A hypernetwork aims to find the best deep neural network architecture to solve a given task. Boris Knyazev of the University of Guelph in Ontario and his colleagues have designed and trained a "hypernetwork" that could speed up the training of neural networks. Given a new, untrained deep neural network designed for some task, the hypernetwork predicts the parameters for the new network in fractions of a second, and in theory could make training unnecessary. The work may also have deeper theoretical implications. The name outlines the approach.

Artificial intelligence is largely a numbers game. When deep neural networks, a form of AI that learns to discern patterns in data, began surpassing traditional algorithms 10 years ago, it was because we finally had enough data and processing power to make full use of them. Today's neural networks are even hungrier for data and power. Training them requires carefully tuning the values of millions or even billions of parameters that characterize these networks, representing the strengths of the connections between artificial neurons. The goal is to find nearly ideal values for them, a process known as optimization, but training the networks to reach this point isn't easy.

In a bid to combat fake news, researchers at the MIT's CSAIL and Qatar's Computing Research Institute have built an artificially intelligent system that is capable of scanning not the news per say, but its source to identify for falsehood. The AI, which is still under development, uses machine learning algorithm which has been trained using Media Bias/Fact Check's analysis of over 2,000 news outlets to look for the linguistic cues of sites that push fake or distorted news, Engadget reported. Additionally, the machine learning approach is also capable of drawing links between a site's authenticity and its Wikipedia page or web addresses. However, the system is not perfect yet, and can only detect accuracy with 65 percent effectiveness and bias with 70 percent.

Intel's secretive Knights Mill mega-chip will challenge GPUs for AI domination