Autonomous driving systems need to handle complex scenarios such as lane following, avoiding collisions, taking turns, and responding to traffic signals. In recent years, approaches based on end-to-end behavioral cloning have demonstrated remarkable performance in point-to-point navigational scenarios, using a realistic simulator and standard benchmarks. Offline imitation learning is readily available, as it does not require expensive hand annotation or interaction with the target environment, but it is difficult to obtain a reliable system. In addition, existing methods have not specifically addressed the learning of reaction for traffic lights, which are a rare occurrence in the training datasets. Inspired by the previous work on multi-task learning and attention modeling, we propose a novel multi-task attention-aware network in the conditional imitation learning (CIL) framework. This does not only improve the success rate of standard benchmarks, but also the ability to react to traffic lights, which we show with standard benchmarks.

Recent machine-learning approaches to deterministic search and domain-independent planning employ policy learning to speed up search. Unfortunately, when attempting to solve a search problem by successively applying a policy, no guarantees can be given on solution quality. The problem of how to effectively use a learned policy within a bounded-suboptimal search algorithm remains largely as an open question. In this paper, we propose various ways in which such policies can be integrated into Focal Search, assuming that the policy is a neural network classifier. Furthermore, we provide mathematical foundations for some of the resulting algorithms. To evaluate the resulting algorithms over a number of policies with varying accuracy, we use synthetic policies which can be generated for a target accuracy for problems where the search space can be held in memory. We evaluate our focal search variants over three benchmark domains using our synthetic approach, and on the 15-puzzle using a neural network learned using 1.5 million examples. We observe that \emph{Discrepancy Focal Search}, which we show expands the node which maximizes an approximation of the probability that its corresponding path is a prefix of an optimal path, obtains, in general, the best results in terms of runtime and solution quality.

The investment of time and resources for better strategies and methodologies to tackle a potential pandemic is key to deal with potential outbreaks of new variants or other viruses in the future. In this work, we recreated the scene of a year ago, 2020, when the pandemic erupted across the world for the fifty countries with more COVID-19 cases reported. We performed some experiments in which we compare state-of-the-art machine learning algorithms, such as LSTM, against online incremental machine learning algorithms to adapt them to the daily changes in the spread of the disease and predict future COVID-19 cases. To compare the methods, we performed three experiments: In the first one, we trained the models using only data from the country we predicted. In the second one, we use data from all fifty countries to train and predict each of them. In the first and second experiment, we used a static hold-out approach for all methods. In the third experiment, we trained the incremental methods sequentially, using a prequential evaluation. This scheme is not suitable for most state-of-the-art machine learning algorithms because they need to be retrained from scratch for every batch of predictions, causing a computational burden. Results show that incremental methods are a promising approach to adapt to changes of the disease over time; they are always up to date with the last state of the data distribution, and they have a significantly lower computational cost than other techniques such as LSTMs.

Question answering from semi-structured tables can be seen as a semantic parsing task and is significant and practical for pushing the boundary of natural language understanding. Existing research mainly focuses on understanding contents from unstructured evidence, e.g., news, natural language sentences, and documents. The task of verification from structured evidence, such as tables, charts, and databases, is still less explored. This paper describes sattiy team's system in SemEval-2021 task 9: Statement Verification and Evidence Finding with Tables (SEM-TAB-FACT). This competition aims to verify statements and to find evidence from tables for scientific articles and to promote the proper interpretation of the surrounding article. In this paper, we exploited ensemble models of pre-trained language models over tables, TaPas and TaBERT, for Task A and adjust the result based on some rules extracted for Task B. Finally, in the leaderboard, we attain the F1 scores of 0.8496 and 0.7732 in Task A for the 2-way and 3-way evaluation, respectively, and the F1 score of 0.4856 in Task B.

