All the sessions from Transform 2021 are available on-demand now. DeepMind today detailed its latest efforts to create AI systems capable of completing a range of different, unique tasks. By designing a virtual environment called XLand, the Alphabet-backed lab says that it managed to train systems with the ability to succeed at problems and games including hide and seek, capture the flag, and finding objects, some of which they didn't encounter during training. The AI technique known as reinforcement learning has shown remarkable potential, enabling systems to learn to play games like chess, shogi, Go, and StarCraft II through a repetitive process of trial and error. But a lack of training data has been one of the major factors limiting reinforcement learning–trained systems' behavior being general enough to apply across diverse games.

Natural convection in porous media is a highly nonlinear multiphysical problem relevant to many engineering applications (e.g., the process of $\mathrm{CO_2}$ sequestration). Here, we present a non-intrusive reduced order model of natural convection in porous media employing deep convolutional autoencoders for the compression and reconstruction and either radial basis function (RBF) interpolation or artificial neural networks (ANNs) for mapping parameters of partial differential equations (PDEs) on the corresponding nonlinear manifolds. To benchmark our approach, we also describe linear compression and reconstruction processes relying on proper orthogonal decomposition (POD) and ANNs. We present comprehensive comparisons among different models through three benchmark problems. The reduced order models, linear and nonlinear approaches, are much faster than the finite element model, obtaining a maximum speed-up of $7 \times 10^{6}$ because our framework is not bound by the Courant-Friedrichs-Lewy condition; hence, it could deliver quantities of interest at any given time contrary to the finite element model. Our model's accuracy still lies within a mean squared error of 0.07 (two-order of magnitude lower than the maximum value of the finite element results) in the worst-case scenario. We illustrate that, in specific settings, the nonlinear approach outperforms its linear counterpart and vice versa. We hypothesize that a visual comparison between principal component analysis (PCA) or t-Distributed Stochastic Neighbor Embedding (t-SNE) could indicate which method will perform better prior to employing any specific compression strategy.

Most of the existing 3D human pose estimation approaches mainly focus on predicting 3D positional relationships between the root joint and other human joints (local motion) instead of the overall trajectory of the human body (global motion). Despite the great progress achieved by these approaches, they are not robust to global motion, and lack the ability to accurately predict local motion with a small movement range. To alleviate these two problems, we propose a relative information encoding method that yields positional and temporal enhanced representations. Firstly, we encode positional information by utilizing relative coordinates of 2D poses to enhance the consistency between the input and output distribution. The same posture with different absolute 2D positions can be mapped to a common representation. It is beneficial to resist the interference of global motion on the prediction results. Second, we encode temporal information by establishing the connection between the current pose and other poses of the same person within a period of time. More attention will be paid to the movement changes before and after the current pose, resulting in better prediction performance on local motion with a small movement range. The ablation studies validate the effectiveness of the proposed relative information encoding method. Besides, we introduce a multi-stage optimization method to the whole framework to further exploit the positional and temporal enhanced representations. Our method outperforms state-of-the-art methods on two public datasets. Code is available at https://github.com/paTRICK-swk/Pose3D-RIE.

Machine learning techniques are becoming a fundamental tool for scientific and engineering progress. These techniques are applied in contexts as diverse as astronomy and spam filtering. However, correctly applying these techniques requires careful engineering. Much attention has been paid to the technical potential; relatively little attention has been paid to the software engineering process required to bring research-based machine learning techniques into practical utility. Technology companies have supported the engineering community through machine learning frameworks such as TensorFLow and PyTorch, but the details of how to engineer complex machine learning models in these frameworks have remained hidden. To promote best practices within the engineering community, academic institutions and Google have partnered to launch a Special Interest Group on Machine Learning Models (SIGMODELS) whose goal is to develop exemplary implementations of prominent machine learning models in community locations such as the TensorFlow Model Garden (TFMG). The purpose of this report is to define a process for reproducing a state-of-the-art machine learning model at a level of quality suitable for inclusion in the TFMG. We define the engineering process and elaborate on each step, from paper analysis to model release. We report on our experiences implementing the YOLO model family with a team of 26 student researchers, share the tools we developed, and describe the lessons we learned along the way.

We propose to use deep learning to estimate parameters in statistical models when standard likelihood estimation methods are computationally infeasible. We show how to estimate parameters from max-stable processes, where inference is exceptionally challenging even with small datasets but simulation is straightforward. We use data from model simulations as input and train deep neural networks to learn statistical parameters. Our neural-network-based method provides a competitive alternative to current approaches, as demonstrated by considerable accuracy and computational time improvements. It serves as a proof of concept for deep learning in statistical parameter estimation and can be extended to other estimation problems.

In applied machine learning, engineering, and the sciences, we are frequently confronted with the problem of identifying low-dimensional structure in high-dimensional data. In certain well-structured data sets, identifying a good low-dimensional model is the principal task: examples include convolutional sparse models in microscopy [43] and neuroscience [13, 19], and low-rank models in collaborative filtering [8, 11]. Even more complicated datasets from problems such as image classification exhibit some form of low-dimensionality: recent experiments estimate the effective dimension of CIFAR-10 as 26 and the effective dimension of ImageNet as 43 [60]. The variability in these datasets can be thought of as comprising two parts: a "probabilistic" variability induced by the distribution of geometries associated with a given class, and a "geometric" variability associated with physical nuisances such as pose and illumination. The former is challenging to model analytically; virtually all progress on this issue has come through the introduction of large datasets and high-capacity learning machines. The latter induces a much cleaner analytical structure: transformations of a given image lie near a low-dimensional submanifold of the image space (Figure 1). The celebrated successes of convolutional neural networks in image classification seem to derive from their ability to simultaneously handle both types of variability.

