Tesla sales fell in the US once again last month, following a wider global trend that further fuels the suggestion that the growing backlash against billionaire CEO Elon Musk could be impacting Tesla at retail. According to Kelley Blue Book, Tesla shifted 43,650 EVs in February, a decrease of nearly 6 percent from the 46,262 sold in the same month last year. It's far from the crash seen in much of the rest of the world, with drops of over 75 percent in Europe in the first two months of the year (the UK being one of the the only markets bucking the trend, with Tesla's February sales jumping by 20 percent compared with the same month last year), but--whatever the reason--sales are stalling. In the US, the month-over-month sales decline in February was primarily driven by significant drops in Cybertruck and Model 3 sales, which fell by 32.5 percent and 17.5 percent, respectively. But Stephanie Valdez Streaty, director of industry insights for Cox Automotive, says these drops aren't that bad when considered within the wider market.

An Australian mayor has threatened a defamation suit against OpenAI, alleging that its chatbot, ChatGPT, made some false claims about him, probably the first of its kind action in the generative AI space. Called "Segment Anything", this AI model can detect objects from photos and videos, and allows users to select those objects by clicking them or using text prompts. Italian regulators said last Friday that the firm had no legal basis to engage in massive data collection and questioned the way it was handling the information it had gathered.

The Goa traffic department along with the public works department (PWD) have begun rolling out an artificial intelligence (AI)-powered traffic signals which will significantly reduce wait times at various junctions in the state. This development comes months after Bengaluru had become the first city in the country to deploy AI powered traffic signals to help reduce snarls. The Goa government has teamed up with Beltech AI to deploy the technology across traffic signals in the state. Also Read: 'Bengaluru to get 75 new junctions for ₹150 crore': Bommai's bid to ease traffic woes Beltech AI is the same traffic management platform that had successfully demonstrated to have reduced the traffic congestion in Bengaluru by over 42%. The tech will be launched by Goa chief minister Pramod Sawant on Wednesday.

We introduce and evaluate an eXplainable Goal Recognition (XGR) model that uses the Weight of Evidence (WoE) framework to explain goal recognition problems. Our model provides human-centered explanations that answer why? and why not? questions. We computationally evaluate the performance of our system over eight different domains. Using a human behavioral study to obtain the ground truth from human annotators, we further show that the XGR model can successfully generate human-like explanations. We then report on a study with 60 participants who observe agents playing Sokoban game and then receive explanations of the goal recognition output. We investigate participants' understanding obtained by explanations through task prediction, explanation satisfaction, and trust.

In this paper, we take a human-centered approach to interpretable machine learning. First, drawing inspiration from the study of explanation in philosophy, cognitive science, and the social sciences, we propose a list of design principles for machine-generated explanations that are meaningful to humans. Using the concept of weight of evidence from information theory, we develop a method for producing explanations that adhere to these principles. We show that this method can be adapted to handle high-dimensional, multi-class settings, yielding a flexible meta-algorithm for generating explanations. We demonstrate that these explanations can be estimated accurately from finite samples and are robust to small perturbations of the inputs. We also evaluate our method through a qualitative user study with machine learning practitioners, where we observe that the resulting explanations are usable despite some participants struggling with background concepts like prior class probabilities. Finally, we conclude by surfacing design implications for interpretability tools

One-hot encoding, otherwise known as dummy variables, is a method of converting categorical variables into several binary columns, where a 1 indicates the presence of that row belonging to that category. It is, pretty obviously, not a great a choice for the encoding of categorical variables from a machine learning perspective. Most apparent is the heavy amount of dimensionality it adds, and it is common knowledge that generally a lower amount of dimensions is better. For example, if we were to have a column representing a US state (e.g. California, New York), a one-hot encoding scheme would result in fifty additional dimensions.

Interpretability is an elusive but highly sought-after characteristic of modern machine learning methods. Recent work has focused on interpretability via $\textit{explanations}$, which justify individual model predictions. In this work, we take a step towards reconciling machine explanations with those that humans produce and prefer by taking inspiration from the study of explanation in philosophy, cognitive science, and the social sciences. We identify key aspects in which these human explanations differ from current machine explanations, distill them into a list of desiderata, and formalize them into a framework via the notion of $\textit{weight of evidence}$ from information theory. Finally, we instantiate this framework in two simple applications and show it produces intuitive and comprehensible explanations.

LONDON – Furhat tilts his or her head, smiles, exudes empathy and warmth, and encourages us to open up. The robot, a 3D bust with a projection of a humanlike face, aims to build on our newfound ease talking to voice assistants like Siri and Alexa, by persuading us to interact with it as if it were a person, picking up on our cues to strike up a rapport. Yet precisely because it isn't human, and is therefore free from bias, the robot can spur people to engage more honestly, its creator says, making it useful in situations such as screening for health risks where people often lie. "We've seen research that shows that in certain situations people are more comfortable opening up and talking about difficult issues with a robot than with a human," said Samer Al Moubayed, chief executive of Furhat Robotics. That's because a robot's personality can mirror the personality of the person interacting with it and because people don't feel judged, he added.

Science and technology firm Merck and Furhat Robotics on Wednesday unveiled a robot in Stockholm which will ask people about their health and lifestyle and screen them for risk of diabetes, alcoholism and hypothyroidism. If necessary, the robot will advise them to go for a blood test or to a doctor.

With all the hype around artificial intelligence, many of our customers are asking for some proof that AI can get them better results in areas where other kinds of analytics are already in use, such as credit risk assessment. With 25 years of experience with AI and machine learning under our belt, we can certainly provide that proof. My colleague Scott Zoldi blogged recently about how we use AI to build credit risk models. In this post, I'd like to drill into one of the examples he gave, to show some of the explorations we're doing to make sure we get the full power of machine learning without losing the transparency that's important in the credit risk arena. A traditional credit risk scorecard model generates a score reflecting probability of default, using various customer characteristics as inputs to the model.