It may have been around for quite awhile, but neuromorphic computing is garnering a lot of attention as of late. Neuromorphic computing employs a process that utilizes lessons learned from biology to build more efficient, brain-like machines. In the five years ending in 2019, over $2 billion was invested in companies that specialize in neuromorphic computing. This estimate does not include internal spending on neuromorphic computing as an aside by large technology providers such as IBM, Intel and Samsung. The article that follows offers a good summary of the subject, and also provides a link to an informative special project on neuromorphic computing.
EETimes editor Sunny Bains just published a fascinating report on neuromorphic electronics; specifically, its advantages when it comes to speed, weight, area, and power for neural processing. Bains also goes into some of the solution’s engineering trade-offs as well as how it’s being used commercially.
Among some of the key topics covered:
- Do AI and neuromorphic computing compete?
- Is neuromorphic computing emerging as a post-Moore’s Law processing technology?
- Can we use this technology as a bridge to quantum computing?
From the Project’s opening section:
Now that computers are ubiquitous, we are looking for more ways to delegate to them the tasks that we were previously content to perform ourselves: operating industrial robots, driving cars and detecting disease. That transition has propelled advances in new approaches, including neuromorphic computing.