Deep Learning (DL) has transformed the automation of a wide range of industries and finds increasing ubiquity in society. The high complexity of DL models and its widespread adoption has led to global energy consumption doubling every 3-4 months. Currently, the relationship between the DL model configuration and energy consumption is not well established. At a general computational energy model level, there is both strong dependency to both the hardware architecture (e.g. generic processors with different configuration of inner components- CPU and GPU, programmable integrated circuits - FPGA), as well as different interacting energy consumption aspects (e.g., data movement, calculation, control). At the DL model level, we need to translate non-linear activation functions and its interaction with data into calculation tasks. Current methods mainly linearize nonlinear DL models to approximate its theoretical FLOPs and MACs as a proxy for energy consumption. Yet, this is inaccurate (est. 93\% accuracy) due to the highly nonlinear nature of many convolutional neural networks (CNNs) for example. In this paper, we develop a bottom-level Transistor Operations (TOs) method to expose the role of non-linear activation functions and neural network structure in energy consumption. We translate a range of feedforward and CNN models into ALU calculation tasks and then TO steps. This is then statistically linked to real energy consumption values via a regression model for different hardware configurations and data sets. We show that our proposed TOs method can achieve a 93.61% - 99.51% precision in predicting its energy consumption.

Advances in ad hoc teamwork have the potential to create agents that collaborate robustly in real-world applications. Agents deployed in the real world, however, are vulnerable to adversaries with the intent to subvert them. There has been little research in ad hoc teamwork that assumes the presence of adversaries. We explain the importance of extending ad hoc teamwork to include the presence of adversaries and clarify why this problem is difficult. We then propose some directions for new research opportunities in ad hoc teamwork that leads to more robust multi-agent cyber-physical infrastructure systems.

Definition: The terms "robotics in snow and ice" refers to robotic systems being studied, developed, and used in areas where water can be found in its solid state. This specialized branch of field robotics investigates the impact of extreme conditions related to cold environments on autonomous vehicles.

The volume contains selected contributions from the Machine Learning Challenge "Discover the Mysteries of the Maya", presented at the Discovery Challenge Track of The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2021). Remote sensing has greatly accelerated traditional archaeological landscape surveys in the forested regions of the ancient Maya. Typical exploration and discovery attempts, beside focusing on whole ancient cities, focus also on individual buildings and structures. Recently, there have been several successful attempts of utilizing machine learning for identifying ancient Maya settlements. These attempts, while relevant, focus on narrow areas and rely on high-quality aerial laser scanning (ALS) data which covers only a fraction of the region where ancient Maya were once settled. Satellite image data, on the other hand, produced by the European Space Agency's (ESA) Sentinel missions, is abundant and, more importantly, publicly available. The "Discover the Mysteries of the Maya" challenge aimed at locating and identifying ancient Maya architectures (buildings, aguadas, and platforms) by performing integrated image segmentation of different types of satellite imagery (from Sentinel-1 and Sentinel-2) data and ALS (lidar) data.

Load balancing (LB) is a challenging issue in the hybrid light fidelity (LiFi) and wireless fidelity (WiFi) networks (HLWNets), due to the nature of heterogeneous access points (APs). Machine learning has the potential to provide a complexity-friendly LB solution with near-optimal network performance, at the cost of a training process. The state-of-the-art (SOTA) learning-aided LB methods, however, need retraining when the network environment (especially the number of users) changes, significantly limiting its practicability. In this paper, a novel deep neural network (DNN) structure named adaptive target-condition neural network (A-TCNN) is proposed, which conducts AP selection for one target user upon the condition of other users. Also, an adaptive mechanism is developed to map a smaller number of users to a larger number through splitting their data rate requirements, without affecting the AP selection result for the target user. This enables the proposed method to handle different numbers of users without the need for retraining. Results show that A-TCNN achieves a network throughput very close to that of the testing dataset, with a gap less than 3%. It is also proven that A-TCNN can obtain a network throughput comparable to two SOTA benchmarks, while reducing the runtime by up to three orders of magnitude.

Using the DALL·E artificial intelligence tool to create images of what a nuclear-heated spa might look like, inspired by Iceland's Blue Lagoon.

