Deep Neural Networks achieve state-of-the-art results in many different problem settings by exploiting vast amounts of training data. However, collecting, storing and - in the case of supervised learning - labelling the data is expensive and time-consuming. Additionally, assessing the networks' generalization abilities or predicting how the inferred output changes under input transformations is complicated since the networks are usually treated as a black box. Both of these problems can be mitigated by incorporating prior knowledge into the neural network. One promising approach, inspired by the success of convolutional neural networks in computer vision tasks, is to incorporate knowledge about symmetric geometrical transformations of the problem to solve that affect the output in a predictable way. This promises an increased data efficiency and more interpretable network outputs. In this survey, we try to give a concise overview about different approaches that incorporate geometrical prior knowledge into neural networks. Additionally, we connect those methods to 3D object detection for autonomous driving, where we expect promising results when applying those methods.

This paper addresses a new semantic multi-robot planning problem in uncertain and dynamic environments. Particularly, the environment is occupied with non-cooperative, mobile, uncertain labeled targets. These targets are governed by stochastic dynamics while their current and future positions as well as their semantic labels are uncertain. Our goal is to control mobile sensing robots so that they can accomplish collaborative semantic tasks defined over the uncertain current/future positions and labels of these targets. We express these tasks using Linear Temporal Logic (LTL). We propose a sampling-based approach that explores the robot motion space, the mission specification space, as well as the future configurations of the labeled targets to design optimal paths. These paths are revised online to adapt to uncertain perceptual feedback. To the best of our knowledge, this is the first work that addresses semantic mission planning problems in uncertain and dynamic semantic environments. We provide extensive experiments that demonstrate the efficiency of the proposed method

Finding important features that contribute to the prediction of neural models is an active area of research in explainable AI. Neural models are opaque and finding such features sheds light on a better understanding of their predictions. In contrast, in this work, we present an inverse perspective of distractor features: features that cast doubt about the prediction by affecting the model's confidence in its prediction. Understanding distractors provide a complementary view of the features' relevance in the predictions of neural models. In this paper, we apply a reduction-based technique to find distractors and provide our preliminary results of their impacts and types. Our experiments across various tasks, models, and datasets of code reveal that the removal of tokens can have a significant impact on the confidence of models in their predictions and the categories of tokens can also play a vital role in the model's confidence. Our study aims to enhance the transparency of models by emphasizing those tokens that significantly influence the confidence of the models.

Saxo Capital Markets (Australia) Limited prepares and distributes information/research produced within the Saxo Bank Group for informational purposes only. In addition to the disclaimer below, if any general advice is provided, such advice does not take into account your individual objectives, financial situation or needs. You should consider the appropriateness of trading any financial instrument as trading can result in losses that exceed your initial investment. Please refer to our Analysis Disclaimer, and our Financial Services Guide and Product Disclosure Statement. All legal documentation and disclaimers can be found at https://www.home.saxo/en-au/legal/.

A new method to assess the quality of organs for donation is set to revolutionise the transplant system – and it could help save lives and tens of millions of pounds. The National Institute for Health and Care Research (NIHR) is contributing more than £1 million in funding to develop the new technology, which is known as Organ Quality Assessment (OrQA). It works in the same way as Artificial Intelligence-based facial recognition to evaluate the quality of an organ. It is estimated the technology could result in up to 200 more patients receiving kidney transplants and 100 more receiving liver transplants a year in the UK. Colin Wilson, transplant surgeon at Newcastle upon Tyne Hospitals NHS Foundation Trust and co-lead of the project, said: "Transplantation is the best treatment for patients with organ failure, but unfortunately some organs can't be used due to concerns they won't function properly once transplanted. "The software we have developed'scores' the quality of the organ and aims to support surgeons to assess if the organ is healthy enough to be transplanted.

Accuracy competition: This competition hosted by Walmart aimed to forecast daily sales of 3,049 products in 10 stores over a period of 28 days. Participants were required to forecast the sales of each product for each day of the competition using historical sales data provided by Walmart. This competition taught participants how to deal with a large dataset with multiple features and how to use various time-series forecasting techniques, such as ARIMA and Prophet. The Rossmann Store Sales competition: This competition aimed to forecast the daily sales of 1,115 Rossmann stores located in Germany. Participants were required to forecast sales for the next six weeks, taking into account factors such as promotions, school holidays, and store closures.

In 2023, the financial sector is predicted to experience massive changes as traditional financial institutions (FIs) compete with Fintechs and digital services for supremacy. The launch of new digital banks like Maribank, Boost Holdings, and Sea Ltd has utilized technology and data to deliver innovative and personalized financial services to draw new customers in Singapore and Malaysia. In Singapore, Deputy Prime Minister and Minister for Finance Lawrence Wong emphasized the potential for digital technologies to create streamlined and efficient financial operations. Amplifying this point, the Monetary Authority of Singapore (MAS) and the Ministry of Finance (MOF) collaborated with FIs to provide digital solutions that reduce processing time for government guarantees and insurance bonds. Digital transformation will be key to altering the way financial institutions deliver positive customer engagement in 2023.

As mobile robots become useful performing everyday tasks in complex real-world environments, they must be able to traverse a range of difficult terrain types such as stairs, stepping stones, gaps, jumps and narrow passages. This work investigated traversing these types of environments with a bipedal robot (simulation experiments), and a tracked robot (real world). Developing a traditional monolithic controller for traversing all terrain types is challenging, and for large physical robots realistic test facilities are required and safety must be ensured. An alternative is a suite of simple behaviour controllers that can be composed to achieve complex tasks. This work efficiently trained complex behaviours to enable mobile robots to traverse difficult terrain. By minimising retraining as new behaviours became available, robots were able to traverse increasingly complex terrain sets, leading toward the development of scalable behaviour libraries.

Research and education in machine learning needs diverse, representative, and open datasets that contain sufficient samples to handle the necessary training, validation, and testing tasks. Currently, the Recommender Systems area includes a large number of subfields in which accuracy and beyond accuracy quality measures are continuously improved. To feed this research variety, it is necessary and convenient to reinforce the existing datasets with synthetic ones. This paper proposes a Generative Adversarial Network (GAN)-based method to generate collaborative filtering datasets in a parameterized way, by selecting their preferred number of users, items, samples, and stochastic variability. This parameterization cannot be made using regular GANs. Our GAN model is fed with dense, short, and continuous embedding representations of items and users, instead of sparse, large, and discrete vectors, to make an accurate and quick learning, compared to the traditional approach based on large and sparse input vectors. The proposed architecture includes a DeepMF model to extract the dense user and item embeddings, as well as a clustering process to convert from the dense GAN generated samples to the discrete and sparse ones, necessary to create each required synthetic dataset. The results of three different source datasets show adequate distributions and expected quality values and evolutions on the generated datasets compared to the source ones. Synthetic datasets and source codes are available to researchers.

Neural Machine Translation (NMT) systems are used in various applications. However, it has been shown that they are vulnerable to very small perturbations of their inputs, known as adversarial attacks. In this paper, we propose a new targeted adversarial attack against NMT models. In particular, our goal is to insert a predefined target keyword into the translation of the adversarial sentence while maintaining similarity between the original sentence and the perturbed one in the source domain. To this aim, we propose an optimization problem, including an adversarial loss term and a similarity term. We use gradient projection in the embedding space to craft an adversarial sentence. Experimental results show that our attack outperforms Seq2Sick, the other targeted adversarial attack against NMT models, in terms of success rate and decrease in translation quality. Our attack succeeds in inserting a keyword into the translation for more than 75% of sentences while similarity with the original sentence stays preserved.