The advent of deep learning has yielded powerful tools to automatically compute gradients of computations. This is because training a neural network equates to iteratively updating its parameters using gradient descent to find the minimum of a loss function. Deep learning is then a subset of a broader paradigm; a workflow with free parameters that is end-to-end optimisable, provided one can keep track of the gradients all the way through. This work introduces neos: an example implementation following this paradigm of a fully differentiable high-energy physics workflow, capable of optimising a learnable summary statistic with respect to the expected sensitivity of an analysis. Doing this results in an optimisation process that is aware of the modelling and treatment of systematic uncertainties.

A robotic exoskeleton and performance art installation is automating the discipline of synchronized dance. At San Francisco's Gray Area Festival, an annual event that combines art, technology, and music, an exhibit called'Inferno' is employing robotics to turn people into puppets. With an exoskeleton and a'dark industrial' soundtrack, Inferno is commandeering participants' limbs for an enthralling -- if off-putting -- performance. Participants in the piece are subject to the input of a'DJ' who controls both the music and how subjects dance to it'Each robot is designed to perform dynamic movements choreographed and activated by the artists, mobilizing the performers to dance in time to the dark, industrial techno soundtrack for the audience,' says a description on the event's website. The installation, which described by one Twitter user as a'forced rave' is not just fascinating to watch, but according to the routine's creators, Louis-Philippe Demers and Bill Vorn, is designed to stoke conversations about agency and technology.

Firefighting gear has evolved continuously since the 1600s to keep pace with the challenges that firefighters face, such as the numerous blazes that are currently ravaging Northern California. During the colonial days, structures routinely burned to the ground because firefighters simply lacked the necessary protection (any protection, really) to enter buildings and fight fires from the inside. The development of the first helmet in the 1730s, self-contained breathing apparatus (SCBA) in 1863 and the telescoping ladder in the 1880s helped make the job safer. Though it wasn't until the 1980s that modern Nomex- and Kevlar-impregnated gear became common. Today, however, the firefighting community is going through a technological revolution that could grant tomorrow's firefighters near superhuman abilities.

Time Budget: 30 seconds Hi, my name is Matthias Langer. I am currently a PhD student at La Trobe University. Today I would like to present to you Inferno, which is a deep learning system that we develop here in Melbourne and can run on top of Spark. Time Budget: 30 seconds My talk will be structured as follows: I will talk with you a little bit about DL. … then about DL and Spark… … our own DL system …. Time Budget: 30 seconds Talking Points: So without further ado, let's start… Time Budget: 1 minute So, what is deep learning? Deep learning is machine learning algorithm that tries to extract hierarchical features from input data. In itself that is kind of similar to how the brain does it in this slide. So how does that work: Let's say a stimulus (or input) comes from the eye and eventually ends up in region V1. There primitive features like edges are extracted.

Apple IS developing a car: First patent for'Project Titan' reveals pedestrian avoidance system Apple's latest patent describes technology for a collision avoidance system that is designed for robots, or self-driving cars. And it uses what it has learned from previous encounters for new ones. Facebook copies Snapchat AGAIN with new'photo frame'... Meet Fyodor: Russia's spacebot put through its paces on... Will Apple's next iPhone FOLD? Patents reveal flexible'flip... Earth could be DESTROYED in a fiery inferno as the sun... Facebook copies Snapchat AGAIN with new'photo frame'... Meet Fyodor: Russia's spacebot put through its paces on... Will Apple's next iPhone FOLD? Patents reveal flexible'flip... Earth could be DESTROYED in a fiery inferno as the sun... Details about Apple's secretive'Project Titan' have been floating around since last year and although the Cupertino company has tried to deny its plan for a self-driving car (pictured is a concept drawing), its actions speak otherwise The new patent describes technology that could be the key to self-driving cars – a system that can operate in both 2D and 3D area, which computer visions systems have had difficulty doing.