Non-negative Matrix Factorization (NMF) has proven to be a powerful unsupervised learning method for uncovering hidden features in complex and noisy data sets with applications in data mining, text recognition, dimension reduction, face recognition, anomaly detection, blind source separation, and many other fields. An important input for NMF is the latent dimensionality of the data, that is, the number of hidden features, K, present in the explored data set. Unfortunately, this quantity is rarely known a priori. We utilize a supervised machine learning approach in combination with a recent method for model determination, called NMFk, to determine the number of hidden features automatically. NMFk performs a set of NMF simulations on an ensemble of matrices, obtained by bootstrapping the initial data set, and determines which K produces stable groups of latent features that reconstruct the initial data set well. We then train a Multi-Layer Perceptron (MLP) classifier network to determine the correct number of latent features utilizing the statistics and characteristics of the NMF solutions, obtained from NMFk. In order to train the MLP classifier, a training set of 58,660 matrices with predetermined latent features were factorized with NMFk. The MLP classifier in conjunction with NMFk maintains a greater than 95% success rate when applied to a held out test set. Additionally, when applied to two well-known benchmark data sets, the swimmer and MIT face data, NMFk/MLP correctly recovered the established number of hidden features. Finally, we compared the accuracy of our method to the ARD, AIC and Stability-based methods.

Once upon a time, Japan was widely expected to eclipse the United States as the technological leader of the world. In 1988, the New York Times reporter David Sanger described a group of U.S. computer science experts, meeting to discuss Japan's technological progress. When the group assessed the new generation of computers coming out of Japan, Sanger wrote, "any illusions that America had maintained its wide lead evaporated." Replace "computers" with "artificial intelligence," and "Japan" with "China," and the article could have been written today. In AI Superpowers: China, Silicon Valley, and the New World Order, which unsurprisingly became an instant bestseller, former Google China President Kai-Fu Lee argues that China's unparalleled trove of data, culture of copying, and strong government commitment to artificial intelligence give it a major leg up against the United States.

Among the intrinsic properties of a sand, the surface friction, the compressibility and the strength of individual grains, the particle shape and particle size distributions are known to play a crucial role in its macroscopic properties [1, 2, 3, 4]. Relative density and confining pressure are the most influent state variables for dry granular soils [5] and govern the mechanical behavior of the material to a large extent [6, 7, 8]. The relationship between the particle size distribution, PSD, and the mechanical behavior is not yet fully understood. On one hand, the effects of variations in the PSD are not independent from those produced by variations of other intrinsic properties or state parameters. For example, the state parameter ψ, proposed within the theoretical framework of the critical state of sands [5], helps to distinguish between the contractive or dilatant behavior exhibited by a sand upon triaxial compression. However the critical state line, and hence the value of ψ associated to given void ratio e, changes with the PSD [9]. As another example, there is a complex interplay between size and shape polydispersity, as shown by numerical modeling [10]. On the other hand, linking single quantities (maximum and minimum dry density, critical state void ratio, macroscopic friction angle, stiffness, etc.) to a PSD is not immediate, since the latter is a highly variable curve that is many times long-tailed and/or multi-modal. Descriptors derived from the PSD are not enough to anticipate macroscopic (void ratio, stiffness, friction angle) or microscopic features (average coordination number, fraction of non-contributing particles, etc.) obtained after a given process.

Recent evidence suggests that Golgi cells in the cerebellar granular layer are densely connected to each other with massive gap junctions. Here, we propose that the massive gap junctions between the Golgi cells contribute to the representational complexity of the granular layer of the cerebellum by inducing chaotic dynamics. We construct a model of cerebellar granular layer with diffusion coupling through gap junctions between the Golgi cells, and evaluate the representational capability of the network with the reservoir computing framework. First, we show that the chaotic dynamics induced by diffusion coupling results in complex output patterns containing a wide range of frequency components. Second, the long non-recursive time series of the reservoir represents the passage of time from an external input. These properties of the reservoir enable mapping different spatial inputs into different temporal patterns.

