Intel creates a chip that can 'smell' drugs, explosives and chemicals

Sniffer dogs could be out of work after Intel creates a computer chip that can ‘smell’ dangerous chemicals in drugs, explosives and other illegal substances

  • Researchers created a circuit on a chip similar to the olfactory circuit in dogs
  • The team then use artificial intelligence to spot different chemical ‘smells’
  • The algorithm identifies smells by replicating the electric signals in the brain 

Intel has created a new computer chip that can smell dangerous chemicals in drugs, explosives and other substances, potentially putting sniffer dogs out of work.

Researchers for Intel and Cornell University created a ‘neuromorphic’ chip called Loii that makes computers think like biological brains.

They crafted a circuit on the chip itself that mirrors the circuit found in the olfactory bulbs of a dog’s brain – that they use to process smells. 

The Loihi chip can detect a specific odour on its first attempt – even if other smells are present, said Intel. 

It could be used to detect smells humans create when they have certain diseases – as well as odours linked to drugs and environmental gasses.

Scroll down for video 

Intel Labs’ Nabil Imam holds a Loihi neuromorphic test chip in his Santa Clara, California, neuromorphic computing lab. The chip has been developed to replicate the way neurons function in a mammal brain

A close-up photo shows Loihi, Intel’s neuromorphic research chip.It has been built to adapt and replicate the way the human brain processes information

Much like training sniffer dogs, the chip relies on artificial intelligence that is trained to identify individual smells so it can spot it again when re-exposed.

The chip itself processes information the same way as a mammal brain by using electrical signals to process different smells. 

When someone smells something the molecules interact with nasal receptors that send signals to the brain’s olfactory bulb. 

The brain then translates the signals to identify the specific smell – based on learning or previous experience with that scent. 

‘We are developing neural algorithms on Loihi that mimic what happens in your brain when you smell something,’ Nabil Imam, senior research scientist in Intel’s Neuromorphic Computing Lab, said in a statement.

He said the work ‘demonstrates Loihi’s potential to provide important sensing capabilities that could benefit various industries.’  

Intel worked with scientists who study the brains of animals while they smell, monitoring the way the neural circuits activate based on different scents.

They used the information on the way electrical circuits in the brain are triggered to recreate the process on silicon. 

They started by training it on ten noxious smells including methane, ammonia and acetone to learn the difference. 

It could be placed on robots in airports to help identify dangerous objects or added to sensors in hospitals or power plants to detect gases.

Researchers say it can learn each individual scent from just a few samples – compared to the thousands of samples usually needed by deep learning technologies. 

The Loihi chip can be used for other purposes as it can be adapted to replicate a range of brain functions. 

The Loihi chip has 130,000 artificial neurons and 130 million synapses that carry signals along the ‘neurons’. 

It constantly re-wires its own internal network to allow different types of learning.  

Dogs like this spaniel are used to detect drugs and explosives thanks to their enhanced sense of smell. The new chip could replace them in future by adding it to robots in airports. Stock image

Loihi chips only use about a thousandths of the energy of a normal computer processor and may be able to be used to solve similar problems in future. 

For the experiment Loihi took in data from 72 sensors in a wind tunnel that were exposed to 10 different odours. 

They were blown through and Loihi was able to build up its neurons in a way that allowed it to create a representation of each smell so it could identify them again in future. 

We do already have sensors in most homes and offices that can detect smoke and carbon monoxide – but this works in a very different way as they just ‘beep’ when they sense one specific odour. 

For the Loihi chip it can learn and place new smells into specific categories that allow it to use or refer to them again in future – similar to a dog’s brain.

The special ‘brain’ chips have been used previously to simulate the way skin perceives touch to move a prosthetic leg and even have it play table football.

They could also be used in future to create powerful brain like computers, say Intel.

The research has been published in the journal Machine Intelligence. 


Kai-Fu Lee, the author of AI Superpowers: China, Silicon Valley, and the New World Order, told the world of employments was facing a crisis ‘akin to that faced by farmers during the industrial revolution.’

Half of current jobs will be taken over by AI within 15 years, one of China’s leading AI experts has warned.

Kai-Fu Lee, the author of bestselling book AI Superpowers: China, Silicon Valley, and the New World Order, told the world of employments was facing a crisis ‘akin to that faced by farmers during the industrial revolution.’

‘People aren’t really fully aware of the effect AI will have on their jobs,’ he said.

Lee, who is a VC in China and once headed up Google in the region, has over 30 years of experience in AI.

He is set to reiterate his views on a Scott Pelley report about AI on the next edition of 60 Minutes, Sunday, Jan. 13 at 7 p.m., ET/PT on CBS. 

He believes it is imperative to ‘warn people there is displacement coming, and to tell them how they can start retraining.’

Luckily, he said all is not lost for humanity.

 ‘AI is powerful and adaptable, but it can’t do everything that humans do.’ 

Lee believe AI cannot create, conceptualize, or do complex strategic planning, or undertake complex work that requires precise hand-eye coordination.

He also says it is poor at dealing with unknown and unstructured spaces.

Crucially, he says AI cannot interact with humans ‘exactly like humans’, with empathy, human-human connection, and compassion.


A neuron, also known as nerve cell, is an electrically excitable cell that takes up, processes and transmits information through electrical and chemical signals. It is one of the basic elements of the nervous system.

In order that a human being can react to his environment, neurons transport stimuli.

The stimulation, for example the burning of the finger at a candle flame, is transported by the ascending neurons to the central nervous system and in return, the descending neurons stimulate the arm in order to remove the finger from the candle. 

A typical neuron is divided into three parts: the cell body, the dendrites and the axon. The cell body, the centre of the neuron, extends its processes called the axon and the dendrites to other cells.Dendrites typically branch profusely, getting thinner with each branching. The axon is thin but can reach enormous distances. 

To make a comparable scale, the diameter of a neuron is about the tenth size of the diameter of a human hair. 

All neurons are electrically excitable. The electrical impulse mostly arrives on the dendrites, gets processed into the cell body to then move along the axon.

On its all length an axon functions merely as an electric cable, simply transmitting the signal. 

Once the electrical reaches the end of the axon, at the synapses, things get a little more complex. 

The key to neural function is the synaptic signalling process, which is partly electrical and partly chemical. 

Once the electrical signal reaches the synapse, a special molecule called neurotransmitter is released by the neuron.

This neurotransmitter will then stimulate the second neuron, triggering a new wave of electrical impulse, repeating the mechanism described above.

Source: Read Full Article