Real-valued word representations have transformed NLP applications; popular examples are word2vec and GloVe, recognized for their ability to capture linguistic regularities. In this paper, we demonstrate a {\em very simple}, and yet counter-intuitive, postprocessing technique -- eliminate the common mean vector and a few top dominating directions from the word vectors -- that renders off-the-shelf representations {\em even stronger}. The postprocessing is empirically validated on a variety of lexical-level intrinsic tasks (word similarity, concept categorization, word analogy) and sentence-level tasks (semantic textural similarity and { text classification}) on multiple datasets and with a variety of representation methods and hyperparameter choices in multiple languages; in each case, the processed representations are consistently better than the original ones.

In this work, we revisit fast dimension reduction approaches, as with random projections and random sampling. Our goal is to summarize the data to decrease computational costs and memory footprint of subsequent analysis. Such dimension reduction can be very efficient when the signals of interest have a strong structure, such as with images. We focus on this setting and investigate feature clustering schemes for data reductions that capture this structure. An impediment to fast dimension reduction is that good clustering comes with large algorithmic costs. We address it by contributing a linear-time agglomerative clustering scheme, Recursive Nearest Agglomeration (ReNA). Unlike existing fast agglomerative schemes, it avoids the creation of giant clusters. We empirically validate that it approximates the data as well as traditional variance-minimizing clustering schemes that have a quadratic complexity. In addition, we analyze signal approximation with feature clustering and show that it can remove noise, improving subsequent analysis steps. As a consequence, data reduction by clustering features with ReNA yields very fast and accurate models, enabling to process large datasets on budget. Our theoretical analysis is backed by extensive experiments on publicly-available data that illustrate the computation efficiency and the denoising properties of the resulting dimension reduction scheme.

Robotics, artificial intelligence, virtual and augmented reality and other new technologies can both strengthen and undermine key values such as privacy, non-discrimination, human dignity (such as when care tasks are carried out by robots), human rights and the right to due process, says the Rathenau Institute. At the same time, these technologies offer new social and commercial opportunities, potential gains in efficiency and quality, and educational benefits. The government has therefore decided to commission more research into the societal effects of technological developments and to establish an inter-ministerial working group to study this issue. And the budget of the Data Protection Authority will be almost doubled. The cabinet made these decisions following proposals put forward jointly by Minister of the Interior and Kingdom Relations Kajsa Ollongren and her ministry's state secretary Raymond Knops, State Secretary for Economic Affairs and Climate Policy Mona Keijzer, Minister of Justice and Security Ferdinand Grapperhaus and Minister for Legal Protection Sander Dekker.

A new dating app called Waving lets users judge potential partners by their voice. We talk with Robert Burriss of Basel University about the role a person's voice plays in attraction.

The tiny tadpole embryo looked like a bean. One day old, it didn't even have a heart yet. The researcher in a white coat and gloves who hovered over it made a precise surgical incision where its head would form. Moments later, the brain was gone, but the embryo was still alive. The brief procedure took Celia Herrera-Rincon, a neuroscience postdoc at the Allen Discovery Center at Tufts University, back to the country house in Spain where she had grown up, in the mountains near Madrid. When she was 11 years old, while walking her dogs in the woods, she found a snake, Vipera latastei.

Artificial intelligence could emulate human bias, including sexism, if there is no oversight on data used to create it, experts at the world's largest mobile phone fair in Barcelona warned Thursday. "We're all very aware the machines will learn the same bias as those who coded them," Emma McGuiguan, in charge of technology at consultants Accenture, said at the Mobile World Congress. AI is the science of programming machines or computers to reproduce human processes, like learning and decision making. Julie Woods-Moss, chief innovation officer at Indian mobile operator Tata Communications, said that in order to do this, a large amount of human-led data was needed. "We have to be very careful that we don't encourage AI to be biased," she said, calling on professionals in the sector to find ways to identify these biases.

An international collaboration led by ETH Zurich scientists used machine learning to teach a computer to predict the outcomes of quantum experiments. Researchers at ETH Zurich in Switzerland have used machine learning to teach a computer to predict the outcomes of quantum experiments, which could be essential for testing future quantum computers. The new machine-learning software enables a computer to "learn" the quantum state of a complex physical system based on experimental observations and to predict the outcomes of hypothetical measurements. The researchers first showed the system handwritten samples, and it learned to replicate each letter, word, and sentence. The computer also calculated a probability distribution that expressed mathematically how often a letter is written in a certain way when it is preceded by some other letter.

IMAGE: This is Ion Petre, Professor of Computer Science at Abo Akademi University. The ongoing research on artificial intelligence methods for precision cancer medicine at the Computational Biomodeling (Combio) Laboratory of Åbo Akademi University and Turku Centre for Computer Science (TUCS) got a major boost with renewed funding from Business Finland. The concept of this project is that a patient's own molecular data can be used to identify, with the use of artificial intelligence methods, the best combinatorial multi-drug therapy for that patient. Network modelling plays a major role in this line of work, integrating genome-scale patient data into detailed interaction networks, that can be analysed by Combio's recently developed algorithms to identify combinations of drugs and inhibitors that are likely to be therapeutically effective. The project focuses on individual patients with the goal to dynamically adapt their therapeutical strategies to avoid the onset of drug resistance.

This UK-based startup is creating affordable and stylish 3D printed prostheses.

Robot Wars has been axed by the BBC for a second time. The show featuring duelling robots was rebooted on BBC Two in 2016 and ran for three series. Presented by Dara Ó Briain and Angela Scanlon since its return, it is to be scrapped to "make room for new shows", the BBC said. Soon after the announcement the hashtag #BringBackRobotWars started trending on social media. Sad to confirm the BBC's decision to de-activate our House Robots.