Fairness can be measured at group levels or at the individual level. Do you wish to ensure that on average you don't discriminate against a protected group or apply the protection to each and every individual? For example, you may hire female job applicants with the same average probability that you hire male applicants. That would achieve group fairness. However, you may be biased by giving junior roles with higher probability to females and senior jobs with higher probability to males. Achieving individual fairness is more difficult than achieving group fairness.

RALEIGH – One of the most perplexing challenges facing businesses wanting to explore Artificial Intelligence as a tool is "How do I build a team?" Rett Crocker CEO and CTO of UDU, an artificial intelligence firm in Raleigh, has plenty of advice. In an interview with Alexander Ferguson, CEO of YourLocalStudio, for its UpTech series focusing on AI, Crocker explains his reasoning in this excerpt of an interview published June 20. "First off, I wouldn't build anything from scratch anymore. There's just almost no point in that because of all of the existing tools that are out there, that are open source" Crocker says.

Artificial intelligence can now figure out recipes based on images of pizza. New York thin-crust topped with pesto chicken. What do you think makes for the perfect pizza? A recent study suggests neural networks could create the ultimate pie. The study out of MIT, which appeared earlier this month on Arxiv.org, Generative adversarial networks (GANs) use models to make decisions.

It's not hard to find a good story in the tech industry. The problem is that due to the industry's staggering gender gap, most of these stories center on the struggles and accomplishments of men. In this article, we aim to provide a platform for female technologists to share the stories of how they got into engineering, the biggest challenges they've faced, and their advice to the next generation of women in tech. You'll meet a former geologist turned product manager, an academic who fell in love with data science, a senior tech leader who discovered her dream job after the first two companies she worked for folded, and more. CCC's technology solutions are designed to increase connectedness among companies in the automotive industry, including insurance carriers, manufacturers, parts suppliers and collision repair shops. Ranjini Vaidyanathan was in academia and earned a PhD before realizing she had a passion for data science. While changing focuses wasn't always easy, Vaidyanathan said the transition was made easier by some simple, yet powerful, advice from her mentors. "When the going gets tough, what'll help you pull through is your passion for the technical work." How did you get into engineering? I studied applied science and mathematics before finally switching to data science after my PhD. It took me some time to decide what, exactly, I wanted to pursue. I had been doing pen-and-paper theory work as a student, but after a certain point, I realized I found applied problems more interesting. What's the biggest challenge you've faced in your career, and how have you worked to overcome it? Switching fields from academia to data science was challenging. I had to brush up industry-relevant skills like programming, and also adjust to the paradigm shift in thinking, both in terms of technical and soft skills.

Communitech, in partnership with the Schulich Foundation and Leaders Fund, revealed the problem statement for the Leaders Prize Competition Wednesday. This first-of-its-kind competition in Canada will award $1 million to the winning team using artificial intelligence (AI) to solve a global problem that is undermining our democracies: fake news and the spread of misinformation. Teams across Canada are invited to create solutions to automatically verify a series of claims, flag whether they are true, partly true, or false and provide evidence to support their determination. The prize will ultimately be awarded to the most effective and efficient AI based fact-checking solution. "This competition will inspire the creation of breakthrough solutions that inform our citizens if the online content they consume is accurate, before and as they read it," said David Stein, Co-Founder and Managing Partner, Leaders Fund.

The robot showed up at Kenneth Williams' doorstep when he needed it most. Williams had just been laid off from his job when he plugged in Jibo, a social home robot, on November 1st, 2017. "For that year [that I didn't have a job], it was a presence in my life every single day that I talked to," he says. Jibo sat in Williams' bedroom, on his desk, where every day, it greeted him in the morning and ran through the weather and his calendar. Williams, 44, asked Jibo questions, requested music, and played its games. Jibo couldn't do much, really, but its most redeeming feature, the one that cemented it as a robot darling in its owner's heart, was its facial recognition.

AI (Artificial Intelligence) is everywhere and it's here to stay. Along with these consumer applications, companies across sectors are increasingly harnessing AI's power for productivity growth and innovation. There are many who believe that AI has the potential to become more significant than even the internet. Availability of enormous amount of data combined with huge leap in computational power and huge improvements in engineering skills should help AI, backed with deep learning, to make huge impact across various facets of human life. Amid all the hype, genuine and inflated, around the world of AI, it is pertinent to ask an important question.

It shouldn't really be a surprise that artificial intelligence (AI) gets a special mention in the long-term plan for the NHS, published in March. AI is seen as important for the future of the NHS because it can make healthcare more effective and efficient, leaving staff free to focus on, as the plan puts it, the'complexity of human interactions that technology will never master'. With a growing population, limited resources yet more and more treatments available, the use of intelligent technology will be key to ensuring our healthcare services can keep pace. At Grow MedTech, we see AI as one of the most important digital technologies that will combine with traditional medtech to create the products and technologies of the future. And Yorkshire is a hotbed for the technology, with all of our partner universities offering expertise in the field.

There's a relatively simple formula which describes "weak" or "narrow" artificial intelligence: AI ML TD HITL. To be more specific, this is the definition of supervised machine learning, which is the most common method to produce artificial intelligence. Strong AI – as defined by the Turing test – is when a human has a conversation with a machine and cannot tell it was not a human, based on the way it responds to questions. The optimists believe that strong AI is 10-15 years away whilst the realists/pessimists say not before the end of this century. Over 90% of all human knowledge accumulated since the beginning of time, is unstructured data i.e. text, images, audio and video.

Large capacity machine learning models are prone to membership inference attacks in which an adversary aims to infer whether a particular data sample is a member of the target model's training dataset. Such membership inferences can lead to serious privacy violations as machine learning models are often trained using privacy-sensitive data such as medical records and controversial user opinions. Recently defenses against membership inference attacks are developed, in particular, based on differential privacy and adversarial regularization; unfortunately, such defenses highly impact the classification accuracy of the underlying machine learning models. In this work, we present a new defense against membership inference attacks that preserves the utility of the target machine learning models significantly better than prior defenses. Our defense, called distillation for membership privacy (DMP), leverages knowledge distillation, a model compression technique, to train machine learning models with membership privacy. We use different techniques in the DMP to maximize its membership privacy with minor degradation to utility. DMP works effectively against the attackers with either a whitebox or blackbox access to the target model. We evaluate DMP's performance through extensive experiments on different deep neural networks and using various benchmark datasets. We show that DMP provides a significantly better tradeoff between inference resilience and classification performance than state-of-the-art membership inference defenses. For instance, a DMP-trained DenseNet provides a classification accuracy of 65.3\% for a 54.4\% (54.7\%) blackbox (whitebox) membership inference attack accuracy, while an adversarially regularized DenseNet provides a classification accuracy of only 53.7\% for a (much worse) 68.7\% (69.5\%) blackbox (whitebox) membership inference attack accuracy.