Deep neural models (e.g. Transformer) naturally learn spurious features, which create a ``shortcut'' between the labels and inputs, thus impairing the generalization and robustness. This paper advances the self-attention mechanism to its robust variant for Transformer-based pre-trained language models (e.g. BERT). We propose \textit{Adversarial Self-Attention} mechanism (ASA), which adversarially biases the attentions to effectively suppress the model reliance on features (e.g. specific keywords) and encourage its exploration of broader semantics. We conduct a comprehensive evaluation across a wide range of tasks for both pre-training and fine-tuning stages. For pre-training, ASA unfolds remarkable performance gains compared to naive training for longer steps. For fine-tuning, ASA-empowered models outweigh naive models by a large margin considering both generalization and robustness.

However, many users are familiar with the frustrating experience of repeatedly not being understood by their voice assistant [16], so much so that frustration with ASR has become a culturally-shared source of comedy [4, 32]. Bias auditing of ASR services has quantified these experiences. English language ASR has higher error rates: for Black Americans compared to white Americans [24, 45], for stigmatised British accents compared to favored British accents [28], for Scottish speakers compared to speakers from California and New Zealand [44], for speakers whose first language is a tone language compared to those whose first language is not [2], for speakers with Indian accents compared to speakers who with "American" accents [31], for speakers whose first language is English compared to those for whom it is not [28]. It should go without saying, but everyone has an accent - there is no "unaccented" version of English [26]. Due to colonization and globalization, different Englishes are spoken around the world. While some English accents may be favored by those with class, race, and national origin privilege [28], there is no technical barrier to building an ASR system which works well on any particular accent. So we are left with the question, why does ASR performance vary as it does as a function of the global English accent spoken?

Hyperdimensional computing (HDC) is a paradigm for data representation and learning originating in computational neuroscience. HDC represents data as high-dimensional, low-precision vectors which can be used for a variety of information processing tasks like learning or recall. The mapping to high-dimensional space is a fundamental problem in HDC, and existing methods encounter scalability issues when the input data itself is high-dimensional. In this work, we explore a family of streaming encoding techniques based on hashing. We show formally that these methods enjoy comparable guarantees on performance for learning applications while being substantially more efficient than existing alternatives. We validate these results experimentally on a popular high-dimensional classification problem and show that our approach easily scales to very large data sets.

This work studies the combinatorial optimization problem of finding an optimal core tensor shape, also called multilinear rank, for a size-constrained Tucker decomposition. We give an algorithm with provable approximation guarantees for its reconstruction error via connections to higher-order singular values. Specifically, we introduce a novel Tucker packing problem, which we prove is NP-hard, and give a polynomial-time approximation scheme based on a reduction to the 2-dimensional knapsack problem with a matroid constraint. We also generalize our techniques to tree tensor network decompositions. We implement our algorithm using an integer programming solver, and show that its solution quality is competitive with (and sometimes better than) the greedy algorithm that uses the true Tucker decomposition loss at each step, while also running up to 1000x faster.

To conduct regulatory monitoring within Consumer and High Net Worth on a specific set of regulatory requirements (e.g., PEPS, Sanctions, EDD, FIC Amendment Bill, CTR, Waterfall (KYC), AML Training, Quality Assurance, etc.) as prescribed by the Regulatory Monitoring framework and drives first level of defence remediation of breaches. To provide insights on the state of regulatory adherence within allocated portfolio and prepare appropriate reports as input into overall regulatory reporting.

OUTsurance is a customer-centric financial services company with a global foot print. We are vibrant, successful and values orientated with an awesome dynamic culture encapsulated by the ethos that clients and staff "always get something OUT." Our success can be attributed, amongst other things, to the outstanding people that work for us. An ideal candidate will be able to align their personal work values to the OUTsurance values of Awesome Service, Passionate, Honest, Human, Dynamic and Recognition. In accordance with OUTsurance Insurance Company Ltd Employment Equity goals, preference will be given to individuals who meet the job requirements and are from the various designated groups.

What are the problems that Tradeteq solves for its clients? Tradeteq is a smart technology platform powering global trade investments from end-to-end. Trade finance is arguably the oldest banking product, although also the only one that is not easily accessible for institutional investors. We have the technology to make trade finance investable. For those unfamiliar with trade finance, it may not be immediately obvious why institutional investors should consider putting funds into this asset class, nor indeed why those lending to companies trading goods globally do not simply retain the instruments on their books.

The graph represents a network of 1,514 Twitter users whose recent tweets contained "datascientist", or who were replied to, mentioned, retweeted or quoted in those tweets, taken from a data set limited to a maximum of 5,000 tweets, tweeted between 3/26/2006 12:00:00 AM and 2/5/2023 5:00:35 PM. The network was obtained from Twitter on Monday, 06 February 2023 at 20:48 UTC. The tweets in the network were tweeted over the 822-day, 16-hour, 33-minute period from Thursday, 05 November 2020 at 08:27 UTC to Monday, 06 February 2023 at 01:00 UTC. There is an edge for each "replies-to" relationship in a tweet, an edge for each "mentions" relationship in a tweet, an edge for each "retweet" relationship in a tweet, an edge for each "quote" relationship in a tweet, an edge for each "mention in retweet" relationship in a tweet, an edge for each "mention in reply-to" relationship in a tweet, an edge for each "mention in quote" relationship in a tweet, an edge for each "mention in quote reply-to" relationship in a tweet, and a self-loop edge for each tweet that is not from above. The graph's vertices were grouped by cluster using the Clauset-Newman-Moore cluster algorithm.

Kenya has been ranked fifth in Africa on the government's readiness to implement Artificial Intelligence. Kenya has been ranked fifth in Africa on the government's readiness to implement Artificial Intelligence (AI) in the delivery of services to the public, a new global survey shows. The 2022 edition of the annual Government AI Readiness Index released by Oxford Insights shows Kenya's overall score of 40.36 percent placing it behind Egypt, South Africa, Tunisia and Morocco. Globally, Kenya was ranked position 90 as countries prepare the ground for disruption expected from the new technology. On the technology sector pillar that examines the availability of requisite skills to enable AI adoption, the country posted a dismal score of 28.76 percent which is below the world average of 35.17 percent.

WNS (Holdings) Limited (NYSE: WNS), is a leading Business Process Management (BPM) company. We combine our deep industry knowledge with technology and analytics expertise to co-create innovative, digital-led transformational solutions with clients across 10 industries. We enable businesses in Travel, Insurance, Banking and Financial Services, Manufacturing, Retail and Consumer Packaged Goods, Shipping and Logistics, Healthcare, and Utilities to re-imagine their digital future and transform their outcomes with operational excellence. We deliver an entire spectrum of BPM services in finance and accounting, procurement, customer interaction services and human resources leveraging collaborative models that are tailored to address the unique business challenges of each client. We co-create and execute the future vision of 400 clients with the help of our 44,000 employees.