Classification algorithms aim to predict an unknown label (e.g., a quality class) for a new instance (e.g., a product). Therefore, training samples (instances and labels) are used to deduct classification hypotheses. Often, it is relatively easy to capture instances but the acquisition of the corresponding labels remain difficult or expensive. Active learning algorithms select the most beneficial instances to be labeled to reduce cost. In research, this labeling procedure is simulated and therefore a ground truth is available. But during deployment, active learning is a one-shot problem and an evaluation set is not available. Hence, it is not possible to reliably estimate the performance of the classification system during learning and it is difficult to decide when the system fulfills the quality requirements (stopping criteria). In this article, we formalize the task and review existing strategies to assess the performance of an actively trained classifier during training. Furthermore, we identified three major challenges: 1)~to derive a performance distribution, 2)~to preserve representativeness of the labeled subset, and 3) to correct against sampling bias induced by an intelligent selection strategy. In a qualitative analysis, we evaluate different existing approaches and show that none of them reliably estimates active learning performance stating a major challenge for future research for such systems. All plots and experiments are provided in a Jupyter notebook that is available for download.

As artificial intelligence becomes both more useful and more widespread, workers everywhere are becoming anxious about how a new age of automation might affect their career prospects. A recent study by Pew Research found that in 10 advanced and emerging economies, most workers expect computers will do much of the work currently done by humans within 50 years. Workers are clearly anxious about the effects on the job market of artificial intelligence and automation. Estimates about how much of the workforce could be automated vary from about 9% to 47%. The consultancy McKinsey estimates up to 800 million workers globally could be displaced by robotic automation by 2030.

As a high school student in a Detroit suburb in the 1990s, Russ Tedrake did not fit the standard profile of a future computer science professor. Although he had a talent for math -- "I won some of the little math competitions," he says -- he spent his spare time playing football or soccer with friends rather than hacking code or even playing video games; in fact, he didn't get his first computer until he was a senior. He got good grades, but he didn't find the work very demanding. The only calculus class offered at his school was geared to the easier of the two Advanced Placement tests offered by the College Board -- although, against the advice of his teachers, Tedrake took the harder test anyway and did well on it. "I just sort of coasted through," he says.

Is voice technology going to become the next big opportunity for brands to engage with consumers? As we enter an era where voice assistants are becoming more popular (Amazon Alexa, Google Home, Apple HomePod, among others), new doors open for marketing and communications professionals. Experts say voice assistants can become the first interactive tool at home that provides brands the capability to dynamically offer up ads in the future that could be user controlled. In this interactive Master Class, we will understand voice technology as part of artificial intelligence, discuss real business examples, and conclude with a discussion on the future of this technology and the marketing field as we know it.

It's a common psychological phenomenon: repeat any word enough times, and it eventually loses all meaning, disintegrating like soggy tissue into phonetic nothingness. For many of us, the phrase "artificial intelligence" fell apart in this way a long time ago. AI is everywhere in tech right now, said to be powering everything from your TV to your toothbrush, but never have the words themselves meant less. It shouldn't be this way. While the phrase "artificial intelligence" is unquestionably, undoubtedly misused, the technology is doing more than ever -- for both good and bad.

The demand for data science and machine learning jobs is rapidly rising and the gap between this demand and the number of data scientists available is still very wide. Now, people from an engineering background and pure sciences are shifting their careers in the field of ML. Physics is one such background which falls into this category because of the high level of logic and mathematics required in an ML job. Physics research requires dealing with a lot of data, just like ML. Physicists are also proficient in at least one programming language -- most likely Python, as it is popular in the Physics community as well. There are many physicists today who are data scientists.

Microsoft's quest to build computing systems that understand the world around them doesn't end with the company's Project Oxford machine-learning technology. Researchers at the Redmond, Wash., software maker are also developing systems that mimic how humans pull information from the things they see. "When a person is asked about something in a photo, they're taking in a lot of details--a lot of words--to answer questions about it," blogged Microsoft spokesperson Athima Chansanchai. "Now, a team of Microsoft researchers, together with colleagues from Carnegie Mellon University, has created a system that uses computer vision, deep learning and language understanding to analyze images and answer questions the same way humans would." Together, the researchers created a model that "applies multi-step reasoning to answer questions about pictures," said Chansanchai.

Before they got down to business for the day, students in Devin Tatro's social studies class were offered a quiet moment of self-reflection: On this golden fall afternoon at Nome-Beltz Junior/Senior High School, were they feeling chipper, distressed, or somewhere in between? One by one, they selected the picture of the facial expression that best matched their mood, and with a swift click sent an answer to the teacher. She scanned the responses and made a few mental notes. Then, without missing a beat, she switched the smartboard display and launched into a multiple-choice quiz using a game-based online learning platform called Kahoot! "Tell me one thing you remember about yesterday's lesson on expansions and tax on Native Americans," Tatro said, pacing the front of the classroom. She rattled off students' responses as they popped up on the smartboard in a colorful word cloud: "Forced relocation, reduced population, disease, warfare, cultural destruction ... wow, that's a powerful term."

When you start work as a data scientist you begin to realize that there is a huge gap between the models you've learned to the real life applications. You acknowledge then, that what makes someone professional is the ability to deliver data science application in a short time frame. And this is what this course is all about. How to create, quickly, applications which based on predictive modeling. The materials in this course are not things I read in books, but lessons learned in the hard way, after many years of building predictive applications.

Deep learning (DL) is a data science term that has become a hot buzzword in tech, business and marketing. Along with artificial intelligence (AI) and machine learning (ML), deep learning is a technology that is now coming into its own, and together, all three are poised to begin ushering in massive changes to practically every industry on the planet. Sounds like a pretty big deal, right? It is – so let's try and get our heads around what deep learning is, does, and aims to achieve. To do so, we need to understand the differences between AI, ML and DL.