As part of the 2016 public evaluation challenge on Detection and Classification of Acoustic Scenes and Events (DCASE 2016), the second task focused on evaluating sound event detection systems using synthetic mixtures of office sounds. This task, which follows the `Event Detection - Office Synthetic' task of DCASE 2013, studies the behaviour of tested algorithms when facing controlled levels of audio complexity with respect to background noise and polyphony/density, with the added benefit of a very accurate ground truth. This paper presents the task formulation, evaluation metrics, submitted systems, and provides a statistical analysis of the results achieved, with respect to various aspects of the evaluation dataset.

Although compelling assessments have been examined in recent years, more studies are required to yield a better understanding of the several methods where assessment techniques significantly affect student learning process. Most of the educational research in this area does not consider demographics data, differing methodologies, and notable sample size. To address these drawbacks, the objective of our study is to analyse student learning outcomes of multiple assessment formats for a web-facilitated in-class section with an asynchronous online class of a core data communications course in the Undergraduate IT program of the Information Sciences and Technology (IST) Department at George Mason University (GMU). In this study, students were evaluated based on course assessments such as home and lab assignments, skill-based assessments, and traditional midterm and final exams across all four sections of the course. All sections have equivalent content, assessments, and teaching methodologies. Student demographics such as exam type and location preferences are considered in our study to determine whether they have any impact on their learning approach. Large amount of data from the learning management system (LMS), Blackboard (BB) Learn, had to be examined to compare the results of several assessment outcomes for all students within their respective section and amongst students of other sections. To investigate the effect of dissimilar assessment formats on student performance, we had to correlate individual question formats with the overall course grade. The results show that collective assessment formats allow students to be effective in demonstrating their knowledge.

Rapid advances in analytical modelling and information processing capabilities, particularly in machine learning (ML) and artificial intelligence (AI), combined with ever more granular data are currently transforming many aspects of everyday life and work. In this blog post we give a brief overview of basic concepts of ML and potential applications at central banks based on our research. We demonstrate how an artificial neural network (NN) can be used for inflation forecasting which lies at the heart of modern central banking. We show how its structure can help to understand model reactions. The NN generally outperforms more conventional models.

In the early 1980s, children at a school in Nicaragua did something remarkable: they spontaneously created a language. Brought together for the first time in a school for deaf children, they had no shared sign language and so they developed their own. The result, ISN (Idioma de Señas de Nicaragua), is a grammatically complex, expressive language that speaks to our natural need to engage with others. Those children created a way to share, learn and converse with each other because that's what humans do. Remember the last time you chatted with a good friend: it's likely that your conversation felt natural, easy.

Astronauts are getting a mouth-watering haul with the latest Earth-to-space delivery - pizza and ice cream. A commercial supply ship arrived at the International Space Station on Tuesday, two days after launching from Virginia. Besides equipment and experiments, the Orbital ATK capsule holds chocolate and vanilla ice cream for the six station astronauts, as well as make-your-own flatbread pizzas. Italy's Paolo Nespoli used the space station's robot arm to grab the cargo ship, as they zoomed 260 miles above the Indian Ocean Astronauts always crave pizza in orbit, but it's been particularly tough for Italy's Paolo Nespoli. He's been up there since July and has another month to go.

The average IQ in the UK is 104 but even the brainiest Brits may struggle to get through this challenging test. A new quiz from Playbuzz puts your IQ to the test in a series of fiendishly difficult puzzles and riddles that are leaving the Internet baffled. Devised by user Terry Stein, players are faced with ten baffling questions and according to Playbuzz only 0.1 per cent will be able to secure full marks. Those who do master the challenge are said to have a'passion for perfection', enjoy challenging themselves and'excel in finding problems and solutions'. Think you can rise to the challenge?

If you're a Machine Learning graduate and can speak the language of your chosen location plus English - this is for you! Do not miss these fantastic opportunities, apply today http://bit.ly/AIMLEur

An increasing number of organizations are using artificial intelligence (AI) to aid in their digital transformation and remain competitive, according to a new report by the International Data Corporation (IDC) and DataRobot released Monday. AI is expected to help companies across the world grow over the next five years, with Japan leading the pack with 74% expected projected growth from 2016-2021, according to the report. The US should expect 49% compound annual growth, with countries in Western Europe expecting around 44% growth. Two-thirds of businesses globally already have implemented AI, or plan on using the technology in the next five years, the report said. The US has the most early adoption, with 38% of companies already using AI, ahead of 11% in Asia and 9% in Western Europe.

A nonparametric family of conditional distributions is introduced, which generalizes conditional exponential families using functional parameters in a suitable RKHS. An algorithm is provided for learning the generalized natural parameter, and consistency of the estimator is established in the well specified case. In experiments, the new method generally outperforms a competing approach with consistency guarantees, and is competitive with a deep conditional density model on datasets that exhibit abrupt transitions and heteroscedasticity.

Solving inverse problems is central to geosciences and remote sensing. Radiative transfer models (RTMs) represent mathematically the physical laws which govern the phenomena in remote sensing applications (forward models). The numerical inversion of the RTM equations is a challenging and computationally demanding problem, and for this reason, often the application of a nonlinear statistical regression is preferred. In general, regression models predict the biophysical parameter of interest from the corresponding received radiance. However, this approach does not employ the physical information encoded in the RTMs. An alternative strategy, which attempts to include the physical knowledge, consists in learning a regression model trained using data simulated by an RTM code. In this work, we introduce a nonlinear nonparametric regression model which combines the benefits of the two aforementioned approaches. The inversion is performed taking into account jointly both real observations and RTM-simulated data. The proposed Joint Gaussian Process (JGP) provides a solid framework for exploiting the regularities between the two types of data. The JGP automatically detects the relative quality of the simulated and real data, and combines them accordingly. This occurs by learning an additional hyper-parameter w.r.t. a standard GP model, and fitting parameters through maximizing the pseudo-likelihood of the real observations. The resulting scheme is both simple and robust, i.e., capable of adapting to different scenarios. The advantages of the JGP method compared to benchmark strategies are shown considering RTM-simulated and real observations in different experiments. Specifically, we consider leaf area index (LAI) retrieval from Landsat data combined with simulated data generated by the PROSAIL model.