The AltaML Applied AI Lab launches today: https://lnkd.in/gbsggVF Each cohort of interns will work with industry partners Suncor, TransAlta, ATB Financial, Spartan Controls on applied #AI and #ML projects in #YYC. The AI Lab operates with support from Calgary Economic Development.

In this work we propose the use of adaptive stochastic search as a building block for general, non-convex optimization operations within deep neural network architectures. Specifically, for an objective function located at some layer in the network and parameterized by some network parameters, we employ adaptive stochastic search to perform optimization over its output. This operation is differentiable and does not obstruct the passing of gradients during backpropagation, thus enabling us to incorporate it as a component in end-to-end learning. We study the proposed optimization module's properties and benchmark it against two existing alternatives on a synthetic energy-based structured prediction task, and further showcase its use in stochastic optimal control applications.

Carbon dioxide Capture and Storage (CCS) is an important strategy in mitigating anthropogenic CO$_2$ emissions. In order for CCS to be successful, large quantities of CO$_2$ must be stored and the storage site conformance must be monitored. Here we present a deep learning method to reconstruct pressure fields and classify the flux out of the storage formation based on the pressure data from Above Zone Monitoring Interval (AZMI) wells. The deep learning method is a version of a semi conditional variational auto-encoder tailored to solve two tasks: reconstruction of an incremental pressure field and leakage rate classification. The method, predictions and associated uncertainty estimates are illustrated on the synthetic data from a high-fidelity heterogeneous 2D numerical reservoir model, which was used to simulate subsurface CO$_2$ movement and pressure changes in the AZMI due to a CO$_2$ leakage.

Retrosynthesis is a problem to infer reactant compounds to synthesize a given product compound through chemical reactions. Recent studies on retrosynthesis focus on proposing more sophisticated prediction models, but the dataset to feed the models also plays an essential role in achieving the best generalizing models. Generally, a dataset that is best suited for a specific task tends to be small. In such a case, it is the standard solution to transfer knowledge from a large or clean dataset in the same domain. In this paper, we conduct a systematic and intensive examination of data transfer approaches on end-to-end generative models, in application to retrosynthesis. Experimental results show that typical data transfer methods can improve test prediction scores of an off-the-shelf Transformer baseline model. Especially, the pre-training plus fine-tuning approach boosts the accuracy scores of the baseline, achieving the new state-of-the-art. In addition, we conduct a manual inspection for the erroneous prediction results. The inspection shows that the pre-training plus fine-tuning models can generate chemically appropriate or sensible proposals in almost all cases.

The stochastic multi-armed bandit (Bubeck and Cesa-Bianchi, 2012; Lattimore and Szepesvári, 2020) has been extensively studied, as an important model to optimize the tradeoff between exploration and exploitation in sequential decision making. Among its many variants, the contextual bandit is widely used in real-world applications such as recommendation (Li et al., 2010), advertising (Graepel et al., 2010), robotic control (Mahler et al., 2016), and healthcare (Greenewald et al., 2017). In each round of a contextual bandit, the agent observes a feature vector (the "context") for each of the K arms, pulls one of them, and in return receives a scalar reward. The goal is to maximize the cumulative reward, or minimize regret (to be defined later), in a total of T rounds. To do so, the agent must find a tradeoff between exploration and exploitation. One of the most effective and widely used techniques is Thompson Sampling, or TS (Thompson, 1933). The basic idea is to compute the posterior distribution of each arm being optimal for the present context, and sample an arm from this distribution. TS is often easy to implement, and has found great success in practice (Chapelle and Li, 2011; Graepel et al., 2010; Kawale et al., 2015; Russo et al., 2017). Recently, a series of work has applied TS or its variants to explore in contextual bandits with neural network models (Blundell et al., 2015; Kveton et al., 2020; Lu and Van Roy, 2017; Riquelme

