Menu

Teaching Computers to Identify Odors

October 18, 2016

In experiments echoing mice behavior, researchers emulate how brains recognize specific smells. The Harvard Gazette spotlights work  by professor of molecular and cellular biology  Venkatesh Murthy using computer housed at the MGHPCC.

Read this story at the Harvard Gazette
by Peter Reuelle, Harvard Staff Writer
Though scientists have long known that mice can pick out scents — the smell of food, say, or the odor of a predator — they have been at a loss to explain how they are able to perform that seemingly complex task so easily.
But a new study, led by Venkatesh Murthy, professor of molecular and cellular biology, suggests that the means of processing smells may be far simpler than researchers realized.
Using a machine-learning algorithm, Murthy and colleagues were able to “train” a computer to recognize the neural patterns associated with various scents, and to identify whether specific odors were present in a mix of smells. The study is described in a Sept. 1 paper in the journal Neuron.
Along with Murthy, the paper was co-authored by Alexander Mathis, Dan Rokni, and Vikrant Kapoor, postdoctoral fellows working in Murthy’s lab, and Professor Matthias Bethge from the Werner Reichardt Centre for Integrative Neuroscience & Institute of Theoretical Physics in Germany.
“It’s easy to identify the smell of coffee on its own. But if the smell of cinnamon and flowers is mixed in, can I still identify the coffee?” Murthy said. “In an earlier study, we tested that in mice, and found they can do it very well.
“With this study, [we wanted to test] if we could build an algorithm … to do this in a computer, and what surprised us was how easy it is,” he said. “Initially, we thought it would be very complicated, but if you lay it out like a logic problem, it’s basically picking out a specific neural activation pattern that’s buried in a mix of patterns, and from a computer science perspective that’s do-able. The problem could be solved with a very simple linear classifier. It didn’t need the complexity and non-linearity that is built into deep neural networks. It’s no wonder mice were able to learn it so quickly and do it so well.”
Essentially, Murthy said, the algorithm works like any other pattern-recognition system, only the patterns are the neural activation patterns of mice reacting to particular odors.
“Essentially, one odor causes a particular neural activation pattern, and another odor causes a different pattern,” he said. “When you start mixing odors, eventually those patterns will overlap. Mice have about 1,000 types of olfactory receptors, but a given odor only activates maybe 10 percent of them. That’s sparse enough that, even if you have many scents mixed, they can still parse them out. What the algorithm does is look at those patterns, and even if they are partly occluded (by another odor), it can recognize that a particular pattern is there.”
To “train” the algorithm to recognize those patterns, Murthy and colleagues gathered data on the neural activation patterns associated with various odors by imaging the brains of mice over thousands of trials. The team then used 80 percent of that data to train the system to recognize patterns of activation for particular odors, even when those patterns were masked by a mixture of other scents.
“The computer looks at the patterns, randomly selects pixels, and adds them up,” Murthy explained. “If they reach a certain level, it says the target is there. Initially, though, it is almost certainly going to make a mistake. There’s then a process of fitting, in which we take the responses the computer gave and the actual responses, and we train it with the correct answers.”
Over thousands of trials, Murthy said, the algorithm eventually became as adept as mice at identifying whether a specific odor was present in a mixture of scents, suggesting that mice may be employing a similar algorithm.
Once they’d shown that the algorithm could identify target odors, Murthy and colleagues set out to trick it, not by making the scent mixtures more complex but by making them less so. Rather than training the computer with mixtures of various scents, researchers trained it exclusively with individual odors, and only exposed it to mixtures later. The result, Murthy said, was disastrous. Though the algorithm could easily identify single odors, it quickly broke down as mixtures became more complex.
When Murthy and colleagues ran the same experiment using mice, they found the same result.
“That was a surprise,” Murthy said. “What we think was happening is if both the algorithm and mouse establish that boundary for how to classify things when the world is simple, as the world gets more and more complex, that’s no longer the proper boundary.”
In addition to shedding light on how mice are able to discern individual scents, the study points toward computer-learning algorithms as potentially powerful tools to examine olfaction, and a way to design and conduct experiments in a virtual space before conducting them in the real world.
“Moving forward, we’re excited about this because we want to design experiments for mice and humans that test new questions, for example, what odor experience will best improve smell detection skills, and is supervised learning necessary for improvement?” Murthy said. “The computer algorithms used in our work can generate strong hypotheses for testing.”
About the Researcher

