Monday, September 24, 2018

How Brains understand to Smell


Unlike images, odours are unstructured, ill-defined things. What neuroscientists are learning about the olfactory system could help computer scientists develop new, more powerful machine learning algorithms.
Now, teams of scientists have developed a deep learning method that smells compounds in the human breath and detects illnesses. The AI can detect 17 diseases, including 8 different types of cancer, just from your breath. This AI is cable of recognizing chemical signatures of the diseases by their chemical structure.







Random and Sparse Networks

Olfaction differs from the vision on many fronts. Smells are unstructured. They don’t have edges; they’re not objects that can be grouped in space. They’re mixtures of varying compositions and concentrations, and they’re difficult to categorize as similar to or different from one another. It’s therefore not always clear which features should get attention.

These odours are analyzed by a shallow, three-layer network that’s considerably less complex than the visual cortex. Neurons in olfactory areas randomly sample the entire receptor space, not specific regions in a hierarchy. They employ what Charles Stevens, a neurobiologist at the Salk Institute, calls an “anti-map.” In a mapped system like the visual cortex, the position of a neuron reveals something about the type of information it carries. But in the anti-map of the olfactory cortex, that’s not the case. Instead, information is distributed throughout the system, and reading that data involves sampling from some minimum number of neurons. An anti-map is achieved through what’s known as a sparse representation of information in a higher dimensional space.

Take the olfactory circuit of the fruit fly: 50 projection neurons receive input from receptors that are each sensitive to different molecules. A single odour will excite many different neurons, and each neuron represents a variety of odours. It’s a mess of information, of overlapped representations, that is at this point represented in a 50-dimensional space. The information is then randomly projected to 2,000 so-called Kenyon cells, which encode particular scents. (In mammals, cells in what’s known as the piriform cortex handle this.) That constitutes a 40-fold expansion in dimension, which makes it easier to distinguish odours by the patterns of neural responses.
Cecile G. Tamura

No comments:

Post a Comment