Anyone with any doubts about the interest in AI and its use across enterprise technologies only needs to look at the example of the Intelligent Document Processing (IDP) market and the kind of verticals that are investing in it to quash those doubts. According to the Everest Group's recently published report, Intelligent Document Processing (IDP) State of the Market Report 2021 (purchase required) the market for this segment alone is estimated at $700-750 million in 2020 and expected to grow at a rate of 55-65% over the next year. Cost impact is now the key driver for intelligent document processing adoption, closely followed by improving operational efficiency and productivity. These solutions blend AI technologies to efficiently process all types of documents and feed the output into downstream applications. Optical character recognition (OCR), computer vision, machine learning (ML) and deep learning models, and natural language processing (NLP) are the key core technologies powering IDP capabilities.

Artificial intelligence is a fifth more accurate at predicting whether individuals are likely to become long-term recipients of benefits. A new method of predicting welfare dependency, developed by Dr. Dario Sansone from the University of Exeter Business School and Dr. Anna Zhu from RMIT University, could save governments billions in welfare costs as well as help them make earlier interventions to prevent long-term economic disadvantage and social exclusion. Their study found that machine learning algorithms, which improve through several iterations and use of big data, are 22% more accurate at predicting the proportion of time individuals are on income support than the standard early warning systems. The researchers were able to apply the off-the-shelf algorithms to the entire population of people enrolled in the Australian social security system between 2014 and 2018. This included demographic and socio-economic data of anyone who received a welfare payment from Australia's social security system Centrelink, whether on the grounds of unemployment, disability, having children, or being a carer, a student or of pensionable age.

We consider the task of feature selection for reconstruction which consists in choosing a small subset of features from which whole data instances can be reconstructed. This is of particular importance in several contexts involving for example costly physical measurements, sensor placement or information compression. To break the intrinsic combinatorial nature of this problem, we formulate the task as optimizing a binary mask distribution enabling an accurate reconstruction. We then face two main challenges. One concerns differentiability issues due to the binary distribution. The second one corresponds to the elimination of redundant information by selecting variables in a correlated fashion which requires modeling the covariance of the binary distribution. We address both issues by introducing a relaxation of the problem via a novel reparameterization of the logitNormal distribution. We demonstrate that the proposed method provides an effective exploration scheme and leads to efficient feature selection for reconstruction through evaluation on several high dimensional image benchmarks. We show that the method leverages the intrinsic geometry of the data, facilitating reconstruction.

Abstract-- This paper addresses task-allocation problems with uncertainty in situational awareness for distributed autonomous robots (DARs). The uncertainty propagation over a task-allocation process is done by using the Unscented transform that uses the Sigma-Point sampling mechanism. It has great potential to be employed for generic task-allocation schemes, in the sense that there is no need to modify an existing task-allocation method that has been developed without considering the uncertainty in the situational awareness. The proposed framework was tested in a simulated environment where the decision-maker needs to determine an optimal allocation of multiple locations assigned to multiple mobile flying robots whose locations come as random variables of known mean and covariance. The simulation result shows that the proposed stochastic task allocation approach generates an assignment with 30% less overall cost than the one without considering the uncertainty.

Saturation-style automated theorem provers (ATPs) based on the given clause procedure are today the strongest general reasoners for classical first-order logic. The clause selection heuristics in such systems are, however, often evaluating clauses in isolation, ignoring other clauses. This has changed recently by equipping the E/ENIGMA system with a graph neural network (GNN) that chooses the next given clause based on its evaluation in the context of previously selected clauses. In this work, we describe several algorithms and experiments with ENIGMA, advancing the idea of contextual evaluation based on learning important components of the graph of clauses.

What is the best simulation tool for robotics? This is a hard question to answer because many people (or their companies) specialize in one tool or another. Some simulators are better at one aspect of robotics than at others. When I'm asked to recommend the best simulation tool for robotics I have to find an expert and hope that they are current and across a wide range of simulation tools in order to give me the best advice, which was why I took particular note of the recent review paper from Australia's CSIRO, "A Review of Physics Simulators for Robotics Applications" by Jack Collins, Shelvin Chand, Anthony Vanderkop, and David Howard, published in IEEE Access (Volume: 9). "We have compiled a broad review of physics simulators for use within the major fields of robotics research. More specifically, we navigate through key sub-domains and discuss the features, benefits, applications and use-cases of the different simulators categorised by the respective research communities. Our review provides an extensive index of the leading physics simulators applicable to robotics researchers and aims to assist them in choosing the best simulator for their use case."

Over the last few months here at Carnegie Mellon University (Australia campus) I've been giving a set of talks on AI and the great leaps it has made in the last 5 or so years. I focus on disruptive technologies and give examples ranging from smart fridges and jackets to autonomous cars, robots, and drones. The title of one of my talks is "AI and the 4th Industrial Revolution". Indeed, we are living in the 4th industrial revolution – a significant time in the history of mankind. The first revolution occurred in the 18th century with the advent of mechanisation and steam power; the second came about 100 years later with the discovery of electrical energy (among other things); and the big one, the 3rd industrial revolution, occurred another 100 years after that (roughly around the 1970s) with things like nuclear energy, space expeditions, electronics, telecommunications, etc. coming to the fore. So, yes, we are living in a significant time.

Despite being designed for performance rather than cognitive plausibility, transformer language models have been found to be better at predicting metrics used to assess human language comprehension than language models with other architectures, such as recurrent neural networks. Based on how well they predict the N400, a neural signal associated with processing difficulty, we propose and provide evidence for one possible explanation - their predictions are affected by the preceding context in a way analogous to the effect of semantic facilitation in humans.

We present a new dataset of Wikipedia articles each paired with a knowledge graph, to facilitate the research in conditional text generation, graph generation and graph representation learning. Existing graph-text paired datasets typically contain small graphs and short text (1 or few sentences), thus limiting the capabilities of the models that can be learned on the data. Our new dataset WikiGraphs is collected by pairing each Wikipedia article from the established WikiText-103 benchmark (Merity et al., 2016) with a subgraph from the Freebase knowledge graph (Bollacker et al., 2008). This makes it easy to benchmark against other state-of-the-art text generative models that are capable of generating long paragraphs of coherent text. Both the graphs and the text data are of significantly larger scale compared to prior graph-text paired datasets. We present baseline graph neural network and transformer model results on our dataset for 3 tasks: graph -> text generation, graph -> text retrieval and text -> graph retrieval. We show that better conditioning on the graph provides gains in generation and retrieval quality but there is still large room for improvement.

For that, we train an Hourglass network using only feedback from a critic model. The Hourglass network learns to produce a mask to decrease the critic's score of a high score image and increase the critic's score of a low score image by swapping the masked areas between these two images. We trained the model on an imitation learning dataset from the NeurIPS 2020 MineRL Competition Track, where our model learned to mask rewarding objects in a complex interactive 3D environment with a sparse reward signal. This approach was part of the 1st place winning solution in this competition.