Intel revealed this week that a system based on its Loihi chip planned for 2019 will include the equivalent of 100 billion synapses, which is about the same brain complexity as a common mouse.
Last September, Intel introduced the world to Loihi which was a chip designed to promote, what Intel calls, probabilistic computing. Intel views probabilistic computing as a vital step on the path to artificial intelligence (AI).
The version of Loihi that Intel introduced last year was equipped with 130,000 silicon “neurons” connected with 130 million “synapses”, the junctions that connect neurons within the brain of a human being. Loihi is designed to mimic the workings of the brain diverging from the sequential pipeline of instructions used by a Core chip.This week, Intel said that it has increased its goal with its 2019 plan, aiming for more than 100 billion synapses within a Loihi “system.” An Intel spokesman said on Monday that the roadmap calls for “one large, multi-chip system,” rather than a single chip.
Scientists have worked for years towards modeling the cortex of various animals giving us a point of comparison for the assessment of how sophisticated these neural networks can get. In a 2009 paper from Rajagopal Ananthanarayanan, Steven K. Esser, Horst D. Simon, and Dharmendra S. Modha of IBM Almaden and Lawrence Berkeley National Laboratory, the research team simulated the cerebral cortex of a cat using LLNL’s Dawn Blue Gene/P supercomputer with 147,456 CPUs and 144TB of main memory.In an accompanying graphic, the team shows the relative synaptic complexity of several animals. At the bottom, with 125 billion synapses, is the common mouse—slightly higher than the complexity the Loihi system will achieve. This further cements the standing of Intel in the field of artificial intelligence and how far they have come in achieving the true sense of AI.
As the graphic indicates, the next step is the rat, with about 500 billion synapses. But if Intel’s progress is charted linearly, that could require several years to achieve. Far ahead, of course, is the cat cortex, estimated at about 6.1 trillion synapses.
Humans, on this scale would lie on the extreme end of the spectrum. A stupendous nine trillion synapses equates to about 4.5 percent of the human cortex, meaning that you’ll have to wait a few decades to achieve the equivalent of a human brain on a chip. On the other hand, the joint IBM/LBNL paper was authored in 2009, so its safe to speculate on simulations constructed by companies like Google with actual supercomputers.Intel continues to work with researchers to test the Loihi chip. It was most recently shown off at an academic conference in Canada, running a keyword recognition app and a neuomorphic robotic arm controller that could react to unexpected changes in weight or orientation. Intel said it’s seeking academic proposals until May 25 of this year.
As multiple companies work towards an enhanced world assisted by artificial intelligence, we need to question the extent of progress to know what lies ahead. How do we measure artificial intelligence across different implementations (AI via the cloud, AI on a chip, or AI on “edge” devices like a PC). This is a very specific implementation of AI: modelling the human brain. At the moment with Loihi, Intel can be commended on its progress with the implementation of animal intelligence in AI.