Last month, the Chinese ecommerce giant Alibaba revealed a powerful new cloud computing system designed for artificial intelligence projects. It is used by Alibaba's cloud customers to train algorithms for tasks like chatbot dialogue and video analysis, and was built using hundreds of chips from US companies Intel and Nvidia. Last week, the US announced new export restrictions that will make future projects like that unlikely. The Biden administration's rules forbid companies from exporting advanced chips needed to train or run the most powerful AI algorithms to China. The sweeping new controls are designed to keep the country's AI industry stuck in the dark ages while the US and other Western countries advance.

Ai-Da the robot has admitted she was'nervous' about speaking at the House of Lords and named her favourite artist as Yoko Ono in an exclusive interview with MailOnline. Ai-Da made history on Tuesday by becoming the first robot to address the House of Lords – although she suffered a slight hiccup after'falling asleep' mid-speech. During the session, the bot had to be rebooted by her creator Aidan Meller, after a technical issue rendered her cross-eyed and zombie-like. Shortly after, MailOnline asked Ai-Da a couple of questions about the address. Wearing dungarees and an orange blouse, Ai-Da said the address to the House of Lords went well and that she feels'quite nervous when speaking in public' Ai-Da is an artificial intelligence robot built in 2019 that creates drawings, paintings and sculptures.

STR's Analytics division researches and develops advanced analytics and machine learning-based solutions to solve challenging problems related to national security. Our team consists of passionate and motivated engineers with advanced degrees in engineering, computer science, mathematics, and data science, who are seeking opportunities to use their deep technical knowledge and creativity to tackle some of the hardest problems that our customers face. Our projects span multiple different data modalities and incorporate advanced algorithms, deep learning, and statistical techniques to uncover patterns in social media, structured and unstructured text, time series, geospatial, and imagery data, and must operate under challenging constraints not typically found in the commercial world. The tools and technologies we develop have real world impact and US Government analysts use them to extract and enrich intelligence information around the globe. As a Data Scientist, you will analyze a diverse collection of interesting and challenging datasets to develop, implement, and evaluate statistical machine learning algorithms to discover interesting trends and form valuable intelligence insights.

Well, from a technical point of view, we leverage the power of a global crowd to provide some of the world's biggest companies with the high-quality data they need to power their artificial intelligence. We're instrumental to the progression and development of artificial intelligence and we couldn't be prouder or more inspired to be involved in an industry that is changing the world. We bond over our shared love of software engineering, data science, and strong coffee. We like online gaming, running marathons, and team drinks. We celebrate authenticity and diversity and we're invested in what we do.

The Bank of England has again intervened to ensure there isn't a fire sale of UK government bonds by pension funds. The Institute for Fiscal Studies has published a report saying the government will have to find £60bn of spending cuts over four years to pay for the recent mini-budget. The International Monetary Fund has restated its criticism of said mini-budget indicating that the unfunded cuts will ramp up inflation. With all this going on, you might have thought that Kwasi Kwarteng and his Treasury gang might have been feeling a bit chastened. After all, it's not every chancellor who gets to screw up their first budget on such a grand scale.

Scientists have long been developing machines that attempt to imitate the human brain. Just as humans are exposed to systemic injustices, machines learn human-like stereotypes and cultural norms from sociocultural data, acquiring biases and associations in the process. Our research shows that bias is not only reflected in the patterns of language, but also in the image datasets used to train computer vision models. As a result, widely used computer vision models such as iGPT and DALL-E 2 generate new explicit and implicit characterizations and stereotypes that perpetuate existing biases about social groups, which further shape human cognition. Such computer vision models are used in downstream applications for security, surveillance, job candidate assessment, border control, and information retrieval.

At RE•WORK, we are strong advocates for supporting women working towards advancing technology, so ahead of the upcoming Toronto AI Summit, on November 9-10, we set out to highlight inspirational women who are working at the forefront of AI developments, and who deserve recognition for their achievements. While we set out to create a list of just 20 – we couldn't narrow it down, as there are so many inspiring and prominent females in this space! Hear from many of them at our Toronto AI Summit, and more at our Women in AI Reception, both being held in Toronto next month. Help us to continue highlighting leading women in AI by nominating your influential woman for our next edition. RE•WORK holds Women in AI events, podcasts, and blogs. Get in touch if you'd like to collaborate or support our initiatives! Doina Precup is a researcher living in Montreal, Canada.

