LA JOLLA--(October 7, 2019) Father of genetics Gregor Mendel spent years tediously observing and measuring pea plant traits by hand in the 1800s to uncover the basics of genetic inheritance. Today, botanists can track the traits, or phenotypes, of hundreds or thousands of plants much more quickly, with automated camera systems. Now, Salk researchers have helped speed up plant phenotyping even more, with machine-learning algorithms that teach a computer system to analyze three-dimensional shapes of the branches and leaves of a plant. The study, published in Plant Physiology on October 7, 2019, may help scientists better quantify how plants respond to climate change, genetic mutations or other factors. "What we've done is develop a suite of tools that helps address some common phenotyping challenges," says Saket Navlakha, an associate professor in Salk's Integrative Biology Laboratory and Pioneer Fund Developmental Chair.

We propose a new class of data-independent locality-sensitive hashing (LSH) algorithms based on the fruit fly olfactory circuit. The fundamental difference of this approach is that, instead of assigning hashes as dense points in a low dimensional space, hashes are assigned in a high dimensional space, which enhances their separability. We show theoretically and empirically that this new family of hash functions is locality-sensitive and preserves rank similarity for inputs in any `p space. We then analyze different variations on this strategy and show empirically that they outperform existing LSH methods for nearest-neighbors search on six benchmark datasets. Finally, we propose a multi-probe version of our algorithm that achieves higher performance for the same query time, or conversely, that maintains performance of prior approaches while taking significantly less indexing time and memory. Overall, our approach leverages the advantages of separability provided by high-dimensional spaces, while still remaining computationally efficient

Today's artificial intelligence systems, including the artificial neural networks broadly inspired by the neurons and connections of the nervous system, perform wonderfully at tasks with known constraints. They also tend to require a lot of computational power and vast quantities of training data. That all serves to make them great at playing chess or Go, at detecting if there's a car in an image, at differentiating between depictions of cats and dogs. "But they are rather pathetic at composing music or writing short stories," said Konrad Kording, a computational neuroscientist at the University of Pennsylvania. "They have great trouble reasoning meaningfully in the world." Original story reprinted with permission from Quanta Magazine, an editorially independent publication of the Simons Foundation whose mission is to enhance public understanding of science by covering research developments and trends in mathematics and the physical and life sciences.

Today's artificial intelligence systems, including the artificial neural networks broadly inspired by the neurons and connections of the nervous system, perform wonderfully at tasks with known constraints. They also tend to require a lot of computational power and vast quantities of training data. That all serves to make them great at playing chess or Go, at detecting if there's a car in an image, at differentiating between depictions of cats and dogs. "But they are rather pathetic at composing music or writing short stories," said Konrad Kording, a computational neuroscientist at the University of Pennsylvania. "They have great trouble reasoning meaningfully in the world." To overcome those limitations, some research groups are turning back to the brain for fresh ideas.

Researchers have identified an incredibly smart method used by fruit flies to categorise odours – and it's so clever it could be applied to powering recommendation algorithms for the likes of Netflix or Spotify. In the same way that YouTube might want to flag up videos similar to the one you've just watched, fruit flies – like many other animals – need to know which smells are similar, for finding food and avoiding poisonous substances. The team from the University of California San Diego (UCSD) and the Salk Institute for Biological Studies in California has found that fruit flies have an especially clever way of categorising odours which lets them recognise differences with a very fine level of accuracy. "In the natural world, you're not going to encounter exactly the same odour every time; there's going to be some noise and fluctuation," says one of the researchers, Saket Navlakha from Salk. "But if you smell something that you've previously associated with a behaviour, you need to be able to identify that similarity and recall that behaviour."

What do a fruit fly and a search engine have in common? Search engine algorithms go through great pains to match items you've clicked on or purchased, songs you've listened to, or things searched for, to similar ones. As a result, we constantly need ever faster and more efficient search engines, and so computer scientists must work tirelessly to keep up. They have to constantly tackle what they call "a fundamental machine learning problem: approximate similarity (or nearest-neighbors) search." Turns out, fruit fly brains go through a similar matching process, and the way they do it is fast, efficient, and dare I say, elegant.

Ask, and it shall be given you; seek, and ye shall find; knock, and it shall be opened unto you." Verse 7:7 from the Gospel of Matthew is generally considered to be a comment on prayer, but it could just as well be about the power of search. Search has become one of the key technologies of the information age, powering industry behemoths and helping us with our daily chores. But that's not where it ends. Scientists are starting to understand that search powers much of the natural world, too. Saket Navlakha, of the Salk Institute for Biological Studies, works at the "interface of theoretical computer science, machine learning, and systems biology," a field, he told me, that he and his colleagues are calling "algorithms in nature." Evolution needs algorithms just as software engineers do, Navlakha says, because it "has also had to deal with building efficient, reliable, low-cost systems that help animals and organisms survive." His hope is to find in nature "new ideas and new engineering principles" that can be exploited by human scientists and engineers. In a study published on Friday, Navlakha and a couple colleagues, Sanjoy Dasgupta and Charles F. Stevens, did just that. They found that the fruit fly brain had some valuable lessons for anyone developing similarity search algorithms. Stevens had been studying fly neural circuits, specifically how they associate different behaviors, like approach or avoidance, with odors in the environment. "When he started telling me about it," Navlakha says, "I realized that what the fly needs to do is do something like a similarity search.