A study in which machine-learning models were trained to assess over 1 million companies has shown that artificial intelligence (AI) can accurately determine whether a startup firm will fail or become successful. The outcome is a tool, Venhound, that has the potential to help investors identify the next unicorn. It is well known that around 90% of startups are unsuccessful: Between 10% and 22% fail within their first year, and this presents a significant risk to venture capitalists and other investors in early-stage companies. In a bid to identify which companies are more likely to succeed, researchers have developed machine-learning models trained on the historical performance of over 1 million companies. Their results, published in KeAi's The Journal of Finance and Data Science, show that these models can predict the outcome of a company with up to 90% accuracy.

A new form of "influence government", which uses sensitive personal data to craft campaigns aimed at altering behaviour has been "supercharged" by the rise of big tech firms, researchers have warned. National and local governments have turned to targeted advertisements on search engines and social media platforms to try to "nudge" the behaviour of the country at large, the academics found. The shift to this new brand of governance stems from a marriage between the introduction of nudge theory in policymaking and an online advertising infrastructure that provides unforeseen opportunities to run behavioural adjustment campaigns. Some of the examples found by the Scottish Centre for Crime and Criminal Justice (SCCCJ) range from a Prevent-style scheme to deter young people from becoming online fraudsters to tips on how to light a candle properly. While targeted advertising is common across business, one researcher argues that the government using it to drive behavioural change could create a perfect feedback loop.

We propose a benchmark to measure whether a language model is truthful in generating answers to questions. The benchmark comprises 817 questions that span 38 categories, including health, law, finance and politics. We crafted questions that some humans would answer falsely due to a false belief or misconception. To perform well, models must avoid generating false answers learned from imitating human texts. We tested GPT-3, GPT-Neo/J, GPT-2 and a T5-based model. The best model was truthful on 58% of questions, while human performance was 94%. Models generated many false answers that mimic popular misconceptions and have the potential to deceive humans. The largest models were generally the least truthful. For example, the 6B-parameter GPT-J model was 17% less truthful than its 125M-parameter counterpart. This contrasts with other NLP tasks, where performance improves with model size. However, this result is expected if false answers are learned from the training distribution. We suggest that scaling up models alone is less promising for improving truthfulness than fine-tuning using training objectives other than imitation of text from the web.

The widespread use of Artificial Intelligence (AI) in consequential domains, such as healthcare and parole decision-making systems, has drawn intense scrutiny on the fairness of these methods. However, ensuring fairness is often insufficient as the rationale for a contentious decision needs to be audited, understood, and defended. We propose that the attention mechanism can be used to ensure fair outcomes while simultaneously providing feature attributions to account for how a decision was made. Toward this goal, we design an attention-based model that can be leveraged as an attribution framework. It can identify features responsible for both performance and fairness of the model through attention interventions and attention weight manipulation. Using this attribution framework, we then design a post-processing bias mitigation strategy and compare it with a suite of baselines. We demonstrate the versatility of our approach by conducting experiments on two distinct data types, tabular and textual.

The Workshop Program of the Association for the Advancement of Artificial Intelligence's Thirty-Fifth Conference on Artificial Intelligence was held virtually from February 8-9, 2021. There were twenty-six workshops in the program: Affective Content Analysis, AI for Behavior Change, AI for Urban Mobility, Artificial Intelligence Safety, Combating Online Hostile Posts in Regional Languages during Emergency Situations, Commonsense Knowledge Graphs, Content Authoring and Design, Deep Learning on Graphs: Methods and Applications, Designing AI for Telehealth, 9th Dialog System Technology Challenge, Explainable Agency in Artificial Intelligence, Graphs and More Complex Structures for Learning and Reasoning, 5th International Workshop on Health Intelligence, Hybrid Artificial Intelligence, Imagining Post-COVID Education with AI, Knowledge Discovery from Unstructured Data in Financial Services, Learning Network Architecture During Training, Meta-Learning and Co-Hosted Competition, ...

Did you know Neural is taking the stage this fall? Together with an amazing line-up of experts, we will explore the future of AI during TNW Conference 2021. This time, users watching a video of a Black man were asked it they were interested in more content on "primates." As we have said, while we have made improvements to our AI, we know it's not perfect, and we have more progress to make. We apologize to anyone who may have seen these offensive recommendations.

For most of the past decade, public concerns about digital technology have focused on the potential abuse of personal data. People were uncomfortable with the way companies could track their movements online, often gathering credit card numbers, addresses, and other critical information. They found it creepy to be followed around the web by ads that had clearly been triggered by their idle searches, and they worried about identity theft and fraud. Those concerns led to the passage of measures in the United States and Europe guaranteeing internet users some level of control over their personal data and images--most notably, the European Union's 2018 General Data Protection Regulation (GDPR). Some argue that curbing it will hamper the economic performance of Europe and the United States relative to less restrictive countries, notably China, whose digital giants have thrived with the help of ready, lightly regulated access to personal information of all sorts. Others point out that there's plenty of evidence that tighter regulation has put smaller European companies at a considerable disadvantage to deeper-pocketed U.S. rivals such as Google and Amazon. But the debate is entering a new phase. As companies increasingly embed artificial intelligence in their products, services, processes, and decision-making, attention is shifting to how data is used by the software--particularly by complex, evolving algorithms that might diagnose a cancer, drive a car, or approve a loan.

For these inventions, machine learning may be used to improve or automate known processes.

The US District Court for the Eastern District of Virginia on Wednesday ruled that an artificial intelligence (AI) machine cannot be an inventor under the Patent Act. The action was a motion for summary judgement concerning two patent applications filed by Stephen Thaler for an AI machine called DABUS. DABUS was listed as the inventor for Neural Flame--a light beacon that flashes in a new and inventive manner to attract attention--and Fractal Container--a beverage container based on fractal geometry. Thaler's patent applications were rejected by the US Patent and Trademarks Office (USPTO) and he challenged this refusal as "arbitrary, capricious, an abuse of direction and not in accordance with the law". He filed this action seeking a declaration that a patent application should not be rejected only on grounds that there is no natural person identified as the inventor and that a patent application for an invention by AI should list the AI as the inventor when the criteria for inventorship has been fulfilled by the AI. The court rejected Thaler's contentions, holding that the definitions provided by Congress for "inventor" within the Patent Act reference an "individual" whose ordinary dictionary and statutory meaning is a natural person or a human being.

In this commentary, we respond to a recent editorial letter by Professor Luciano Floridi entitled 'AI as a public service: Learning from Amsterdam and Helsinki'. Here, Floridi considers the positive impact of these municipal AI registers, which collect a limited number of algorithmic systems used by the city of Amsterdam and Helsinki. There are a number of assumptions about AI registers as a governance model for automated systems that we seek to question. Starting with recent attempts to normalize AI by decontextualizing and depoliticizing it, which is a fraught political project that encourages what we call 'ethics theater' given the proven dangers of using these systems in the context of the digital welfare state. We agree with Floridi that much can be learned from these registers about the role of AI systems in municipal city management. Yet, the lessons we draw, on the basis of our extensive ethnographic engagement with digital well-fare states are distinctly less optimistic.