The model uncertainty obtained by variational Bayesian inference with Monte Carlo dropout is prone to miscalibration. In this paper, different logit scaling methods are extended to dropout variational inference to recalibrate model uncertainty. Expected uncertainty calibration error (UCE) is presented as a metric to measure miscalibration. The effectiveness of recalibration is evaluated on CIFAR-10/100 and SVHN for recent CNN architectures. Experimental results show that logit scaling considerably reduce miscalibration by means of UCE. Well-calibrated uncertainty enables reliable rejection of uncertain predictions and robust detection of out-of-distribution data.

System identification is a key step for model-based control, estimator design, and output prediction. This work considers the offline identification of partially observed nonlinear systems. We empirically show that the certainty-equivalent approximation to expectation-maximization can be a reliable and scalable approach for high-dimensional deterministic systems, which are common in robotics. We formulate certainty-equivalent expectation-maximization as block coordinate-ascent, and provide an efficient implementation. The algorithm is tested on a simulated system of coupled Lorenz attractors, demonstrating its ability to identify high-dimensional systems that can be intractable for particle-based approaches. Our approach is also used to identify the dynamics of an aerobatic helicopter. By augmenting the state with unobserved fluid states, a model is learned that predicts the acceleration of the helicopter better than state-of-the-art approaches. The codebase for this work is available at https://github.com/sisl/CEEM.

A strange'swarm' of small earthquakes in California that lasted nearly four years was triggered by fluid spilling into the fault system from underground reservoirs, scientists say. The naturally occurring injection of underground fluid drove the earthquake swarm near Cahuilla in Southern California, which occurred in bursts around the region from early 2016 to late 2019. US scientists have made their conclusions based on earthquake detection algorithms that catalogued more than 22,000 individual seismic events that made up the'swarm'. Using machine learning to plot the location, depth and size of the tremors, the researchers generated a 3D representation of the underlying fault zone. The results suggested dynamic pressure changes from natural fluid injections deep below the surface largely controlled the prolonged evolution of the Cahuilla swarm.

Artificial intelligence (AI), in many different industries, is about to unleash the next era of digital innovation, and the power and energy (P&U) industries are no exception. The distribution of energy is not a linear equation anymore. As new sources of energy and data expand, utility providers are seeking to take a more holistic approach to understand and manage their resources and involve active clients on the edge of the grid. In a broad sense, AI makes it possible for the stakeholders to recognize the operational dynamics when it arrives in the management of power supplies and distributed resources. Utilities can harness comprehensive, real-time models to provide a more robust and efficient grid with AI-powered solutions, machine learning functioning underneath scenes to investigate different data sources, and to provide industry and customers with actionable insights.

Nowadays, liquid rocket engines use closed-loop control at most near steady operating conditions. The control of the transient phases is traditionally performed in open-loop due to highly nonlinear system dynamics. This situation is unsatisfactory, in particular for reusable engines. The open-loop control system cannot provide optimal engine performance due to external disturbances or the degeneration of engine components over time. In this paper, we study a deep reinforcement learning approach for optimal control of a generic gas-generator engine's continuous start-up phase. It is shown that the learned policy can reach different steady-state operating points and convincingly adapt to changing system parameters. A quantitative comparison with carefully tuned open-loop sequences and PID controllers is included. The deep reinforcement learning controller achieves the highest performance and requires only minimal computational effort to calculate the control action, which is a big advantage over approaches that require online optimization, such as model predictive control. control.

In this paper, we propose a new end-to-end methodology to optimize the energy performance and the comfort, air quality and hygiene of large buildings. A metamodel based on a Transformer network is introduced and trained using a dataset sampled with a simulation program. Then, a few physical parameters and the building management system settings of this metamodel are calibrated using the CMA-ES optimization algorithm and real data obtained from sensors. Finally, the optimal settings to minimize the energy loads while maintaining a target thermal comfort and air quality are obtained using a multi-objective optimization procedure. The numerical experiments illustrate how this metamodel ensures a significant gain in energy efficiency while being computationally much more appealing than models requiring a huge number of physical parameters to be estimated.