According to a report by Accenture, artificial intelligence can possibly add US$957 billion, or 15% of India's present gross value in 2035. The blend of the technology, information, and ability that make intelligent systems possible has arrived at the critical mass, driving exceptional growth in AI investment. Here are the most popular AI start-ups of India that one should know about. Locus is a technology platform that uses machine learning and proprietary algorithms to automate complex supply chain decisions. Its smart supply chain solutions provide end-to-end visibility and enable enterprises to enhance their operational efficiency by reining in costs, streamlining the customer experience, and reducing environmental impact.

Networks are landmarks of many complex phenomena where interweaving interactions between different agents transform simple local rule-sets into nonlinear emergent behaviors. While some recent studies unveil associations between the network structure and the underlying dynamical process, identifying stochastic nonlinear dynamical processes continues to be an outstanding problem. Here we develop a simple data-driven framework based on operator-theoretic techniques to identify and control stochastic nonlinear dynamics taking place over large-scale networks. The proposed approach requires no prior knowledge of the network structure and identifies the underlying dynamics solely using a collection of two-step snapshots of the states. This data-driven system identification is achieved by using the Koopman operator to find a low dimensional representation of the dynamical patterns that evolve linearly. Further, we use the global linear Koopman model to solve critical control problems by applying to model predictive control (MPC)--typically, a challenging proposition when applied to large networks. We show that our proposed approach tackles this by converting the original nonlinear programming into a more tractable optimization problem that is both convex and with far fewer variables.

Dealing with missing values and incomplete time series is a labor-intensive and time-consuming inevitable task when handling data coming from real-world applications. Effective spatio-temporal representations would allow imputation methods to reconstruct missing temporal data by exploiting information coming from sensors at different locations. However, standard methods fall short in capturing the nonlinear time and space dependencies existing within networks of interconnected sensors and do not take full advantage of the available - and often strong - relational information. Notably, most of state-of-the-art imputation methods based on deep learning do not explicitly model relational aspects and, in any case, do not exploit processing frameworks able to adequately represent structured spatio-temporal data. Conversely, graph neural networks have recently surged in popularity as both expressive and scalable tools for processing sequential data with relational inductive biases. In this work, we present the first assessment of graph neural networks in the context of multivariate time series imputation. In particular, we introduce a novel graph neural network architecture, named GRIL, which aims at reconstructing missing data in the different channels of a multivariate time series by learning spatial-temporal representations through message passing. Preliminary empirical results show that our model outperforms state-of-the-art methods in the imputation task on relevant benchmarks with mean absolute error improvements often higher than 20%.

When you think about solving the climate crisis, what springs to mind? Most people's knee-jerk reaction is along the lines of "electrification," "carbon sequestration," "recycling," or "renewable agriculture." While not many think of phrases like "big data" or "artificial intelligence," several recent conversations have convinced me how important these fields are to helping our civilization thrive and survive into the next century. The two founder / CEOs with whom I have had the pleasure to speak recently use AI in very different ways and in completely different fields, but it is clear that the ubiquity of cheap computing power, combined with smart engineers and focused, visionary entrepreneurs represents a formidable force in helping us mitigate and adapt to today's harsher, more challenging post-climate world. The companies featured in this article are Clir and SINAI Technologies.

The AI system can generate an almost instant prediction of building emissions rates (BER) for use in calculating the energy performance of non-domestic buildings. Current methods can take hours to days to produce BERs and are generated by manually inputting hundreds of variables. Dr Georgina Cosma and postgraduate student Kareem Ahmed, of the School of Science, have designed and trained an AI model to predict BER values with 27 inputs with little loss in accuracy. The model has been created with the support of Cundall's head of research and innovation, Edwin Wealend, and trained using data obtained from UK government energy performance assessments. Cosma said the research "is an important first step towards the use of machine learning tools for energy prediction in the UK" and it shows how data can "improve current processes in the construction industry".

