned against the plod teaming up with software like D-PO, citing concerns over inaccurate facial recognition matches and biased predictive policing policies. "The good news is that in the emails we obtained, one of the authors acknowledges in internal emails that elements like a D-PO taking over driving is a'long way off' and monitoring live drone feeds is'not a near-term capability,' the digital privacy-focused non-profit said.

New Scientist Live, the world's greatest festival of science, finished yesterday after three days of mind-expanding talks and exhilarating experiences. Thousands of people attended each day, meeting robots, trying cutting-edge virtual reality set-ups and learning everything from whether science can save humanity to the design flaws in the human body. Most importantly, we had an amazing time. Here are nine incredible things we learned there. We heard Gillian Forrester explain that we may be able to shed light on the longstanding mystery of how humans evolved the ability to speak by studying these great apes.

With FarmVibes.AI, you can develop rich geospatial insights for agriculture and sustainability. Build models that fuse multiple geospatial and spatiotemporal datasets to obtain insights (e.g. Fusing datasets this way helps generate more robust insights and unlocks new insights that are otherwise not possible without fusion. This repo contains several fusion workflows (published and shown to be key for agriculture related problems) that help you build robust remote sensing, earth observation, and geospatial models with focus on agriculture/farming with ease. Our main focus right now is agriculture and sustainability, which the models are optimized for.

With a focus on safety and the opportunity to greatly enhance operations and the quality of research and learning, educational institutions could see significant gains by implementing computer vision with real-time federated analytics. Computer vision is revolutionizing many industries but is still making inroads into education. That's not surprising, given the historically tight budgets for many educational institutions. As the technology advances and becomes more mainstream in the commercial world, colleges and universities are more likely to be the first adopters in the education realm. With a camera infrastructure already in place on most education campuses, along with adequate district, campus and departmental networks, much of the infrastructure needed for computer vision is already in place.

Modeling multivariate time series as temporal signals over a (possibly dynamic) graph is an effective representational framework that allows for developing models for time series analysis. In fact, discrete sequences of graphs can be processed by autoregressive graph neural networks to recursively learn representations at each discrete point in time and space. Spatiotemporal graphs are often highly sparse, with time series characterized by multiple, concurrent, and long sequences of missing data, e.g., due to the unreliable underlying sensor network. In this context, autoregressive models can be brittle and exhibit unstable learning dynamics. The objective of this paper is, then, to tackle the problem of learning effective models to reconstruct, i.e., impute, missing data points by conditioning the reconstruction only on the available observations. In particular, we propose a novel class of attention-based architectures that, given a set of highly sparse discrete observations, learn a representation for points in time and space by exploiting a spatiotemporal propagation architecture aligned with the imputation task. Representations are trained end-to-end to reconstruct observations w.r.t. the corresponding sensor and its neighboring nodes. Compared to the state of the art, our model handles sparse data without propagating prediction errors or requiring a bidirectional model to encode forward and backward time dependencies. Empirical results on representative benchmarks show the effectiveness of the proposed method.