Kicking neural network design automation into high gear
A new area in artificial intelligence involves using algorithms to automatically design machine-learning systems known as neural networks, which are more accurate and efficient than those developed by human engineers. But this so-called neural architecture search (NAS) technique is computationally expensive. A state-of-the-art NAS algorithm recently developed by Google to run on a squad of graphic
MIT mathematicians solve age-old spaghetti mystery
If you happen to have a box of spaghetti in your pantry, try this experiment: Pull out a single spaghetti stick and hold it at both ends. Now bend it until it breaks. How many fragments did you make? If the answer is three or more, pull out another stick and try again. Can you break the noodle in two? If not, you’re in very good company. The spaghetti challenge has flummoxed even the likes of fame
Faster big-data analysis
We live in the age of big data, but most of that data is “sparse.” Imagine, for instance, a massive table that mapped all of Amazon’s customers against all of its products, with a “1” for each product a given customer bought and a “0” otherwise. The table would be mostly zeroes. With sparse data, analytic algorithms end up doing a lot of addition and multiplication by zero, which is wasted computa
Engineers design artificial synapse for “brain-on-a-chip” hardware
When it comes to processing power, the human brain just can’t be beat. Packed within the squishy, football-sized organ are somewhere around 100 billion neurons. At any given moment, a single neuron can relay instructions to thousands of other neurons via synapses — the spaces between neurons, across which neurotransmitters are exchanged. There are more than 100 trillion synapses that mediate neuro
Surprisingly simple scheme for self-assembling robots
In 2011, when an MIT senior named John Romanishin proposed a new design for modular robots to his robotics professor, Daniela Rus, she said, “That can’t be done.” Two years later, Rus showed her colleague Hod Lipson, a robotics researcher at Cornell University, a video of prototype robots, based on Romanishin’s design, in action. “That can’t be done,” Lipson said. In November, Romanishin — now a r
1
リリース、障害情報などのサービスのお知らせ
最新の人気エントリーの配信
j次のブックマーク
k前のブックマーク
lあとで読む
eコメント一覧を開く
oページを開く
Lobster’s underbelly is as tough as industrial rubber
Team invents method to shrink objects to the nanoscale | MIT News
Model helps robots navigate more like humans do | MIT News