Rice U. expert: Key is creating ML systems that question their own predictions
Rice University statistician Genevera Allen says scientists must keep questioning the accuracy and reproducibility of scientific discoveries made by machine-learning techniques until researchers develop new computational systems that can critique themselves.
Allen, associate professor of statistics, computer science and electrical and computer engineering at Rice and of pediatrics-neurology at Baylor College of Medicine, will address the topic in both a press briefing and a general session today at the 2019 Annual Meeting of the American Association for the Advancement of Science (AAAS).
“The question is, ‘Can we really trust the discoveries that are currently being made using machine-learning techniques applied to large data sets?’” Allen said. “The answer in many situations is probably, ‘Not without checking,’ but work is underway on next-generation machine-learning systems that will assess the uncertainty and reproducibility of their predictions.”
Machine learning (ML) is a branch of statistics and computer science concerned with building computational systems that learn from data rather than following explicit instructions. Allen said much attention in the ML field has focused on developing predictive models that allow ML to make predictions about future data based on its understanding of data it has studied.
“A lot of these techniques are designed to always make a prediction,” she said. “They never come back with ‘I don’t know,’ or ‘I didn’t discover anything,’ because they aren’t made to.”
She said uncorroborated data-driven discoveries from recently published ML studies of cancer data are a good example.
“In precision medicine, it’s important to find groups of patients that have genomically similar profiles so you can develop drug therapies that are targeted to the specific genome for their disease,” Allen said. “People have applied machine learning to genomic data from clinical cohorts to find groups, or clusters, of patients with similar genomic profiles.
“But there are cases where discoveries aren’t reproducible; the clusters discovered in one study are completely different than the clusters found in another,” she said. “Why? Because most machine-learning techniques today always say, ‘I found a group.’ Sometimes, it would be far more useful if they said, ‘I think some of these are really grouped together, but I’m uncertain about these others.’”
The Latest on: Machine-learning discoveries
via Google News
The Latest on: Machine-learning discoveries
- DeepMind’s improved protein-folding prediction AI could accelerate drug discoveryon November 30, 2020 at 3:30 pm
DeepMind claims that its AI system, AlphaFold, is among the most accurate with respect to protein folding predictions.
- Google's DeepMind solved a mystery about protein behavior that's puzzled scientists for 50 years, and it could revolutionize drug discoveryon November 30, 2020 at 10:25 am
has announced a scientific breakthrough which could have a major influence on drug discovery and disease research. The company's AI program AlphaFold brought together experts from a variety of fields ...
- Global Cognitive Systems, Content Analytics and Discovery Software Industryon November 30, 2020 at 6:20 am
Amid the COVID-19 crisis, the global market for Cognitive Systems, Content Analytics and Discovery Software estimated at US$17.9 Billion in the year 2020, is projected to reach a revised size of US$65 ...
- World’s largest proteomics centre accelerates biomarker discoveries to improve people’s liveson November 30, 2020 at 4:06 am
Manchester’s Stoller Biomarker Discovery Centre (SBDC) is a globally renowned, multi-million-pound precision medicine research facility.
- AI for Drug Discovery Market Application, Region, Global Growth, Trends, and Forecast To 2027on November 29, 2020 at 3:04 am
The report covers the forecast and analysis of the AI for drug discovery market on a global and regional level. The study provides historical data from 2015 to 2018 along with a forecast from 2019 to ...
- Lantern: Early Stage 'Smart Drug' Discovery Companyon November 25, 2020 at 2:46 pm
Lantern works at the intersection of Artificial Intelligence, Genomics, and Machine Learning. It discovers novel oncology assets using its platform.
- SMi’s 2nd Annual AI in Drug Discovery Announces Key Industry Speakers and Agenda Releasedon November 22, 2020 at 1:57 am
SMi’s Group is proud to announce the 2nd Annual AI in Drug Discovery Conference is back and taking place on 15th and 16th March 2021 as a virtual conference with online access only and sponsored by ...
- Before machine learning can become ubiquitous, here are four things we need to do nowon November 20, 2020 at 10:56 am
Now, as we enter the golden age of machine learning, we can expect a similar boom of benefits that previously seemed impossible. Machine learning is already helping companies make better and faster ...
- Keeping Machine Learning Algorithms Honest in the ‘Ethics-First’ Eraon November 19, 2020 at 4:57 am
Today in so many industries, from manufacturing and life sciences to financial services and retail, we rely on algorithms to conduct large-scale machine learning analysis. They are hugely effective ...
- Machine learning innovation to develop chemical library for drug discoveryon November 18, 2020 at 1:11 am
Machine learning has been used widely in the chemical sciences for drug design and other processes. The models that are prospectively tested for new reaction outcomes and used to enhance human ...
via Bing News