Machine learning (ML) and artificial intelligence (AI) algorithms are now being used to automate the discovery of physics principles and governing equations from measurement data alone. However, positing a universal physical law from data is challenging without simultaneously proposing an accompanying discrepancy model to account for the inevitable mismatch between theory and measurements. By revisiting the classic problem of modeling falling objects of different size and mass, we highlight a number of subtle and nuanced issues that must be addressed by modern data-driven methods for the automated discovery of physics. Specifically, we show that measurement noise and complex secondary physical mechanisms, such as unsteady fluid drag forces, can obscure the underlying law of gravitation, leading to an erroneous model. Without proposing an appropriate discrepancy model to handle these drag forces, the data supports an Aristotelian, versus a Galilean, theory of gravitation. Using the sparse identification of nonlinear dynamics (SINDy) algorithm, with the additional assumption that each separate falling object is governed by the same physical law, we are able to identify a viable discrepancy model to account for the fluid dynamic forces that explain the mismatch between a posited universal law of gravity and the measurement data. This work highlights the fact that the simple application of ML/AI will generally be insufficient to extract universal physical laws without further modification.

Researchers at Argonne National Laboratory are working on optimization models that use machine learning, a form of artificial intelligence, to simulate the electric system and the severity of various problems. In a region with 1,000 electric power assets, an outage of just three assets can produce nearly a billion scenarios of potential failure. Argonne researchers apply machine learning to inform more reliable grid planning and operations. The following article is part of a series on Argonne National Laboratory's efforts to use the predictive power of artificial intelligence, specifically machine learning, to advance discoveries in a broad range of scientific disciplines. How much electricity will you need tomorrow?

From discovering drugs, to locating black holes, to finding safer nuclear energy sources, high performance computing systems around the world have enabled breakthroughs across all scientific domains. Japan's fastest supercomputer, ABCI, powered by NVIDIA Tensor Core GPUs, enables similar breakthroughs by taking advantage of AI. The system is the world's first large-scale, open AI infrastructure serving researchers, engineers and industrial users to advance their science. The software used to drive these advances is as critical as the servers the software runs on. However, installing an application on an HPC cluster is complex and time consuming.

In this talk I will discuss some of the long-term challenges emerging with the effort of making deep learning a relevant tool for controlled scientific discovery in many-body quantum physics. The current state of the art of deep neural quantum states and learning tools will be discussed in connection with open challenging problems in condensed matter physics, including frustrated magnetism and quantum dynamics. Variational algorithms for a gate-based quantum computer, like the QAOA, prescribe a fixed circuit ansatz --- up to a set of continuous parameters --- that is designed to find a low-energy state of a given target Hamiltonian. After reviewing the relevant aspects of the QAOA, I will describe attempts to make the algorithm more efficient. The strategies I will explore are 1) tuning the variational objective function away from the energy expectation value, 2) analytical estimates that allow elimination of some of the gates in the QAOA circuit, and 3) using methods of machine learning to search the design space of nearby circuits for improvements to the original ansatz.

Around the world, and particularly in Australia, energy traders are trying to get their minds, and their algorithms, around the complexities of trading in variable wind and solar projects and super-fast battery storage installations. Maybe they should give up now, and hand it over to artificial intelligence. US-based software-as-a-service platform provider AMS says automated trading systems for batteries and renewable energy projects using deep learning and artificial intelligence can out-compete the best human traders, by around a factor of five. With the deployment of large-scale energy storage systems occurring at an ever-increasing rate, this is critical – not just for the ability to make money out of the markets, but also for the ongoing operation of the National Electricity Market itself. Traditional generators only need to maximise their generation during periods of sufficiently high energy prices.

This research investigates an equation of productivity for workflows regarding its robustness towards the definition of workflows as probabilistic distributions. The equation was formulated across its derivations through a theoretical framework about information theory, probabilities and complex adaptive systems. By defining the productivity equation for organism-object interactions, workflows mathematical derivations can be predicted and monitored without strict empirical methods and allows workflow flexibility for organism-object environments.

