Paris-CARLA-3D is a dataset of several dense colored point clouds of outdoor environments built by a mobile LiDAR and camera system. The data are composed of two sets with synthetic data from the open source CARLA simulator (700 million points) and real data acquired in the city of Paris (60 million points), hence the name Paris-CARLA-3D. One of the advantages of this dataset is to have simulated the same LiDAR and camera platform in the open source CARLA simulator as the one used to produce the real data. In addition, manual annotation of the classes using the semantic tags of CARLA was performed on the real data, allowing the testing of transfer methods from the synthetic to the real data. The objective of this dataset is to provide a challenging dataset to evaluate and improve methods on difficult vision tasks for the 3D mapping of outdoor environments: semantic segmentation, instance segmentation, and scene completion. For each task, we describe the evaluation protocol as well as the experiments carried out to establish a baseline.

Social network alignment aims at aligning person identities across social networks. Embedding based models have been shown effective for the alignment where the structural proximity preserving objective is typically adopted for the model training. With the observation that ``overly-close'' user embeddings are unavoidable for such models causing alignment inaccuracy, we propose a novel learning framework which tries to enforce the resulting embeddings to be more widely apart among the users via the introduction of carefully implanted pseudo anchors. We further proposed a meta-learning algorithm to guide the updating of the pseudo anchor embeddings during the learning process. The proposed intervention via the use of pseudo anchors and meta-learning allows the learning framework to be applicable to a wide spectrum of network alignment methods. We have incorporated the proposed learning framework into several state-of-the-art models. Our experimental results demonstrate its efficacy where the methods with the pseudo anchors implanted can outperform their counterparts without pseudo anchors by a fairly large margin, especially when there only exist very few labeled anchors.

Active inference is a state-of-the-art framework for modelling the brain that explains a wide range of mechanisms such as habit formation, dopaminergic discharge and curiosity. However, recent implementations suffer from an exponential (space and time) complexity class when computing the prior over all the possible policies up to the time horizon. Fountas et al. (2020) used Monte Carlo tree search to address this problem, leading to very good results in two different tasks. Additionally, Champion et al. (2021a) proposed a tree search approach based on structure learning. This was enabled by the development of a variational message passing approach to active inference (Champion et al., 2021b), which enables compositional construction of Bayesian networks for active inference. However, this message passing tree search approach, which we call branching-time active inference (BTAI), has never been tested empirically. In this paper, we present an experimental study of the approach (Champion et al., 2021a) in the context of a maze solving agent. In this context, we show that both improved prior preferences and deeper search help mitigate the vulnerability to local minima. Then, we compare BTAI to standard active inference (AI) on a graph navigation task. We show that for small graphs, both BTAI and AI successfully solve the task. For larger graphs, AI exhibits an exponential (space) complexity class, making the approach intractable. However, BTAI explores the space of policies more efficiently, successfully scaling to larger graphs.

Over the last 10 to 15 years, active inference has helped to explain various brain mechanisms from habit formation to dopaminergic discharge and even modelling curiosity. However, the current implementations suffer from an exponential (space and time) complexity class when computing the prior over all the possible policies up to the time-horizon. Fountas et al (2020) used Monte Carlo tree search to address this problem, leading to impressive results in two different tasks. In this paper, we present an alternative framework that aims to unify tree search and active inference by casting planning as a structure learning problem. Two tree search algorithms are then presented. The first propagates the expected free energy forward in time (i.e., towards the leaves), while the second propagates it backward (i.e., towards the root). Then, we demonstrate that forward and backward propagations are related to active inference and sophisticated inference, respectively, thereby clarifying the differences between those two planning strategies.

Abstract--Supporting the current trend in the AI community, we propose the AI Journey 2021 Challenge called Fusion Brain which is targeted to make the universal architecture process different modalities (namely, images, texts, and code) and to solve multiple tasks for vision and language. We have created datasets for each task to test the participants' submissions on it. Moreover, we have opened a new handwritten dataset in both Russian and English, which consists of 94,128 pairs of images and texts. The Russian part of the dataset is the largest Russian handwritten dataset in the world. We also propose the baseline solution and corresponding task-specific solutions as well as overall metrics.

Onboard autonomy technologies such as planning and scheduling, identification of scientific targets, and content-based data summarization, will lead to exciting new space science missions. However, the challenge of operating missions with such onboard autonomous capabilities has not been studied to a level of detail sufficient for consideration in mission concepts. These autonomy capabilities will require changes to current operations processes, practices, and tools. We have developed a case study to assess the changes needed to enable operators and scientists to operate an autonomous spacecraft by facilitating a common model between the ground personnel and the onboard algorithms. We assess the new operations tools and workflows necessary to enable operators and scientists to convey their desired intent to the spacecraft, and to be able to reconstruct and explain the decisions made onboard and the state of the spacecraft. Mock-ups of these tools were used in a user study to understand the effectiveness of the processes and tools in enabling a shared framework of understanding, and in the ability of the operators and scientists to effectively achieve mission science objectives.

IEEE says the most important technologies in 2022 will be AI/machine learning, cloud computing and 5G wireless. That comes in a new report published by the large technical professional organization titled "The Impact of Technology in 2022 and Beyond: an IEEE Global Study," based on an October survey of 350 chief information officers, chief technology officers and technology leaders from the U.S., U.K., China, India and Brazil who were asked about key technology trends, priorities and predictions for 2022 and beyond. "Among total respondents, more than one in five (21 percent) say AI and machine learning, cloud computing (20 percent), and 5G (17 percent) will be the most important technologies next year," IEEE said in a Nov. 18 announcement. "Because of the global pandemic, technology leaders surveyed said in 2021 they accelerated adoption of cloud computing (60 percent), AI and machine learning (51 percent), and 5G (46 percent), among others." The report includes respondent data for 12 questions, starting off with: "Which will be the most important technology in 2022?"

Welcome to The TechCrunch Exchange, a weekly startups-and-markets newsletter. It's inspired by the daily TechCrunch column where it gets its name. If you aren't in the United States, it's a little hard to explain. In short, certain deficiencies in our policing and judicial systems flared brightly as the week came to a close. So, today's Exchange newsletter will be shorter than intended. Hug the people you love, and everyone else.

The cybersecurity concerns most likely to be in technology leaders' top two are issues related to the mobile and hybrid workforce including employees using their own devices (39%) and cloud vulnerability (35%). Additional concerns include data center vulnerability (27%), a coordinated attack on their network (26%), and a ransomware attack (25%). Notably, 59% of all technology leaders surveyed currently use or in the next five years plan to use drones for security, surveillance, or threat prevention as part of their business model. There are regional disparities though. Current drone use for security or plans to do so in the next five years are strongest in Brazil (78%), China (71%), India (60%), and the U.S. (52%) compared to only (32%) in the U.K., where 48% of respondents say they have no plans to use drones in their business.

In this paper, we present an algorithm for creating a synthetic population for the Greater Melbourne area using a combination of machine learning, probabilistic, and gravity-based approaches. We combine these techniques in a hybrid model with three primary innovations: 1. when assigning activity patterns, we generate individual activity chains for every agent, tailored to their cohort; 2. when selecting destinations, we aim to strike a balance between the distance-decay of trip lengths and the activity-based attraction of destination locations; and 3. we take into account the number of trips remaining for an agent so as to ensure they do not select a destination that would be unreasonable to return home from. Our method is completely open and replicable, requiring only publicly available data to generate a synthetic population of agents compatible with commonly used agent-based modeling software such as MATSim. The synthetic population was found to be accurate in terms of distance distribution, mode choice, and destination choice for a variety of population sizes.