Realiste, a leading AI developer in the real estate market has finally launched in the Middle East, changing the real-estate and housing landscape using the latest advanced technologies within all operations. Realiste is an AI-based real estate market development company committed to providing users with accurate and timely market value appraisals. The company's mission is to digitise the real estate market of every major city across the world, while offering free access to appraisals and personalised recommendations. Since launching in December 2021 it has established operations in Riyadh, Dubai, London, New York, and Moscow and are planning more expansions in the next year. Realiste has successfully fielded an application capable of monitoring the market round-the-clock and displaying the true value of real estate, as well as predicting price movements of properties for the next 6 to 12 months.

Recent years have seen the rapid development of fairness-aware machine learning in mitigating unfairness or discrimination in decision-making in a wide range of applications. However, much less attention has been paid to the fairness-aware multi-objective optimization, which is indeed commonly seen in real life, such as fair resource allocation problems and data driven multi-objective optimization problems. This paper aims to illuminate and broaden our understanding of multi-objective optimization from the perspective of fairness. To this end, we start with a discussion of user preferences in multi-objective optimization and then explore its relationship to fairness in machine learning and multi-objective optimization. Following the above discussions, representative cases of fairness-aware multiobjective optimization are presented, further elaborating the importance of fairness in traditional multi-objective optimization, data-driven optimization and federated optimization. Finally, challenges and opportunities in fairness-aware multi-objective optimization are addressed. We hope that this article makes a small step forward towards understanding fairness in the context of optimization and promote research interest in fairness-aware multi-objective optimization.

Deep Neural Network (DNN) models are usually trained sequentially from one layer to another, which causes forward, backward and update locking's problems, leading to poor performance in terms of training time. The existing parallel strategies to mitigate these problems provide suboptimal runtime performance. In this work, we have proposed a novel layer-wise partitioning and merging, forward and backward pass parallel framework to provide better training performance. The novelty of the proposed work consists of 1) a layer-wise partition and merging model which can minimise communication overhead between devices without the memory cost of existing strategies during the training process; 2) a forward pass and backward pass parallelisation and optimisation to address the update locking problem and minimise the total training cost. The experimental evaluation on real use cases shows that the proposed method outperforms the state-of-the-art approaches in terms of training speed; and achieves almost linear speedup without compromising the accuracy performance of the non-parallel approach.

Code summaries help developers comprehend programs and reduce their time to infer the program functionalities during software maintenance. Recent efforts resort to deep learning techniques such as sequence-to-sequence models for generating accurate code summaries, among which Transformer-based approaches have achieved promising performance. However, effectively integrating the code structure information into the Transformer is under-explored in this task domain. In this paper, we propose a novel approach named SG-Trans to incorporate code structural properties into Transformer. Specifically, we inject the local symbolic information (e.g., code tokens and statements) and global syntactic structure (e.g., data flow graph) into the self-attention module of Transformer as inductive bias. To further capture the hierarchical characteristics of code, the local information and global structure are designed to distribute in the attention heads of lower layers and high layers of Transformer. Extensive evaluation shows the superior performance of SG-Trans over the state-of-the-art approaches. Compared with the best-performing baseline, SG-Trans still improves 1.4% and 2.0% in terms of METEOR score, a metric widely used for measuring generation quality, respectively on two benchmark datasets.

Neural Architecture Search (NAS) methods have been successfully applied to image tasks with excellent results. However, NAS methods are often complex and tend to converge to local minima as soon as generated architectures seem to yield good results. This paper proposes GEA, a novel approach for guided NAS. GEA guides the evolution by exploring the search space by generating and evaluating several architectures in each generation at initialisation stage using a zero-proxy estimator, where only the highest-scoring architecture is trained and kept for the next generation. Subsequently, GEA continuously extracts knowledge about the search space without increased complexity by generating several off-springs from an existing architecture at each generation. More, GEA forces exploitation of the most performant architectures by descendant generation while simultaneously driving exploration through parent mutation and favouring younger architectures to the detriment of older ones. Experimental results demonstrate the effectiveness of the proposed method, and extensive ablation studies evaluate the importance of different parameters. Results show that GEA achieves state-of-the-art results on all data sets of NAS-Bench-101, NAS-Bench-201 and TransNAS-Bench-101 benchmarks.