Training deep neural networks with the error backpropagation algorithm is considered implausible from a biological perspective. Numerous recent publications suggest elaborate models for biologically plausible variants of deep learning, typically defining success as reaching around 98% test accuracy on the MNIST data set. Here, we investigate how far we can go on digit (MNIST) and object (CIFAR10) classification with biologically plausible, local learning rules in a network with one hidden layer and a single readout layer. The hidden layer weights are either fixed (random or random Gabor filters) or trained with unsupervised methods (PCA, ICA or Sparse Coding) that can be implemented by local learning rules. The readout layer is trained with a supervised, local learning rule. We first implement these models with rate neurons. This comparison reveals, first, that unsupervised learning does not lead to better performance than fixed random projections or Gabor filters for large hidden layers. Second, networks with localized receptive fields perform significantly better than networks with all-to-all connectivity and can reach backpropagation performance on MNIST. We then implement two of the networks - fixed, localized, random & random Gabor filters in the hidden layer - with spiking leaky integrate-and-fire neurons and spike timing dependent plasticity to train the readout layer. These spiking models achieve > 98.2% test accuracy on MNIST, which is close to the performance of rate networks with one hidden layer trained with backpropagation. The performance of our shallow network models is comparable to most current biologically plausible models of deep learning. Furthermore, our results with a shallow spiking network provide an important reference and suggest the use of datasets other than MNIST for testing the performance of future models of biologically plausible deep learning.

Intelligent agents need a physical understanding of the world to predict the impact of their actions in the future. While learning-based models of the environment dynamics have contributed to significant improvements in sample efficiency compared to model-free reinforcement learning algorithms, they typically fail to generalize to system states beyond the training data, while often grounding their predictions on non-interpretable latent variables. We introduce Interactive Differentiable Simulation (IDS), a differentiable physics engine, that allows for efficient, accurate inference of physical properties of rigid-body systems. Integrated into deep learning architectures, our model is able to accomplish system identification using visual input, leading to an interpretable model of the world whose parameters have physical meaning. We present experiments showing automatic task-based robot design and parameter estimation for nonlinear dynamical systems by automatically calculating gradients in IDS. When integrated into an adaptive model-predictive control algorithm, our approach exhibits orders of magnitude improvements in sample efficiency over model-free reinforcement learning algorithms on challenging nonlinear control domains.

As electronically stored data grow in daily life, obtaining novel and relevant information becomes challenging in text mining. Thus people have sought statistical methods based on term frequency, matrix algebra, or topic modeling for text mining. Popular topic models have centered on one single text collection, which is deficient for comparative text analyses. We consider a setting where one can partition the corpus into subcollections. Each subcollection shares a common set of topics, but there exists relative variation in topic proportions among collections. Including any prior knowledge about the corpus (e.g. organization structure), we propose the compound latent Dirichlet allocation (cLDA) model, improving on previous work, encouraging generalizability, and depending less on user-input parameters. To identify the parameters of interest in cLDA, we study Markov chain Monte Carlo (MCMC) and variational inference approaches extensively, and suggest an efficient MCMC method. We evaluate cLDA qualitatively and quantitatively using both synthetic and real-world corpora. The usability study on some real-world corpora illustrates the superiority of cLDA to explore the underlying topics automatically but also model their connections and variations across multiple collections.

The challenge to analyze earthquake signals with optimum precision grows along with the amount of available seismic data. At the Karlsruhe Institute of Technology (KIT), researchers have deployed a neural network to determine the arrival-time of seismic waves and thus precisely locate the epicenter of the earthquake. In their report in the Seismological Research Letters journal, they point out that Artificial Intelligence is able to evaluate the data with the same precision as an experienced seismologist. For precisely locating an earthquake event, it is critical to determine the exact arrival-time of the majority of seismic waves at the seismometer station (the so-called phase arrival). Without this knowledge, further accurate seismological evaluations are not possible.