While precise data observation is essential for the learning processes of predictive models, it can be challenging owing to factors such as insufficient observation accuracy, high collection costs, and privacy constraints. In this paper, we examines cases where some qualitative features are unavailable as precise information indicating "what it is," but rather as complementary information indicating "what it is not." We refer to features defined by precise information as ordinary features (OFs) and those defined by complementary information as complementary features (CFs). We then formulate a new learning scenario termed Complementary Feature Learning (CFL), where predictive models are constructed using instances consisting of OFs and CFs. The simplest formalization of CFL applies conventional supervised learning directly using the observed values of CFs. However, this approach does not resolve the ambiguity associated with CFs, making learning challenging and complicating the interpretation of the predictive model's specific predictions. Therefore, we derive an objective function from an information-theoretic perspective to estimate the OF values corresponding to CFs and to predict output labels based on these estimations. Based on this objective function, we propose a theoretically guaranteed graph-based estimation method along with its practical approximation, for estimating OF values corresponding to CFs. The results of numerical experiments conducted with real-world data demonstrate that our proposed method effectively estimates OF values corresponding to CFs and predicts output labels.

In partial label learning, each training example is associated with a set of candidate labels, among which only one is valid. An intuitive strategy to learn from partial label examples is to treat all candidate labels equally and make prediction by averaging their modeling outputs. Nonetheless, this strategy may suffer from the problem that the modeling output from the valid label is overwhelmed by those from the false positive labels. In this paper, an instance-based approach named IPAL is proposed by directly disambiguating the candidate label set. Briefly, IPAL tries to identify the valid label of each partial label example via an iterative label propagation procedure, and then classifies the unseen instance based on minimum error reconstruction from its nearest neighbors. Extensive experiments show that IPAL compares favorably against the existing instance-based as well as other state-of-the-art partial label learning approaches.

Except for the sexism that continues to persist throughout the market, toys have evolved a lot in recent decades. Children are now having fun with new tech-heavy toys -- a trend that has only grown stronger with the digital revolution. Dolls, fire trucks, electric trains, and many other toys are not just "lifeless" miniature replicas of their real-life inspirations like they used to be. For one thing, electronic chips have become omnipresent in toys, adding more and more features, functions, and interactivity to them. But this was only the start of the toy tech revolution.

It speaks two languages, gives math lessons, tells jokes and interacts with children through the tablet screen in its chest--China's latest robot is the babysitter every parent needs. The "iPal" was among a slew of new tech unveiled at the Consumer Electronics Show Asia in Shanghai this week, offering education and company for lonely children and peace of mind for adults. The humanoid device stands as tall as a five-year-old, moves and dances on wheels and its eyes keep track of its charges through facial recognition technology. Parents can also remotely talk to and monitor the children through the iPal, which is linked to a smartphone app that allows them to see and hear everything. "The idea for this robot is to be a companion for children," said Tingyu Huang, co-founder of AvatarMind Robot Technology.

Parents in China are handing over babysitting duties to robots. The £1,050 ($1,400) 'iPal' speaks two languages, gives maths lessons, tells jokes and interacts with children through a tablet screen in its chest. Engineers designed the device to act like a four to eight-year-old, becoming an extra child in the family that also helps'relieve the burden' felt by China's busy parents. The android offers education and company for lonely children and peace of mind for adults, who can remotely talk to and monitor their child through iPal's screen. A smartphone app directly links parents to the humanoid machine, allowing them to see and hear everything in iPal's vicinity.

Around a decade ago at the Indian Institute of Technology Bombay (IIT-B), classmates Sneh Rajkumar Vaswani, Chintan Subhash Raikar, and Prashant Iyengar were involved in a project to build intelligent underwater vehicles for the India Navy and the oil and gas industry. In the process, they developed a knack for artificial intelligence (AI) and robotics. That culminated in their setting up of emotix in 2015, and this startup has now developed Miko, India's first companion robot. Miko, weighing around 750 grams and standing a little over a foot, engages, educates, and entertains children above the age of five. Besides talking to and playing games with the kids, Miko is also equipped to answer basic questions related to general knowledge and academics.

This article is part of a series that explores how artificial intelligence could change life in China. Lü moved to Shanghai in 2014 from his hometown in central China's Henan province, one of the country's poorer provinces, to work at an app development company. A year later, his wife joined him, leaving their son back in Henan with his grandparents. Living some 800 kilometers away is not an ideal situation, says Lü, but it's a necessary compromise to give the whole family a better life. Because he's only able to visit his son around six times a year, Lü spends generously on whatever he thinks will help the boy's intellectual development -- from cheap toys and storybooks to a 1,200-yuan ($180) robot playmate named Ledi, who's powered by artificial intelligence (AI).

Social robots are making their entrance at the Consumer Electronics Show this year. AvatarMind today unveiled its iPal Companion Robot, which is designed as an educational and entertaining friend for children and elderly people. AvatarMind is showing off the robot in a booth at the Family and Technology Marketplace at the Sands Expo during CES 2017. The robot can sing, dance, navigate a maze, and interact with people. The iPal is intended to serve as a learning and safety companion for children.

The three-foot tall robot with "wide eyes, working fingers, pastel trimming, and a touchscreen tablet on its chest" showed off its babysitting skills at an annual robotics event in San Jose, California, the Guardian reported. The iPal is designed to act like a companion for children: the robot talks to them, answering general-knowledge questions like "Why is the sun hot?," and entertaining them with song, dance, and games, such as rock-paper-scissors. Jiping Wang, founder of Avatar Mind, which created the iPal, told the Guardian that the robot can keep children between the ages of 3 and 8 occupied for "a couple of hours" without adult supervision, touting it as a perfect solution to fill the time between when children return home from school and when parents get back from work. Madeline Duva, an adviser to Avatar Mind, clarified that "it cannot replace a babysitter." But, she said, in cases where you do need to occupy a child for a brief period while you, say, run to the store for some laundry detergent, the iPal is better than devices like the iPad, which are far less interactive than the robot.

Robots can do many things humans can do, often better. They mix cocktails, stand in for security guards and dispose of bombs. One thing we're sure they can never do better: care for our kids. They can't snuggle, kiss boo-boos or exhibit unconditional love, not like a mom or dad or child care worker can. But that didn't stop the makers of iPal from creating a creepy nanny robot that they're billing as a babysitter. It's a 3-foot-tall talking bot, complete with a surveillance cam, a touch screen tablet and tons of apps, you know, to keep your kid occupied and happy when you can't.