Despite emissions falling in 2020 at the fastest rate for nearly a century, scientists are worried they will rebound in 2021 as lockdown restrictions ease and'normal life' resumes. Across the business community, growing concern about climate change is driving greater action: with the majority of UK business leaders planning to increase long-term investment in sustainability initiatives. This is a shift in the right direction, but the tricky next step is making sure such green efforts actually drive change. While over half of company leaders recognize this calls for better green measurement, achieving that is difficult with limited frameworks for green reporting available both globally and locally. Additionally, business leaders are now responsible for the sustainability efforts of their entire network of suppliers, which means clear oversight is key in holding partners accountable for'greenwashing' – where organizations claim to be green through use of renewable energy, but they do not have the necessary processes in place to offset their overall carbon footprint.

We study learning based controllers as a replacement for model predictive controllers (MPC) for the control of autonomous vehicles. We concentrate for the experiments on the simple yet representative bicycle model. We compare training by supervised learning and by reinforcement learning. We also discuss the neural net architectures so as to obtain small nets with the best performances. This work aims at producing controllers that can both be embedded on real-time platforms and amenable to verification by formal methods techniques.

We present a novel approach for data-driven modeling of the time-domain induced polarization (IP) phenomenon using variational autoencoders (VAE). VAEs are Bayesian neural networks that aim to learn a latent statistical distribution to encode extensive data sets as lower dimension representations. We collected 1 600 319 IP decay curves in various regions of Canada, the United States and Kazakhstan, and compiled them to train a deep VAE. The proposed deep learning approach is strictly unsupervised and data-driven: it does not require manual processing or ground truth labeling of IP data. Moreover, our VAE approach avoids the pitfalls of IP parametrization with the empirical Cole-Cole and Debye decomposition models, simple power-law models, or other sophisticated mechanistic models. We demonstrate four applications of VAEs to model and process IP data: (1) representative synthetic data generation, (2) unsupervised Bayesian denoising and data uncertainty estimation, (3) quantitative evaluation of the signal-to-noise ratio, and (4) automated outlier detection. We also interpret the IP compilation's latent representation and reveal a strong correlation between its first dimension and the average chargeability of IP decays. Finally, we experiment with varying VAE latent space dimensions and demonstrate that a single real-valued scalar parameter contains sufficient information to encode our extensive IP data compilation. This new finding suggests that modeling time-domain IP data using mathematical models governed by more than one free parameter is ambiguous, whereas modeling only the average chargeability is justified. A pre-trained implementation of our model -- readily applicable to new IP data from any geolocation -- is available as open-source Python code for the applied geophysics community.

We use Reinforcement Meta Learning to optimize an adaptive guidance system suitable for the approach phase of a gliding hypersonic vehicle. Adaptability is achieved by optimizing over a range of off-nominal flight conditions including perturbation of aerodynamic coefficient parameters, actuator failure scenarios, and sensor noise. The system maps observations directly to commanded bank angle and angle of attack rates. These observations include a velocity field tracking error formulated using parallel navigation, but adapted to work over long trajectories where the Earth's curvature must be taken into account. Minimizing the tracking error keeps the curved space line of sight to the target location aligned with the vehicle's velocity vector. The optimized guidance system will then induce trajectories that bring the vehicle to the target location with a high degree of accuracy at the designated terminal speed, while satisfying heating rate, load, and dynamic pressure constraints. We demonstrate the adaptability of the guidance system by testing over flight conditions that were not experienced during optimization. The guidance system's performance is then compared to that of a linear quadratic regulator tracking an optimal trajectory.

Today's supply chains are laden with inefficiencies, as most companies rely on antiquated practices to oversee and manage how goods get from place to place. The supply chain is delicate -- even one disruption among suppliers, buyers, and logistics providers can have a trickle-down effect that causes waste, time loss, and increased carbon emissions. With the supply chain still managed manually, logistics managers are operating under intense pressure, with the sheer amount of data about material supply, demand, and transportation routes overwhelming. Even with machine learning providing managers with intelligent analysis, logistics managers can only react so quickly to the thousands of changes along a single supply chain. As managers are overburdened, their slow reactions to real-time problems and disruptions cause the supply chain inefficiencies that create higher costs, waste, and even greater environmental impact.