We will describe the sampling-based learning procedures Safe path-tracking control is crucial for reliable autonomous for constructing candidate neural barrier functions, and driving. Widely-adopted control methods [1], [2] have inherent certification procedures that utilize robustness analysis for difficulty with nonlinearity and uncertainty that cannot neural networks to certify regions where the barrier conditions be ignored when the vehicles are operating at relatively high are fully satisfied. Our approach is built on recent advances in speed or under adverse road conditions. Controllers obtained robustness certification of neural networks [10], [11], which from deep learning methods have shown great promise in a allows us to rigorously bound the Lie derivative values of the variety of application [3], [4]. However, neural networks are learned neural barrier function. With these methods, we are known to be highly nonlinear and complex, preventing them able to train and certify barrier functions with small region from being easily analyzed as classical controllers such as of boundary violations: 99% of the barrier region is fully Stanley [5] or Model Predictive Control (MPC) [2], [6]. In this certified for the kinematic vehicle model, 86% for the highly paper, we propose methods for the quantitative safety analysis nonlinear dynamic model with inertial effects and lateral of learning-based neural controllers by synthesizing and slip, and 91% in the TORCS environment with high-fidelity certifying neural almost-barrier functions, for path-tracking vehicle dynamics simulation (Fig.1). We visualize the certified with only black-box access to high-fidelity simulations of regions (in blue contour) and the sparse uncertified regions (in nonlinear vehicle dynamics.

Contrails are condensation trails generated from emitted particles by aircraft engines, which perturb Earth's radiation budget. Simulation modeling is used to interpret the formation and development of contrails. These simulations are computationally intensive and rely on high-performance computing solutions, and the contrail structures are not well defined. We propose a visual computing system to assist in defining contrails and their characteristics, as well as in the analysis of parameters for computer-generated aircraft engine simulations. The back-end of our system leverages a contrail-formation criterion and clustering methods to detect contrails' shape and evolution and identify similar simulation runs. The front-end system helps analyze contrails and their parameters across multiple simulation runs. The evaluation with domain experts shows this approach successfully aids in contrail data investigation.

During the operation of a chemical plant, product quality must be consistently maintained, and the production of off-specification products should be minimized. Accordingly, process variables related to the product quality, such as the temperature and composition of materials at various parts of the plant must be measured, and appropriate operations (that is, control) must be performed based on the measurements. Some process variables, such as temperature and flow rate, can be measured continuously and instantaneously. However, other variables, such as composition and viscosity, can only be obtained through time-consuming analysis after sampling substances from the plant. Soft sensors have been proposed for estimating process variables that cannot be obtained in real time from easily measurable variables. However, the estimation accuracy of conventional statistical soft sensors, which are constructed from recorded measurements, can be very poor in unrecorded situations (extrapolation). In this study, we estimate the internal state variables of a plant by using a dynamic simulator that can estimate and predict even unrecorded situations on the basis of chemical engineering knowledge and an artificial intelligence (AI) technology called reinforcement learning, and propose to use the estimated internal state variables of a plant as soft sensors. In addition, we describe the prospects for plant operation and control using such soft sensors and the methodology to obtain the necessary prediction models (i.e., simulators) for the proposed system.

Distributed acoustic sensors (DAS) are effective apparatus which are widely used in many application areas for recording signals of various events with very high spatial resolution along the optical fiber. To detect and recognize the recorded events properly, advanced signal processing algorithms with high computational demands are crucial. Convolutional neural networks are highly capable tools for extracting spatial information and very suitable for event recognition applications in DAS. Long-short term memory (LSTM) is an effective instrument for processing sequential data. In this study, we proposed a multi-input multi-output, two stage feature extraction methodology that combines the capabilities of these neural network architectures with transfer learning to classify vibrations applied to an optical fiber by a piezo transducer. First, we extracted the differential amplitude and phase information from the Phase-OTDR recordings and stored them in a temporal-spatial data matrix. Then, we used a state-of-the-art pre-trained CNN without dense layers as a feature extractor in the first stage. In the second stage, we used LSTMs to further analyze the features extracted by the CNN. Finally, we used a dense layer to classify the extracted features. To observe the effect of the utilized CNN architecture, we tested our model with five state-of-the art pre-trained models (VGG-16, ResNet-50, DenseNet-121, MobileNet and Inception-v3). The results show that using the VGG-16 architecture in our framework manages to obtain 100% classification accuracy in 50 trainings and got the best results on our Phase-OTDR dataset. Outcomes of this study indicate that the pre-trained CNNs combined with LSTM are very suitable for the analysis of differential amplitude and phase information, represented in a temporal spatial data matrix which is promising for event recognition operations in DAS applications.