Intel has developed a neuromorphic chip that can distinguish odors
Brain-computer interfaces, artificial neural networks, and neuromorphic chips are areas where researchers are currently researching to drive new computing frameworks and interfaces by simulating the structure of the human brain. Recently, a paper published in the journal Nature revealed that Intel researchers and olfactory neurophysiologists have created a neuromorphic chip that can distinguish odors.
The design of the chip is inspired by the structure of the olfactory bulb in the human brain. The olfactory bulb is responsible for analyzing the electrical signals transmitted by the olfactory cells in the nose in our human body. The chip created this time is based on the brain processing odor. The neural circuit that was triggered at that time is now implemented on Intel‘s Loihi neuromorphic system.
In order to enable the chip to analyze these electrical signals transmitted by the sensor, the research team produced a neural algorithm as the “receiver” of the electrical pulse. The algorithm was trained using a data set containing 10 “odors”. The traditional chip requires more training samples to recognize the smell of a given test sample.
“My next step is to generalize this approach to a wider range of problems—from sensory scene analysis (understanding the relationships between objects you observe) to abstract problems like planning and decision-making,” said Nabil Imam, a senior research scientist in Intel Lab’s neuromorphic computing group, in a statement. “Understanding how the brain’s neural circuits solve these complex computational problems will provide important clues for designing efficient and robust machine intelligence.”