ClearScore is searching for Data Scientist. This is an amazing opportunity to engage with a rich data set on 15 million users. We have captured every interaction the users have had with our high touch website and native apps, their fully monthly credit files and growing access to insurance, bank account and mobile data as well. Ordinarily a data set this vast would be buried in legacy systems, however ClearScore is only 6 years old and operates a strict'zero legacy' approach that means the data is held in an autoscaling AWS redshift environment. This is an exciting opportunity to work within a fast-paced, rapidly growing team of talented data scientists, helping to build revolutionary experiences that will help millions of users manage and better understand their finances.

In March, a largely overlooked, 90-page Government Accountability Office study revealed something interesting: This summer, the Pentagon is getting a new AI Strategy. Between shaping ethical norms for AI and establishing a new Chief Data and AI Officer, it's clear top brass have big plans for the technology, though the report is light on the details. Released in 2018, the last AI Strategy laid the scaffolding for the U.S. military's high-tech competition with China. But over the past four years one thing has become apparent: The United States needs a balanced approach to AI investment -- one that doesn't simply guard against threats, but also imposes costs on a Chinese force that sees AI as the key to victory. Undoubtedly, a military conflict between the United States and China would be catastrophic, and every effort must be taken to avoid such an outcome through diplomatic means.

Large-scale pre-trained language models have contributed significantly to natural language processing by demonstrating remarkable abilities as few-shot learners. However, their effectiveness depends mainly on scaling the model parameters and prompt design, hindering their implementation in most real-world applications. This study proposes a novel pluggable, extensible, and efficient approach named DifferentiAble pRompT (DART), which can convert small language models into better few-shot learners without any prompt engineering. The main principle behind this approach involves reformulating potential natural language processing tasks into the task of a pre-trained language model and differentially optimizing the prompt template as well as the target label with backpropagation. Furthermore, the proposed approach can be: (i) Plugged to any pre-trained language models; (ii) Extended to widespread classification tasks. A comprehensive evaluation of standard NLP tasks demonstrates that the proposed approach achieves a better few-shot performance. Code is available in https://github.com/zjunlp/DART.

Just when you thought modern life couldn't get any crazier, a video emerged during the run-up to the recent UK election, in which the Prime Minister Boris Johnson appeared to endorse his political opponent Jeremy Corbyn. "Appeared" is the important word here, because this was actually just one of the latest in a steady stream of deepfakes – video and audio clips in which artificial intelligence simulates real people doing unreal things. Of course, humans have been faking it for centuries. From tattoos and piercings to face paints and wigs, we love altering ourselves and indulging in a bit of make-believe. My own little secret for years was that I wore green-coloured contact lenses. I did need them for short-sightedness – the colour was purely a personal choice.

In the elegant quiet of the café at the Church of Sweden, a narrow Gothic-style building in Midtown Manhattan, Daniel Cohen is taking a break from explaining genetics. He moves toward the creaky piano positioned near the front door, sits down, and plays a flowing, flawless rendition of "Over the Rainbow." If human biology is the scientific equivalent of a complicated score, Cohen has learned how to navigate it like a virtuoso. Cohen was the driving force behind Généthon, the French laboratory that in December 1993 produced the first-ever "map" of the human genome. He essentially introduced Big Data and automation to the study of genomics, as he and his team demonstrated for the first time that it was possible to use super-fast computing to speed up the processing of DNA samples.

Covid-19 can cause lasting cognitive and mental health issues, including brain fog, fatigue and even post-traumatic stress disorder. To better understand the scale of the problem, researchers at the University of Cambridge analysed 46 people who were hospitalised due to the infection between March and July 2020. The participants underwent cognitive tests on average six months after their initial illness. These results were compared against those of more than 66,000 people from the general population. Those hospitalised with covid-19 scored worse on verbal analogical reasoning tests, which assess an individual's ability to recognise relationships between ideas and think methodically. They also recorded slower processing speeds. Previous studies suggest glucose is less efficiently used by the part of the brain responsible for attention, complex problem-solving and working memory after covid-19. Scores and reaction speeds improved over time, however, any recovery was gradual at best, according to the researchers. This cognitive impairment probably has multiple causes, including inadequate blood supply to the brain, blood vessel blockage and microscopic bleeds caused by SARS-CoV-2 virus, as well as damage triggered by an overactive immune system, they added. "Around 40,000 people have been through intensive care with covid-19 in England alone and many more will have been very sick, but not admitted to hospital," Adam Hampshire at Imperial College London said in a statement. "This means there is a large number of people out there still experiencing problems with cognition many months later." The biological mechanism behind a rare and severe covid-19 response seen in some children may have been uncovered by researchers at the Murdoch Children's Research Institute in Melbourne, Australia. Doctors have so far been unable to identify why some children develop multisystem inflammatory syndrome (MIS) in response to covid-19, which can cause symptoms such as fever, abdominal pain and heart disease.