Professor Venkatesh Murthy performs experiments on the brain to identify olfactory receptors. Staff Photo Matt Craig/Harvard University News Office

Professor Venkatesh Murthy Staff – Photo Matt Craig/Harvard University News Office


Venkatesh N. Murthy a  professor of molecular and cellular biology at Harvard University, performs experiments on the brain to identify olfactory receptors.
Murthy Lab
Department of Molecular and Cellular Biology, Harvard University
Center for Brain Science, Harvard University
Program in Neuroscience, Harvard University
Program in Biophysics, Harvard University

Publication

Alexander Mathis, Dan Rokni, Vikrant Kapoor, Matthias Bethge, Venkatesh N. Murthy (2016) Reading Out Olfactory Receptors: Feedforward Circuits Detect Odors in Mixtures without Demixing. Neuron first published September, 7, 2016, doi: 10.1016/j.neuron.2016.08.007
Story Image: Olfactory sensory neurons (green) and astrocytes (red) – Image courtesy: Murthy Lab

Research projects

A Future of Unmanned Aerial Vehicles
Yale Budget Lab
Volcanic Eruptions Impact on Stratospheric Chemistry & Ozone
The Rhode Island Coastal Hazards Analysis, Modeling, and Prediction System
Towards a Whole Brain Cellular Atlas
Tornado Path Detection
The Kempner Institute – Unlocking Intelligence
The Institute for Experiential AI
Taming the Energy Appetite of AI Models
Surface Behavior
Studying Highly Efficient Biological Solar Energy Systems
Software for Unreliable Quantum Computers
Simulating Large Biomolecular Assemblies
SEQer – Sequence Evaluation in Realtime
Revolutionizing Materials Design with Computational Modeling
Remote Sensing of Earth Systems
QuEra at the MGHPCC
Quantum Computing in Renewable Energy Development
Pulling Back the Quantum Curtain on ‘Weyl Fermions’
New Insights on Binary Black Holes
NeuraChip
Network Attached FPGAs in the OCT
Monte Carlo eXtreme (MCX) – a Physically-Accurate Photon Simulator
Modeling Hydrogels and Elastomers
Modeling Breast Cancer Spread
Measuring Neutrino Mass
Investigating Mantle Flow Through Analyses of Earthquake Wave Propagation
Impact of Marine Heatwaves on Coral Diversity
IceCube: Hunting Neutrinos
Genome Forecasting
Global Consequences of Warming-Induced Arctic River Changes
Fuzzing the Linux Kernel
Exact Gravitational Lensing by Rotating Black Holes
Evolution of Viral Infectious Disease
Evaluating Health Benefits of Stricter US Air Quality Standards
Ephemeral Stream Water Contributions to US Drainage Networks
Energy Transport and Ultrafast Spectroscopy Lab
Electron Heating in Kinetic-Alfvén-Wave Turbulence
Discovering Evolution’s Master Switches
Dexterous Robotic Hands
Developing Advanced Materials for a Sustainable Energy Future
Detecting Protein Concentrations in Assays
Denser Environments Cultivate Larger Galaxies
Deciphering Alzheimer’s Disease
Dancing Frog Genomes
Cyber-Physical Communication Network Security
Avoiding Smash Hits
Analyzing the Gut Microbiome
Adaptive Deep Learning Systems Towards Edge Intelligence
Accelerating Rendering Power
ACAS X: A Family of Next-Generation Collision Avoidance Systems
Neurocognition at the Wu Tsai Institute, Yale
Computational Modeling of Biological Systems
Computational Molecular Ecology
Social Capital and Economic Mobility
All Research Projects

Collaborative projects

ALL Collaborative PROJECTS

Outreach & Education Projects

See ALL Scholarships
100 Bigelow Street, Holyoke, MA 01040