A collaboration from UoC Berkeley, Stanford University and Facebook offers a deeper and more granular picture of the actual state of poverty in and across nations, through the use of machine learning. The research, entitled Micro-Estimates of Wealth for all Low-and Middle-Income Countries, is accompanied by a beta website that allows users to interactively explore the absolute and relative economic state of fine-grained areas and pockets of poverty in low and middle-income countries. The framework incorporates data from satellite imagery, topographic maps, mobile phone networks and aggregated anonymized data from Facebook, and is verified against extensive face-to-face surveys, for purposes of reporting relative wealth disparity in a region, rather than absolute estimates of income. A map of global poverty, weighted towards the most affected areas. The system has been adopted by the government of Nigeria as a basis for administering social protection programs, and runs in tandem with the existing framework from the World Bank, the National Social Safety nets Project (NASSP).

A new analysis of the upper body of famed fossil'Little Foot,' a near-complete skeleton of a hominin that lived 3.67 million years ago, reveals she was a creature adapted to living in trees. Scientists at the University of Southern California (USC) examined Little Foot's shoulder assembly, showing it supported arms well suited for hanging from branches and moving up and down trees – similar to that of apes. The latest analysis'provides the best evidence yet of how human ancestors used their arms more than 3 million years ago,' said Kristian J. Carlson, lead author of the study. The findings also suggests the structural similarities in the shoulder between humans and African apes are much more recent, and persisted much longer, than previously believed. A new analysis of the upper body of famed fossil'Little Foot,' a near-complete skeleton of a hominin that lived 3.67 million years ago, reveals she was a creature adapted to living in trees Little Foot was discovered in South Africa in 1994 and has allowed scientists to travel back in time to learn more about the evolution of humans.

A UK technology company is inserting customised product placement into films and TV shows – even those that were originally released decades ago. The firm uses artificial intelligence (AI) to analyse films and TV episodes for space where the ads or objects can be subtly inserted. It means old Hollywood classics like Casablanca or The Great Escape could soon appear on streaming services with the newest ads in the background, like a new Apple smartphone or the latest McDonald's whopper. Streaming services including Netflix and Amazon Prime Video could be temped by large offers from companies to insert their ads to content, to accompany the subscription fees from its userbase. Mirriad's technology could even allow different ads to be seen by different people, based on their internet search history, just like targeted ads on Facebook.

Police in Texas investigating a Tesla car crash in which two men died will serve search warrants on the company to ascertain if the vehicle's autopilot mode was engaged at the time of the incident. However Tesla's CEO, Elon Musk, has said the self-driving feature was not being used, based on an internal probe by the company. In the incident, two men, both in their 50s, were killed after their 2019 Tesla Model S crashed into a tree and caught fire. According to police reports, the car was travelling at a high speed and failed to negotiate a curve in the road. Texas police noted that nobody was at the driving seat at the time of impact, raising doubts about the involvement of the car's autopilot mode.

Top-k recommendation seeks to deliver a personalized list of k items to each individual user. An established methodology in the literature based on matrix factorization (MF), which usually represents users and items as vectors in low-dimensional space, is an effective approach to recommender systems, thanks to its superior performance in terms of recommendation quality and scalability. A typical matrix factorization recommender system has two main phases: preference elicitation and recommendation retrieval. The former analyzes user-generated data to learn user preferences and item characteristics in the form of latent feature vectors, whereas the latter ranks the candidate items based on the learnt vectors and returns the top-k items from the ranked list. For preference elicitation, there have been numerous works to build accurate MF-based recommendation algorithms that can learn from large datasets. However, for the recommendation retrieval phase, naively scanning a large number of items to identify the few most relevant ones may inhibit truly real-time applications. In this work, we survey recent advances and state-of-the-art approaches in the literature that enable fast and accurate retrieval for MF-based personalized recommendations. Also, we include analytical discussions of approaches along different dimensions to provide the readers with a more comprehensive understanding of the surveyed works.

We establish a link between multiwinner elections and apportionment problems by showing how approval-based multiwinner election rules can be interpreted as methods of apportionment. We consider several multiwinner rules and observe that they induce apportionment methods that are well-established in the literature on proportional representation. For instance, we show that Proportional Approval Voting induces the D'Hondt method and that Monroe's rule induces the largest reminder method. We also consider properties of apportionment methods and exhibit multiwinner rules that induce apportionment methods satisfying these properties.