LONDON, May 3 (Reuters) - Over the last two years a series of unexpected events has scrambled global supply chains. Coronavirus, war in Ukraine, Brexit and a container ship wedged in the Suez Canal have combined to delay deliveries of everything from bicycles to pet food. In response, a growing group of startups and established logistics firms has created a multi-billion dollar industry applying the latest technology to help businesses minimize the disruption. Interos Inc, Fero Labs, KlearNow Corp and others are using artificial intelligence and other cutting-edge tools so manufacturers and their customers can react more swiftly to supplier snarl-ups, monitor raw material availability and get through the bureaucratic thicket of cross-border trade. The market for new technology services focused on supply chains could be worth more than $20 billion a year in the next five years, analysts told Reuters.

LONDON – Over the last two years a series of unexpected events has scrambled global supply chains. Coronavirus, war in Ukraine, Brexit and a container ship wedged in the Suez Canal have combined to delay deliveries of everything from bicycles to pet food. In response, a growing group of startups and established logistics firms has created a multibillion dollar industry applying the latest technology to help businesses minimize the disruption. Interos Inc., Fero Labs, KlearNow Corp. and others are using artificial intelligence and other cutting-edge tools so manufacturers and their customers can react more swiftly to supplier snarl-ups, monitor raw material availability and get through the bureaucratic thicket of cross-border trade. The market for new technology services focused on supply chains could be worth more than $20 billion a year in the next five years, analysts told Reuters.

The above scenario may not be the stuff of sci-fi blockbusters, but in its own waypoints to an exciting shift in the relationship between citizens and governments. To some degree, we are already seeing this transformation taking shape--government agencies using machines to crunch data, say, or to improve citizen outreach programs. In our daily lives, meanwhile, AI makes countless decisions on our behalf-- though these are rarely more urgent than what to watch on Netflix tonight. The idea that a smart network might, without prompting, take decisive action in order to save human lives, however, is potentially a very big deal. This might be a way off, but the prospect of AI-enhanced government has led to what one observer describes as "a global race among nations," with several Gulf countries--particularly Saudi Arabia and the UAE-- very much in the running.

We study the first gradient descent step on the first-layer parameters $\boldsymbol{W}$ in a two-layer neural network: $f(\boldsymbol{x}) = \frac{1}{\sqrt{N}}\boldsymbol{a}^\top\sigma(\boldsymbol{W}^\top\boldsymbol{x})$, where $\boldsymbol{W}\in\mathbb{R}^{d\times N}, \boldsymbol{a}\in\mathbb{R}^{N}$ are randomly initialized, and the training objective is the empirical MSE loss: $\frac{1}{n}\sum_{i=1}^n (f(\boldsymbol{x}_i)-y_i)^2$. In the proportional asymptotic limit where $n,d,N\to\infty$ at the same rate, and an idealized student-teacher setting, we show that the first gradient update contains a rank-1 "spike", which results in an alignment between the first-layer weights and the linear component of the teacher model $f^*$. To characterize the impact of this alignment, we compute the prediction risk of ridge regression on the conjugate kernel after one gradient step on $\boldsymbol{W}$ with learning rate $\eta$, when $f^*$ is a single-index model. We consider two scalings of the first step learning rate $\eta$. For small $\eta$, we establish a Gaussian equivalence property for the trained feature map, and prove that the learned kernel improves upon the initial random features model, but cannot defeat the best linear model on the input. Whereas for sufficiently large $\eta$, we prove that for certain $f^*$, the same ridge estimator on trained features can go beyond this "linear regime" and outperform a wide range of random features and rotationally invariant kernels. Our results demonstrate that even one gradient step can lead to a considerable advantage over random features, and highlight the role of learning rate scaling in the initial phase of training.