Harnessing data to discover the underlying governing laws or equations that describe the behavior of complex physical systems can significantly advance our modeling, simulation and understanding of such systems in various science and engineering disciplines. Recent advances in sparse identification show encouraging success in distilling closed-form governing equations from data for a wide range of nonlinear dynamical systems. However, the fundamental bottleneck of this approach lies in the robustness and scalability with respect to data scarcity and noise. This work introduces a novel physics-informed deep learning framework to discover governing partial differential equations (PDEs) from scarce and noisy data for nonlinear spatiotemporal systems. In particular, this approach seamlessly integrates the strengths of deep neural networks for rich representation learning, automatic differentiation and sparse regression to approximate the solution of system variables, compute essential derivatives, as well as identify the key derivative terms and parameters that form the structure and explicit expression of the PDEs. The efficacy and robustness of this method are demonstrated on discovering a variety of PDE systems with different levels of data scarcity and noise. The resulting computational framework shows the potential for closed-form model discovery in practical applications where large and accurate datasets are intractable to capture.

We consider the problem of demand-side energy management, where each household is equipped with a smart meter that is able to schedule home appliances online. The goal is to minimise the overall cost under a real-time pricing scheme. While previous works have introduced centralised approaches, we formulate the smart grid environment as a Markov game, where each household is a decentralised agent, and the grid operator produces a price signal that adapts to the energy demand. The main challenge addressed in our approach is partial observability and perceived non-stationarity of the environment from the viewpoint of each agent. We propose a multi-agent extension of a deep actor-critic algorithm that shows success in learning in this environment. This algorithm learns a centralised critic that coordinates training of all agents. Our approach thus uses centralised learning but decentralised execution. Simulation results show that our online deep reinforcement learning method can reduce both the peak-to-average ratio of total energy consumed and the cost of electricity for all households based purely on instantaneous observations and a price signal.

Many applications require a learner to make sequential decisions given uncertainty regarding both the system's payoff function and safety constraints. In safety-critical systems, it is paramount that the learner's actions do not violate the safety constraints at any stage of the learning process. In this paper, we study a stochastic bandit optimization problem where the unknown payoff and constraint functions are sampled from Gaussian Processes (GPs) first considered in [Srinivas et al., 2010]. We develop a safe variant of GP-UCB called SGP-UCB, with necessary modifications to respect safety constraints at every round. The algorithm has two distinct phases. The first phase seeks to estimate the set of safe actions in the decision set, while the second phase follows the GP-UCB decision rule. Our main contribution is to derive the first sub-linear regret bounds for this problem. We numerically compare SGP-UCB against existing safe Bayesian GP optimization algorithms.

We study here the problem of learning the exploration exploitation trade-off in the contextual bandit problem with linear reward function setting. In the traditional algorithms that solve the contextual bandit problem, the exploration is a parameter that is tuned by the user. However, our proposed algorithm learn to choose the right exploration parameters in an online manner based on the observed context, and the immediate reward received for the chosen action. We have presented here two algorithms that uses a bandit to find the optimal exploration of the contextual bandit algorithm, which we hope is the first step toward the automation of the multi-armed bandit algorithm.

In this paper, we discuss the learning of generalised policies for probabilistic and classical planning problems using Action Schema Networks (ASNets). The ASNet is a neural network architecture that exploits the relational structure of (P)PDDL planning problems to learn a common set of weights that can be applied to any problem in a domain. By mimicking the actions chosen by a traditional, non-learning planner on a handful of small problems in a domain, ASNets are able to learn a generalised reactive policy that can quickly solve much larger instances from the domain. This work extends the ASNet architecture to make it more expressive, while still remaining invariant to a range of symmetries that exist in PPDDL problems. We also present a thorough experimental evaluation of ASNets, including a comparison with heuristic search planners on seven probabilistic and deterministic domains, an extended evaluation on over 18,000 Blocksworld instances, and an ablation study. Finally, we show that sparsity-inducing regularisation can produce ASNets that are compact enough for humans to understand, yielding insights into how the structure of ASNets allows them to generalise across a domain.

