Current trends in AI are nothing if not remarkable. Day after day, we hear stories about systems and machines taking on tasks that, until very recently, we saw as the exclusive and permanent preserve of humankind: making medical diagnoses, drafting legal documents, designing buildings, and even composing music. Our concern here, though, is with something even more striking: the prospect of high-level machine intelligence systems that outperform human beings at essentially every task. This is not science fiction. In a recent survey the median estimate among leading computer scientists reported a 50% chance that this technology would arrive within 45 years.

Thanks to advancements in speech and natural language processing, there is hope that one day you may be able to ask your virtual assistant what the best salad ingredients are. Currently, it is possible to ask your home gadget to play music, or open on voice command, which is a feature already found in some many devices. If you speak Moroccan, Algerian, Egyptian, Sudanese, or any of the other dialects of the Arabic language, which are immensely varied from region to region, where some of them are mutually unintelligible, it is a different story. If your native tongue is Arabic, Finnish, Mongolian, Navajo, or any other language with high level of morphological complexity, you may feel left out. These complex constructs intrigued Ahmed Ali to find a solution.

Artificial intelligence (AI) was once the stuff of science fiction. It is used in mobile phone technology and motor vehicles. But concerns have emerged about the accountability of AI and related technologies like machine learning. In December 2020 a computer scientist, Timnit Gebru, was fired from Google's Ethical AI team. She had previously raised the alarm about the social effects of bias in AI technologies.

Unmanned aerial, ground and underwater vehicles are increasingly being used for national security in Japan and other countries, with the lack of training requirements and risk to human life seen as major benefits. Autonomous vehicles are seen as indispensable to Japan, which has a rapidly aging population and low birthrate. In the National Defense Program Guidelines adopted in late 2018, the government pledged to promote the Self-Defense Forces' use of artificial intelligence and other technological innovations for "automation and manpower-saving," with accelerating population declines now making the recruitment of SDF members a pressing issue. The Defense Ministry has launched a project to develop unmanned aircraft to escort the new fighter jet Japan plans to deploy as the successor to the Air Self-Defense Force's existing F-2s in fiscal 2035 at the earliest. Equipped with AI, the planned unmanned aircraft would be able to detect enemy fighters and missiles, fire missiles, stage electronic attacks and serve as a decoy to disorient enemy missiles.

Artificial neural networks have successfully tackled a large variety of problems by training extremely deep networks via back-propagation. A direct application of back-propagation to spiking neural networks contains biologically implausible components, like the weight transport problem or separate inference and learning phases. Various methods address different components individually, but a complete solution remains intangible. Here, we take an alternate approach that avoids back-propagation and its associated issues entirely. Recent work in deep learning proposed independently training each layer of a network via the information bottleneck (IB). Subsequent studies noted that this layer-wise approach circumvents error propagation across layers, leading to a biologically plausible paradigm. Unfortunately, the IB is computed using a batch of samples. The prior work addresses this with a weight update that only uses two samples (the current and previous sample). Our work takes a different approach by decomposing the weight update into a local and global component. The local component is Hebbian and only depends on the current sample. The global component computes a layer-wise modulatory signal that depends on a batch of samples. We show that this modulatory signal can be learned by an auxiliary circuit with working memory (WM) like a reservoir. Thus, we can use batch sizes greater than two, and the batch size determines the required capacity of the WM. To the best of our knowledge, our rule is the first biologically plausible mechanism to directly couple synaptic updates with a WM of the task. We evaluate our rule on synthetic datasets and image classification datasets like MNIST, and we explore the effect of the WM capacity on learning performance. We hope our work is a first-step towards understanding the mechanistic role of memory in learning.

Constrained tensor and matrix factorization models allow to extract interpretable patterns from multiway data. Therefore identifiability properties and efficient algorithms for constrained low-rank approximations are nowadays important research topics. This work deals with columns of factor matrices of a low-rank approximation being sparse in a known and possibly overcomplete basis, a model coined as Dictionary-based Low-Rank Approximation (DLRA). While earlier contributions focused on finding factor columns inside a dictionary of candidate columns, i.e. one-sparse approximations, this work is the first to tackle DLRA with sparsity larger than one. I propose to focus on the sparse-coding subproblem coined Mixed Sparse-Coding (MSC) that emerges when solving DLRA with an alternating optimization strategy. Several algorithms based on sparse-coding heuristics (greedy methods, convex relaxations) are provided to solve MSC. The performance of these heuristics is evaluated on simulated data. Then, I show how to adapt an efficient MSC solver based on the LASSO to compute Dictionary-based Matrix Factorization and Canonical Polyadic Decomposition in the context of hyperspectral image processing and chemometrics. These experiments suggest that DLRA extends the modeling capabilities of low-rank approximations, helps reducing estimation variance and enhances the identifiability and interpretability of estimated factors.

