Intel introduces self learning Loihi research test chip with circuits that mimic the mechanics of the human brain

**Intel** has developed a neuromorphic chip, code named Loihi, that emulates the way the human brain works by learning based on feedback from the environment. The chip learns and adapts based on data, gets smarter over time, does not need to be trained in the conventional way and promises to make **machine learning** faster while being conservative on energy use. The rate at which the chip learns is demonstrated to be one million times better than typical neural nets. The energy efficiency is a 1,000 times better than general purpose computers conventionally used for training systems. [caption id=“attachment_4100101” align=“alignleft” width=“380”]  Image: Intel[/caption] Dr. Michael Mayberry, corporate vice president and managing director of Intel Labs says, “I hope you will follow the exciting milestones coming from Intel Labs in the next few months as we bring concepts like neuromorphic computing to the mainstream in order to support the world’s economy for the next 50 years. In a future with neuromorphic computing, all of what you can imagine – and more – moves from possibility to reality, as the flow of intelligence and decision-making becomes more fluid and accelerated.” The asynchronous neuromorphic core mesh on the chip supports a number of neural network topologies, with each node or neuron capable of communicating with thousands of other neurons. There are a total of 130,000 neurons and 130 million synapses on each chip. Each neuromorphic core includes a learning engine that supports a number of machine learning paradigms, including supervised learning, unsupervised learning and reinforcement learning. Applications for the chip include autonomous robots, image recognition including facial recognition or CCTV footage analysis, integration in manufacturing assembly lines, processing data for healthcare workers, cybersecurity processes and integration into smart cities. The chip will be shared with leading universities and research institutions with a focus on advancing AI, from the first half of 2018.