Consciousness continues to be of one of the most important, interesting and complex question to focus upon. While the study of consciousness has a long and rich history in the field of philosophy, the scientific study of consciousness has become less taboo recently, and made tremendous progress in the field over the last couple of decades, due to significant contributions from disciplines like neuroscience, cognitive science and computer science. Though research interests have continued to grow, fueled by the recent artificial intelligence/machine learning (AI/ML) revolution (reigniting questions around artificial consciousness), the topic of consciousness itself has generally been ignored or dismissed by a majority of those who work in mainstream AI as either an unimportant factor for their research goals or accusing work in (artificial) consciousness as distracting flights of fantasy. It seems as this trend might change in the near future as leaders in the field of AI recognize the importance of mechanisms of higher level cognition for making progress in AI, their relationship to the'easy problems' of consciousness and the important work that has been conducted in the field of cognitive science to understand these better (Yoshua Bengio's keynote address at NEURIPS 2019 being an important example of this [1]). While this might not satisfy those who are interested in the phenomenal aspects of our conscious experience, it represents a step forward in the right direction by the larger AI community. In keeping with the (beginnings of a) trend, the author will look to make the case for a non-equilibrium thermodynamic framework of consciousness, it's relationship to the field of AI and the crucial role that computer hardware engineers might have to play in the scientific study of consciousness. The author would like to take a brief moment (to digress) and explain the journey towards these ideas, hoping that it would elucidate their motivations as an engineer to study and understand the field of consciousness from a more physics based approach. The author's primary research interests lie in the field of artificial intelligence and was lucky

The Middle East oil and gas industry faces pressure on several fronts. Enterprises around the world are deploying sustainable-energy technology designed to reduce reliance on oil in an effort to curb greenhouse gas emissions, while geopolitical turmoil has caused oil prices to plunge, putting pressure on energy company IT budgets. Shumon Zaman is a UAE-based technology executive and consultant who most recently worked as technology vice president at Lamprell PLC, a company specializing in the oil rig construction business; in this edited Q&A he highlights the power of digital twins and other emerging tech to accelerate digitalization in oil and gas industry -- with the aim of curbing costs, optimising revenue streams and supporting sustainability initiatives. Which emerging technologies will shape the future for the oil and gas industry? Shumon Zaman is a UAE-based technology executive.

As more artificial intelligence applications move to smartphones, deep learning models are getting smaller to allow apps to run faster and save battery power. Now, MIT researchers have a new and better way to compress models. It's so simple that they unveiled it in a tweet last month: Train the model, prune its weakest connections, retrain the model at its fast, early training rate, and repeat, until the model is as tiny as you want. "That's it," says Alex Renda, a Ph.D. student at MIT. "The standard things people do to prune their models are crazy complicated." Renda discussed the technique when the International Conference of Learning Representations (ICLR) convened remotely this month.

The contribution of this paper is two-fold. First, we present ProbCast - a novel probabilistic model for multivariate time-series forecasting. We employ a conditional GAN framework to train our model with adversarial training. Second, we propose a framework that lets us transform a deterministic model into a probabilistic one with improved performance. The motivation of the framework is to either transform existing highly accurate point forecast models to their probabilistic counterparts or to train GANs stably by selecting the architecture of GAN's component carefully and efficiently. We conduct experiments over two publicly available datasets namely electricity consumption dataset and exchange-rate dataset. The results of the experiments demonstrate the remarkable performance of our model as well as the successful application of our proposed framework.

Artificial Intelligence may seem transient, yet it always managed to have a controversial presence. Recently it raised concerns about its sustainability. In June 2019, the University of Massachusetts at Amherst study discovered that a single large (213 million parameters) Transformer-based neural network built using NAS (commonly used in machine translation) has produced around 626,000 pounds of carbon dioxide. This amount is equivalent to five times more than an average car produces in its lifespan. These massive consumption numbers are because of the energy needed to run specialized hardware like GPUs and TPUs for AI training and development.