Network Security Internet Technology Development Database Servers Mobile Phone Android Software Apple Software Computer Software News IT Information

In addition to Weibo, there is also WeChat

Please pay attention

WeChat public account


Many universities in the United States have jointly developed a new brain-like transistor, which can simulate human brain thinking and memory.

2024-04-22 Update From: SLTechnology News&Howtos shulou NAV: SLTechnology News&Howtos > IT Information >


Shulou( Report--, December 21 (Xinhua) according to foreign media Tech Xplore local time on the 20th, researchers at the Massachusetts Institute of Technology, Northwestern University and Boston College have created a special transistor that can think and remember things like the human brain-- that is, it can process and store information at the same time.

Ordinary computers consume a lot of energy when performing tasks, especially when processing data from smart devices. This kind of device has the characteristics of high speed and high energy efficiency, and has the function of memory even when there is no electricity, so it is more suitable for daily use. At the same time, unlike other brain-like devices that can only work at ultra-low temperatures, this device can work at room temperature.

In the new experiment, researchers have shown that the transistor can do more than simple machine learning: it can classify data and perform associative learning. Researchers have reportedly developed a new type of synaptic transistor capable of thinking at a higher level by drawing inspiration from the human brain.

Mark Hersam, a researcher at Northwestern University who co-led the study, said the team's goal is to push AI technology to a higher level of thinking because real-world conditions are often more complex than current AI algorithms can handle.

If the purpose of AI is to mimic the human mind, then one of its lowest tasks is to classify data, that is, simply categorize.

The researchers showed the device a pattern with the word "000" and then asked it to recognize a similar pattern, such as the number 111 or 101. "if we train it to detect 000 and give it 111 and 101, it will know that 111 is more similar to 000 than 101."

The team's research was published in the journal Nature on December 20. attached a link: click here

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.

Views: 0

*The comments in the above article only represent the author's personal views and do not represent the views and positions of this website. If you have more insights, please feel free to contribute and share.

Share To

IT Information


© 2024 SLNews company. All rights reserved.