Automatic International Classification of Diseases (ICD) coding aims to assign multiple ICD codes to a medical note with average length of 3,000+ tokens. This task is challenging due to a high-dimensional space of multi-label assignment (tens of thousands of ICD codes) and the long-tail challenge: only a few codes (common diseases) are frequently assigned while most codes (rare diseases) are infrequently assigned. This study addresses the long-tail challenge by adapting a prompt-based fine-tuning technique with label semantics, which has been shown to be effective under few-shot setting. To further enhance the performance in medical domain, we propose a knowledge-enhanced longformer by injecting three domain-specific knowledge: hierarchy, synonym, and abbreviation with additional pretraining using contrastive learning. Experiments on MIMIC-III-full, a benchmark dataset of code assignment, show that our proposed method outperforms previous state-of-the-art method in 14.5% in marco F1 (from 10.3 to 11.8, P<0.001). To further test our model on few-shot setting, we created a new rare diseases coding dataset, MIMIC-III-rare50, on which our model improves marco F1 from 17.1 to 30.4 and micro F1 from 17.2 to 32.6 compared to previous method.

Deep neural networks (DNNs) have been shown to be vulnerable to adversarial examples, which can produce erroneous predictions by injecting imperceptible perturbations. In this work, we study the transferability of adversarial examples, which is significant due to its threat to real-world applications where model architecture or parameters are usually unknown. Many existing works reveal that the adversarial examples are likely to overfit the surrogate model that they are generated from, limiting its transfer attack performance against different target models. To mitigate the overfitting of the surrogate model, we propose a novel attack method, dubbed reverse adversarial perturbation (RAP). Specifically, instead of minimizing the loss of a single adversarial point, we advocate seeking adversarial example located at a region with unified low loss value, by injecting the worst-case perturbation (the reverse adversarial perturbation) for each step of the optimization procedure. The adversarial attack with RAP is formulated as a min-max bi-level optimization problem. By integrating RAP into the iterative process for attacks, our method can find more stable adversarial examples which are less sensitive to the changes of decision boundary, mitigating the overfitting of the surrogate model. Comprehensive experimental comparisons demonstrate that RAP can significantly boost adversarial transferability. Furthermore, RAP can be naturally combined with many existing black-box attack techniques, to further boost the transferability. When attacking a real-world image recognition system, Google Cloud Vision API, we obtain 22% performance improvement of targeted attacks over the compared method. Our codes are available at https://github.com/SCLBD/Transfer_attack_RAP.

Given a convex function $f\colon\mathbb{R}^{d}\to\mathbb{R}$, the problem of sampling from a distribution $\propto e^{-f(x)}$ is called log-concave sampling. This task has wide applications in machine learning, physics, statistics, etc. In this work, we develop quantum algorithms for sampling log-concave distributions and for estimating their normalizing constants $\int_{\mathbb{R}^d}e^{-f(x)}\mathrm{d} x$. First, we use underdamped Langevin diffusion to develop quantum algorithms that match the query complexity (in terms of the condition number $\kappa$ and dimension $d$) of analogous classical algorithms that use gradient (first-order) queries, even though the quantum algorithms use only evaluation (zeroth-order) queries. For estimating normalizing constants, these algorithms also achieve quadratic speedup in the multiplicative error $\epsilon$. Second, we develop quantum Metropolis-adjusted Langevin algorithms with query complexity $\widetilde{O}(\kappa^{1/2}d)$ and $\widetilde{O}(\kappa^{1/2}d^{3/2}/\epsilon)$ for log-concave sampling and normalizing constant estimation, respectively, achieving polynomial speedups in $\kappa,d,\epsilon$ over the best known classical algorithms by exploiting quantum analogs of the Monte Carlo method and quantum walks. We also prove a $1/\epsilon^{1-o(1)}$ quantum lower bound for estimating normalizing constants, implying near-optimality of our quantum algorithms in $\epsilon$.