Abstract: To build a robust secure solution for smart city's IOT network from any Cyber-attacks using Artificial Intelligence (AI). In Smart City's IOT network, data collected from different log collectors or direct sources from cloud or edge should harness the potential of AI. The smart city command and control center team will leverage these models and deploy it in different city's IOT network to help on intrusion prediction, network packet surge, potential botnet attacks from external network. Some of the vital use cases considered based on the users of command-and-control center. Keywords-Artificial Intelligence, Internet of Things, Smart City, IOT Security, Smart City command and control center I. INTRODUCTION The Internet of Things market will grow from 170 Billion devices (as on 2017) to 561 Billion devices by 2020 as reply.com It will bring more niche devices like Smart Home appliances, Smart Home Security, Digital Assistants and Home Robots from different providers.

Electricity load forecasting is crucial for the power systems' planning and maintenance. However, its un-stationary and non-linear characteristics impose significant difficulties in anticipating future demand. This paper proposes a novel ensemble deep Random Vector Functional Link (edRVFL) network for electricity load forecasting. The weights of hidden layers are randomly initialized and kept fixed during the training process. The hidden layers are stacked to enforce deep representation learning. Then, the model generates the forecasts by ensembling the outputs of each layer. Moreover, we also propose to augment the random enhancement features by empirical wavelet transformation (EWT). The raw load data is decomposed by EWT in a walk-forward fashion, not introducing future data leakage problems in the decomposition process. Finally, all the sub-series generated by the EWT, including raw data, are fed into the edRVFL for forecasting purposes. The proposed model is evaluated on twenty publicly available time series from the Australian Energy Market Operator of the year 2020. The simulation results demonstrate the proposed model's superior performance over eleven forecasting methods in three error metrics and statistical tests on electricity load forecasting tasks.

The emergence of IoT technology and recent advancement in sensor networks enabled transportation systems to a new dimension called Intelligent Transportation System (ITS). Due to increased usage of vehicles and communication among entities in road traffic scenarios, the amount of raw data generation in ITS is huge. This raw data are to be processed to infer contextual information and provide new services related to different modes of road transport such as traffic signal management, accident prediction, object detection etc.,. To understand the importance of context, this article aims to study context-awareness in the Intelligent Transportation System. We present a review on prominent applications developed in the literature concerning context - awareness in the intelligent transportation system. The objective of this survey article is (i) to highlight context and its features in ITS (ii) to address the applicability of modelling techniques and reasoning approaches in ITS (iii) to shed light on impact of IoT and machine learning in ITS development. I. Introduction The Intelligent Transportation System (ITS) plays a significant role in the transformation of conventional transportation by enhancing user convenience and safety, ensuring efficiency and improving transportation networks. Many countries around the globe have widely accepted and started implementing intelligent transportation systems as a solution to the current road traffic management practices [1]. Research in ITS aims to afford services relating to different modes of road transport and assist users to be better informed on road safety and make safer, coordinated, comfort and smarter use of transportation [2]. The traditional road transportation currently in practise encompasses more of human to human communication. Imparting intelligence to it increases many technical challenges in enabling human to machine communication and machine to machine communication. Yet thanks to advanced technologies such as electronic sensor technology, wireless sensor network, mobile computing, cloud computing, Internet of Things, computer vision, data transmission technology and intelligent control have enabled large scale deployment of intelligent transportation in reality [56].

Deep neural networks set the state-of-the-art across many tasks in computer vision, but their generalization ability to image distortions is surprisingly fragile. In contrast, the mammalian visual system is robust to a wide range of perturbations. Recent work suggests that this generalization ability can be explained by useful inductive biases encoded in the representations of visual stimuli throughout the visual cortex. Here, we successfully leveraged these inductive biases with a multi-task learning approach: we jointly trained a deep network to perform image classification and to predict neural activity in macaque primary visual cortex (V1). We measured the out-of-distribution generalization abilities of our network by testing its robustness to image distortions. We found that co-training on monkey V1 data leads to increased robustness despite the absence of those distortions during training. Additionally, we showed that our network's robustness is very close to that of an Oracle network where parts of the architecture are directly trained on noisy images. Our results also demonstrated that the network's representations become more brain-like as their robustness improves. Using a novel constrained reconstruction analysis, we investigated what makes our brain-regularized network more robust. We found that our co-trained network is more sensitive to content than noise when compared to a Baseline network that we trained for image classification alone. Using DeepGaze-predicted saliency maps for ImageNet images, we found that our monkey co-trained network tends to be more sensitive to salient regions in a scene, reminiscent of existing theories on the role of V1 in the detection of object borders and bottom-up saliency. Overall, our work expands the promising research avenue of transferring inductive biases from the brain, and provides a novel analysis of the effects of our transfer.