Sports game summarization aims at generating sports news from live commentaries. However, existing datasets are all constructed through automated collection and cleaning processes, resulting in a lot of noise. Besides, current works neglect the knowledge gap between live commentaries and sports news, which limits the performance of sports game summarization. In this paper, we introduce K-SportsSum, a new dataset with two characteristics: (1) K-SportsSum collects a large amount of data from massive games. It has 7,854 commentary-news pairs. To improve the quality, K-SportsSum employs a manual cleaning process; (2) Different from existing datasets, to narrow the knowledge gap, K-SportsSum further provides a large-scale knowledge corpus that contains the information of 523 sports teams and 14,724 sports players. Additionally, we also introduce a knowledge-enhanced summarizer that utilizes both live commentaries and the knowledge to generate sports news. Extensive experiments on K-SportsSum and SportsSum datasets show that our model achieves new state-of-the-art performances. Qualitative analysis and human study further verify that our model generates more informative sports news.

Artificial intelligence (AI) compute solutions provider Cerebras Systems and G42, the UAE-based AI and cloud computing company, have signed a memorandum of understanding (MOU) at GMIS, under which they will bring high performance AI capabilities to the Middle East. G42, who manages the region's largest cloud computing infrastructure, will upgrade its technology stack with Cerebras' CS-2 systems to deliver AI compute capabilities to its partners and the broader ecosystem. "Cerebras, in partnership with our extraordinary customers, has achieved incredible breakthroughs that are transforming AI," said Andrew Feldman, CEO and Co-Founder of Cerebras Systems. "We are privileged to be working with G42, the Middle East's leader in AI innovation. Together we will transform our industry, making the impossible commonplace."

Analyzing the behaviour of a population in response to disease and interventions is critical to unearth variability in healthcare as well as understand sub-populations that require specialized attention, but also to assist in designing future interventions. Two aspects become very essential in such analysis namely: i) Discovery of differentiating patterns exhibited by sub-populations, and ii) Characterization of the identified subpopulations. For the discovery phase, an array of approaches in the anomalous pattern detection literature have been employed to reveal differentiating patterns, especially to identify anomalous subgroups. However, these techniques are limited to describing the anomalous subgroups and offer little in form of insightful characterization, thereby limiting interpretability and understanding of these data-driven techniques in clinical practices. In this work, we propose an analysis of differentiated output (rather than discovery) and quantify anomalousness similarly to the counter-factual setting. To this end we design an approach to perform post-discovery analysis of anomalous subsets, in which we initially identify the most important features on the anomalousness of the subsets, then by perturbation, the approach seeks to identify the least number of changes necessary to lose anomalousness. Our approach is presented and the evaluation results on the 2019 MarketScan Commercial Claims and Medicare data, show that extra insights can be obtained by extrapolated examination of the identified subgroups.

Collaborative deep reinforcement learning (CDRL) algorithms in which multiple agents can coordinate over a wireless network is a promising approach to enable future intelligent and autonomous systems that rely on real-time decision-making in complex dynamic environments. Nonetheless, in practical scenarios, CDRL faces many challenges due to the heterogeneity of agents and their learning tasks, different environments, time constraints of the learning, and resource limitations of wireless networks. To address these challenges, in this paper, a novel semantic-aware CDRL method is proposed to enable a group of heterogeneous untrained agents with semantically-linked DRL tasks to collaborate efficiently across a resource-constrained wireless cellular network. To this end, a new heterogeneous federated DRL (HFDRL) algorithm is proposed to select the best subset of semantically relevant DRL agents for collaboration. The proposed approach then jointly optimizes the training loss and wireless bandwidth allocation for the cooperating selected agents in order to train each agent within the time limit of its real-time task. Simulation results show the superior performance of the proposed algorithm compared to state-of-the-art baselines.