Pretrained language models have become the standard approach for many NLP tasks due to strong performance, but they are very expensive to train. We propose a simple and efficient learning framework, TLM, that does not rely on large-scale pretraining. Given some labeled task data and a large general corpus, TLM uses task data as queries to retrieve a tiny subset of the general corpus and jointly optimizes the task objective and the language modeling objective from scratch. On eight classification datasets in four domains, TLM achieves results better than or similar to pretrained language models (e.g., RoBERTa-Large) while reducing the training FLOPs by two orders of magnitude. With high accuracy and efficiency, we hope TLM will contribute to democratizing NLP and expediting its development.

We propose FiberNet, a method to estimate \emph{in-vivo} the cardiac fiber architecture of the human atria from multiple catheter recordings of the electrical activation. Cardiac fibers play a central role in the electro-mechanical function of the heart, yet they are difficult to determine in-vivo, and hence rarely truly patient-specific in existing cardiac models. FiberNet learns the fiber arrangement by solving an inverse problem with physics-informed neural networks. The inverse problem amounts to identifying the conduction velocity tensor of a cardiac propagation model from a set of sparse activation maps. The use of multiple maps enables the simultaneous identification of all the components of the conduction velocity tensor, including the local fiber angle. We extensively test FiberNet on synthetic 2-D and 3-D examples, diffusion tensor fibers, and a patient-specific case. We show that 3 maps are sufficient to accurately capture the fibers, also in the presence of noise. With fewer maps, the role of regularization becomes prominent. Moreover, we show that the fitted model can robustly reproduce unseen activation maps. We envision that FiberNet will help the creation of patient-specific models for personalized medicine. The full code is available at http://github.com/fsahli/FiberNet.

As Netflix's profits have begun to wane, some business analysts have argued that, when compared to rivals like HBO Max or Amazon Prime, Netflix has a "quantity over quality" problem with its content. Critics have joined this bandwagon, turning on the streaming service's wide array of original material. This trend manifested itself most recently in the wake of the release of the television series Resident Evil, loosely based on the Capcom survival-horror video game from the 1990s. A week after its July 14th release, the show has been snubbed by critics, earning a 51% on Rotten Tomatoes, as well as absolutely savaged by viewers who rated the show on that website, leaving a bloodbath of one-star reviews and an "Audience Score" of 26%. Given the history of the Resident Evil movie franchise--six schlocky Milla Jovovich vehicles that contained, in total, exactly one memorable scene; one forgettable 2021 prequel--this kind of critical drubbing might be the expected outcome.

In our mission toward powering careers through tech education, we are doubling down on the support that we offer to our students. As a part of this, we want to extend an opportunity for you to become a Tutor for the Digital Marketing program with Udacity. Udacity is committed to creating economic empowerment and a more diverse and equitable world. To ensure that our products and culture continue to incorporate everyone's perspectives and experience we never discriminate on the basis of race, color, religion, sex, gender, gender identity or expression, sexual orientation, marital status, national origin, ancestry, disability, medical condition (including genetic information), age, veteran status or military status, denial of pregnancy disability leave or reasonable accommodation.

Udunna C. Anazodo, PhD, is an assistant professor of neurology and neurosurgery at the Montreal Neurological Institute at McGill University. She is the founder and chair of the Consortium for Advancement of MRI Education and Research in Africa (CAMERA) and is currently leading efforts to create the Africa Neuroimaging Archive (AfNiA). Her research interests include diagnostic image analysis using artificial intelligence methods to enable quantitative PET and MRI for population neuroscience and global health. Maruf Adewole, MSc, is a medical physicist. He holds a bachelor's degree in physics and master's degree in medical physics from the Federal University of Technology Akure and University of Lagos, Nigeria, respectively.