We study the problem of balancing effectiveness and efficiency in automated feature selection. After exploring many feature selection methods, we observe a computational dilemma: 1) traditional feature selection is mostly efficient, but difficult to identify the best subset; 2) the emerging reinforced feature selection automatically navigates to the best subset, but is usually inefficient. Can we bridge the gap between effectiveness and efficiency under automation? Motivated by this dilemma, we aim to develop a novel feature space navigation method. In our preliminary work, we leveraged interactive reinforcement learning to accelerate feature selection by external trainer-agent interaction. In this journal version, we propose a novel interactive and closed-loop architecture to simultaneously model interactive reinforcement learning (IRL) and decision tree feedback (DTF). Specifically, IRL is to create an interactive feature selection loop and DTF is to feed structured feature knowledge back to the loop. First, the tree-structured feature hierarchy from decision tree is leveraged to improve state representation. In particular, we represent the selected feature subset as an undirected graph of feature-feature correlations and a directed tree of decision features. We propose a new embedding method capable of empowering graph convolutional network to jointly learn state representation from both the graph and the tree. Second, the tree-structured feature hierarchy is exploited to develop a new reward scheme. In particular, we personalize reward assignment of agents based on decision tree feature importance. In addition, observing agents' actions can be feedback, we devise another reward scheme, to weigh and assign reward based on the feature selected frequency ratio in historical action records. Finally, we present extensive experiments on real-world datasets to show the improved performance.

The most common representation formalisms for automated planning are descriptive models that abstractly describe what the actions do and are tailored for effciently computing the next state(s) in a state-transition system. However, real-world acting requires operational models that describe how to do things, with rich control structures for closed-loop online decision-making in a dynamic environment. To use a different action model for planning than the one used for acting causes problems with combining acting and planning, in particular for the development and consistency verification of the different models. As an alternative, we define and implement an integrated acting-and-planning system in which both planning and acting use the same operational models, which are written in a general-purpose hierarchical task-oriented language offering rich control structures. The acting component, called Reactive Acting Engine (RAE), is inspired by the well-known PRS system, except that instead of being purely reactive, it can get advice from the planner. Our planner uses a UCT-like Monte Carlo Tree Search procedure, called UPOM (UCT Procedure for Operational Models), whose rollouts are simulations of the actor's operational models. We also present learning strategies for use with RAE and UPOM that acquire, from online acting experiences and/or simulated planning results, a mapping from decision contexts to method instances as well as a heuristic function to guide UPOM. Our experimental results show that UPOM and our learning strategies significantly improve the acting efficiency and robustness of RAE. We discuss the asymptotic convergence of UPOM by mapping its search space to an MDP.

New battery materials are constantly being invented, but there are still challenges in producing them at a large scale and at high quality. Through the power of artificial intelligence (AI) and advanced simulation, scientists can dramatically accelerate translating these materials from benchtop to large-scale manufacturing and in the process provide a way to generate higher-performance materials at scale. Argonne researchers are currently using AI to optimize nanomaterials produced from flame-spray pyrolysis (FSP) in a minimum number of trials. Argonne scientists are simultaneously building a comprehensive simulation of FSP to reveal the physics and inform the AI model. An advanced suite of diagnostics available at the FSP facility will provide validation data for the simulations.

Machine learning techniques don't just have the capability to make our computers, software, and devices more'intelligent' -- enhancing systems with the ability to predict, personalize, analyze, and more. More direct, physical advantages include their ability to reduce the amount of power these systems use. Engineers at the Swiss Center for Electronics and Microtechnology (CSEM) develop a new machine-learning method capable of cutting energy use in real-life scenarios, such as the heating, ventilation, and air conditioning (HVAC) systems in buildings. HVAC systems are typically responsible for a significant proportion of total building energy consumption, and subsequently, a large volume of total energy consumption in any industry. The engineers' research was published in IEEE Transactions on Neural Networks and Learning Systems.

The phrase "data is an asset" is something of a corporate cliché. However, it is increasingly true as companies in industry after industry undergo programs to digitize their businesses. It is obvious that Netflix is a highly digital business with data at its heart, but what about more down-to-earth enterprises like manufacturing or energy? Even in the oil industry, the talk these days is of the digital oilfield where vast amounts of sensor data about the operation of an oil platform is captured and analyzed so field production can be tweaked and tuned in real time. In order to extract value from your data, though, you first have to know what you have and where it is, and this seemingly obvious starting point is a major hurdle in a large corporation.