In a joint study published in Nature Machine Intelligence, researchers from Intel Labs and Cornell University have demonstrated the ability of Intel’s neuromorphic search chip, Loihi, to internalize dangerous chemicals and recognize them in the presence of interference and important blocking elements . Loihi internalized each odor with a single sample without interrupting the storage of previously internalized odors. It demonstrated superior recognition accuracy compared to state-of-the-art conventional methods, including a deep learning solution that required 3,000 times more training samples to achieve the same level of classification accuracy.
Nabil Imam, a senior research scientist at Intel’s Neuromorphic Computing Laboratory, notes that “we are developing neural algorithms in Loihi that mimic the processes that are activated in our brain when we smell something. This work is an excellent example of contemporary research, halfway between neuroscience and artificial intelligence (AI), and highlights Loihi’s potential to deliver outstanding sensing capabilities that could benefit multiple industries. “
Because it is important
Dangerous odors internalized and recognized by Loihi pose a danger to public health, as they serve as precursors in the manufacture of explosives, narcotics and polymers. The findings support the potential of neuromorphic chips to recognize these odors in real situations more effectively than conventional solutions and offer us insight into possible use cases for neuromorphic technology.
In the future, wearable ‘electronic olfactory systems’ with neuromorphic chips could be used by doctors to diagnose diseases, by airport security personnel to detect weapons and explosives, by police and border control to more easily locate and seize substances. narcotics, and even to create more effective smoke and carbon monoxide detectors for homes.
Using a neural algorithm derived from the architecture and dynamics of the brain’s olfactory circuits, researchers at Intel and Cornell University trained Intel’s Loihi neuromorphic search chip to internalize and recognize the odors of ten dangerous chemicals. To do this, the team used a data set consisting of the activity of 72 chemical sensors in response to these odors and configured the circuit diagram of biological smell in Loihi. The chip quickly learned the neural representation of each of the smells and recognized them all even in a context of considerable blockage, revealing a promising future for the intersection between neuroscience and artificial intelligence.
What Loihi Wikipedia Says
Loihi is an active underwater volcano that is located about 35 km south east of the coast of the island of Hawaii, but it is also the name that Intel gave in 2017 to its first chip. This processor introduced an important advance for the development of neuromorphic hardware, and in March 2018 Intel created the Neuromorphic Research Community to drive the development of neuromorphic algorithms, software and applications.
In the middle of last year, the American company once again took a qualitative leap in its commitment to processors that simulate the human brain and announced the availability for the research community of a neuromorphic system of 8 million neurons, made up of 64 Loihi research chips. , and called Pohoiki Beach. Thanks to Pohoiki Beach, researchers will be able to experiment with Intel’s Loihi research chip, which applies the principles of biological brains to computer architectures. Loihi enables information processing up to 1,000 times faster and 10,000 times more efficient than CPUs used in specialized applications, including sparse coding, graphics search, and constraint compliance issues.
