Transitioning from hype to reality, artificial intelligence (AI) is gaining momentum across industries thanks to an explosion in computing power and storage, the emergence of IoT (Internet of Things) and big data, and algorithmic advances.

In a very deep network such as a conv net with lots of filters and/or full layers, it seems to me that not all filters/weights are equally important - some could even be useless. Is there a scheme that removes these from the network (to save computation time)? I'm not talking about dropout which temporarily takes them out, I mean permanently take them out based on small gradients, high varience, etc. If anyone knows anything I'd appreciate some links/papers (sorry I'm new to NN).

Subrata Rakshit, a scientist at the Centre for Artificial Intelligence and Robotics, said the DRDO is trying to develop a set of robots for surveillance. He said services need to come to a certain level of digitalisation. "We are developing these large applications software and putting in Artificial Intelligence …

Chinese police have used facial recognition technology to locate and arrest a man who was among a crowd of 60,000 concert goers. The suspect, who has been identified only as Mr Ao, was attending a concert by pop star Jacky Cheung in Nanchang city last weekend when he was caught. Police said the 31-year-old, who was wanted for "economic crimes", was "shocked" when he was caught. China has a huge surveillance network of over 170 million CCTV cameras. Mr Ao was identified by cameras at the concert's ticket entrance, and apprehended by police after he had sat down with other concert goers.

The Flintstones, a cartoon about life in the Stone Age, has just surpassed The Jetsons, a cartoon about life in the distant future, when it comes to technological innovation. Researchers have successfully trained artificial intelligence to generate new clips of the prehistoric animated series based on nothing but random text descriptions of what's happening in a scene. A team of researchers from the Allen Institute for Artificial Intelligence, and the University of Illinois Urbana-Champaign, trained an AI by feeding it over 25,000 three-second clips of the cartoon, which hasn't seen any new episodes in over 50 years. Most AI experiments as of late have involved generating freaky images based on what was learned, but this time the researchers included detailed descriptions and annotations of what appeared, and what was happening, in every clip the AI ingested. As a result, the new Flintstones animations generated by the Allen Institute's AI aren't just random collages of chopped up cartoons.

Driven by new technology, there are some big changes coming in entertainment, though by all accounts, the massive exhibition at this year's National Association of Broadcasters Show was nevertheless quieter in comparison with recent years. One booth that attracted many from the Hollywood crowd was that of Sony, where delegates -- whether that be tech leaders or cinematographers -- took a keen interest in the images produced by Sony's Crystal LED video wall, which was featured in the center of the booth in an 8K x 4K (and 32 ft. Sony, as well as Samsung, have both proposed their LED panels, offering modular configurations, as a replacement to cinema projection. It's a radical concept when one considers that cinema projection has been around since the birth of the artform. Meanwhile there are still plenty of issues to address, from how to handle sound to the cost.

Driven by new technology, there are some big changes coming in entertainment, though by all accounts, the massive exhibition at this year's National Association of Broadcasters Show was nevertheless quieter in comparison with recent years. One booth that attracted many from the Hollywood crowd was that of Sony, where delegates -- whether that be tech leaders or cinematographers -- took a keen interest in the images produced by Sony's Crystal LED video wall, which was featured in the center of the booth in an 8K x 4K (and 32 ft. Sony, as well as Samsung, have both proposed their LED panels, offering modular configurations, as a replacement to cinema projection. It's a radical concept when one considers that cinema projection has been around since the birth of the artform. Meanwhile there are still plenty of issues to address, from how to handle sound to the cost.

A report from Bloomberg earlier this week claimed that Apple's HomePod isn't doing so well, and that the company cut orders for new hardware from suppliers. This might not shock some of you: Apple missed the all-important holiday buying season and is competing with less expensive hardware from Google, Sonos and Amazon. But is the first smart speaker with Siri already a failure, or does the HomePod simply need time to find its place? I'm not in any way surprised that the HomePod has fizzled, simply because it's a weird product with a very weird proposition. I seriously considered buying it in the run-up to its launch, but ultimately couldn't find a strong enough reason to plunk down $350.

The fundamental problem in short-text classification is \emph{feature sparseness} -- the lack of feature overlap between a trained model and a test instance to be classified. We propose \emph{ClassiNet} -- a network of classifiers trained for predicting missing features in a given instance, to overcome the feature sparseness problem. Using a set of unlabeled training instances, we first learn binary classifiers as feature predictors for predicting whether a particular feature occurs in a given instance. Next, each feature predictor is represented as a vertex $v_i$ in the ClassiNet where a one-to-one correspondence exists between feature predictors and vertices. The weight of the directed edge $e_{ij}$ connecting a vertex $v_i$ to a vertex $v_j$ represents the conditional probability that given $v_i$ exists in an instance, $v_j$ also exists in the same instance. We show that ClassiNets generalize word co-occurrence graphs by considering implicit co-occurrences between features. We extract numerous features from the trained ClassiNet to overcome feature sparseness. In particular, for a given instance $\vec{x}$, we find similar features from ClassiNet that did not appear in $\vec{x}$, and append those features in the representation of $\vec{x}$. Moreover, we propose a method based on graph propagation to find features that are indirectly related to a given short-text. We evaluate ClassiNets on several benchmark datasets for short-text classification. Our experimental results show that by using ClassiNet, we can statistically significantly improve the accuracy in short-text classification tasks, without having to use any external resources such as thesauri for finding related features.

Lately, the DJI Drone Photography Award, make creative use of a drone to explore new photographic possibilities. The drone work is awe-inspiring, letting us consider the world from an alternative perspective. The Sand Castles (Part II) by Markel Redondo focuses on highlighting the Spain's problem from a new perspective. "We live in a society with huge housing issues, where many cannot afford a place to live, yet Spain has more than three million empty homes," said Redondo. Hegen loves exploring the relationship between man and nature and uses aerial photography via drone to document landscapes that have been transformed by human intervention.