Breakthroughs, discoveries, and DIY tips sent every weekday. Using advanced imaging techniques, an international research team has reconstructed an ancient extinct fish's heart, brain, and fins from an intricately detailed, fingernail-sized fossil fragment. But cartoon lookalikes aside, the creature may help rewrite one of the earliest chapters in animal evolution. Its details are described in a study published on August 6 in Nature. Earth's first fish arrived about half a billion years ago, but not anywhere near the ocean's surface.

The use of deep neural networks in edge computing devices hinges on the balance between accuracy and complexity of computations. Ternary Connect (TC) \cite{lin2015neural} addresses this issue by restricting the parameters to three levels $-1, 0$, and $+1$, thus eliminating multiplications in the forward pass of the network during prediction. We propose Generalized Ternary Connect (GTC), which allows an arbitrary number of levels while at the same time eliminating multiplications by restricting the parameters to integer powers of two. The primary contribution is that GTC learns the number of levels and their values for each layer, jointly with the weights of the network in an end-to-end fashion. Experiments on MNIST and CIFAR-10 show that GTC naturally converges to an `almost binary' network for deep classification networks (e.g. VGG-16) and deep variational auto-encoders, with negligible loss of classification accuracy and comparable visual quality of generated samples respectively. We demonstrate superior compression and similar accuracy of GTC in comparison to several state-of-the-art methods for neural network compression. We conclude with simulations showing the potential benefits of GTC in hardware.

Seen it, seen it, seen it, seen it, seen it. Most of us instinctively know whether objects are familiar or unfamiliar. Now we may know how we know. It turns out monkeys have a cluster of neurons in their brains that decides whether or not they have seen objects before. The primary visual area, at the back of the brain, does most of the early work in perceiving an object, especially its physical attributes, such as what direction it is moving.

In experiments involving a simulation of the human esophagus and stomach, researchers at MIT, the University of Sheffield, and the Tokyo Institute of Technology have demonstrated a tiny origami robot that can unfold itself from a swallowed capsule and, steered by external magnetic fields, crawl across the stomach wall to remove a swallowed button battery or patch a wound. The new work, which the researchers are presenting this week at the International Conference on Robotics and Automation, builds on a long sequence of papers on origami robots from the research group of Daniela Rus, the Andrew and Erna Viterbi Professor in MIT's Department of Electrical Engineering and Computer Science. "It's really exciting to see our small origami robots doing something with potential important applications to health care," says Rus, who also directs MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL). "For applications inside the body, we need a small, controllable, untethered robot system. It's really difficult to control and place a robot inside the body if the robot is attached to a tether."

The new work, which the researchers are presenting this week at the International Conference on Robotics and Automation, builds on a long sequence of papers on origami robots from the research group of Daniela Rus, the Andrew and Erna Viterbi Professor in MIT's Department of Electrical Engineering and Computer Science. "It's really exciting to see our small origami robots doing something with potential important applications to health care," says Rus, who also directs MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL). "For applications inside the body, we need a small, controllable, untethered robot system. It's really difficult to control and place a robot inside the body if the robot is attached to a tether." Joining Rus on the paper are first author Shuhei Miyashita, who was a postdoc at CSAIL when the work was done and is now a lecturer in electronics at the University of York, in England; Steven Guitron, a graduate student in mechanical engineering; Shuguang Li, a CSAIL postdoc; Kazuhiro Yoshida of Tokyo Institute of Technology, who was visiting MIT on sabbatical when the work was done; and Dana Damian of the University of Sheffield, in England.

Photography company Getty Images is accusing Google of scraping images from third party websites and encouraging piracy, adding a new wrinkle to the Mountain View, Calif.'s ongoing legal battles in Europe. Google first introduced the feature in Jan. 2013. Previously, the search engine only displayed tiny thumbnails of images. In a statement released to TIME ahead of the filing, Getty argues that since image consumption is immediate, "there is little impetus to view the image on the original source site" once it's seen in high resolution on Google. The complaint comes less than a week after the European Union's antitrust commission charged Google with using unfair practices to promote its own services on Android devices.

From fuel cell vehicles to self-driving cars, new technologies for next-generation autos are gaining traction. In a move likely to accelerate this, the United Nations World Forum for Harmonization of Vehicle Regulations, which consists of major car-producing nations and sets international safety and environmental standards on vehicles, said in November it will allow carmakers worldwide to replace side and rear mirrors with camera monitor systems. Following the U.N. panel's decision, the transport ministry will from June allow mirrorless cars on to the nation's roads. A mirrorless car does not have rear-view and side-view mirrors. Instead, the car is equipped with a sophisticated camera monitor system that shows drivers surrounding views on small screens positioned in front of them.