Prof. Dion Vlachos (left), director of UD’s Catalysis Center for Energy Innovation, and Joshua Lansford, a doctoral student in UD’s Department of Chemical and Biomolecular Engineering, are co-authors on the paper recently published in the journal Science Advances.
UD’s Vlachos and Lansford develop high-confidence approach for artificial intelligence-based models
They call it artificial intelligence — not because the intelligence is somehow fake. It’s real intelligence, but it’s still made by humans. That means AI — a power tool that can add speed, efficiency, insight and accuracy to a researcher’s work — has many limitations.
It’s only as good as the methods and data it has been given. On its own, it doesn’t know if information is missing, how much weight to give differing kinds of information or whether the data it draws on is incorrect or corrupted. It can’t deal precisely with uncertainty or random events — unless it learns how. Relying exclusively on data, as machine-learning models usually do, it does not leverage the knowledge experts have accumulated over years and physical models underpinning physical and chemical phenomena. It has been hard to teach the computer to organize and integrate information from widely different sources.
Now researchers at the University of Delaware and the University of Massachusetts-Amherst have published details of a new approach to artificial intelligence that builds uncertainty, error, physical laws, expert knowledge and missing data into its calculations and leads ultimately to much more trustworthy models. The new method provides guarantees typically lacking from AI models, showing how valuable — or not — the model can be for achieving the desired result.
Joshua Lansford, a doctoral student in UD’s Department of Chemical and Biomolecular Engineering, and Prof. Dion Vlachos, director of UD’s Catalysis Center for Energy Innovation, are co-authors on the paper published Oct. 14 in the journal Science Advances. Also contributing were Jinchao Feng and Markos Katsoulakis of the Department of Mathematics and Statistics at the University of Massachusetts-Amherst.
The new mathematical framework could produce greater efficiency, precision and innovation for computer models used in many fields of research. Such models provide powerful ways to analyze data, study materials and complex interactions and tweak variables in virtual ways instead of in the lab.
“Traditionally in physical modelings, we build a model first using only our physical intuition and expert knowledge about the system,” Lansford said. “Then after that, we measure uncertainty in predictions due to error in underlying variables, often relying on brute-force methods, where we sample, then run the model and see what happens.”
Effective, accurate models save time and resources and point researchers to more efficient methods, new materials, greater precision and innovative approaches they might not otherwise consider.
The paper describes how the new mathematical framework works in a chemical reaction known as the oxygen reduction reaction, but it is applicable to many kinds of modeling, Lansford said.
“The chemistries and materials we need to make things faster or even make them possible — like fuel cells — are highly complex,” he said. “We need precision…. And if you want to make a more active catalyst, you need to have bounds on your prediction error. By intelligently deciding where to put your efforts, you can tighten the area to explore.
“Uncertainty is accounted for in the design of our model,” Lansford said. “Now it is no longer a deterministic model. It is a probabilistic one.”
With these new mathematical developments in place, the model itself identifies what data are needed to reduce model error, he said. Then a higher level of theory can be used to produce more accurate data or more data can be generated, leading to even smaller error boundaries on the predictions and shrinking the area to explore.
“Those calculations are time-consuming to generate, so we’re often dealing with small datasets — 10-15 data points. That’s where the need comes in to apportion error.”
That’s still not a money-back guarantee that using a specific substance or approach will deliver precisely the product desired. But it is much closer to a guarantee than you could get before.
This new method of model design could greatly enhance work in renewable energy, battery technology, climate change mitigation, drug discovery, astronomy, economics, physics, chemistry and biology, to name just a few examples.
Artificial intelligence doesn’t mean human expertise is no longer needed. Quite the opposite.
The expert knowledge that emerges from the laboratory and the rigors of scientific inquiry is essential, foundational material for any computational model.
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
Artificial intelligence-based models
- In network transformation push, Mavenir adds webscale platform, MEC, AI analyticson January 11, 2021 at 12:08 pm
Cloud-native 5G is all about efficiently delivering new, monetizable services; Mavenir is chasing this opportunity with a new product suite.
- Opening the black box: AI, appliedon January 11, 2021 at 11:00 am
In the accounting profession, there is a similar uneasiness when dealing with the idea of AI, though it has nothing to with how the software looks. The technology has the potential for high-level ...
- Roche launches two digital pathology image analysis algorithms for precision patient diagnosis in breast canceron January 10, 2021 at 10:03 pm
Path HER2 (4B5) image analysis and uPath Dual ISH image analysis aid pathologists in providing faster, more accurate patient diagnoses in breast cancer In combination with ...
- Top 25 Machine Learning Startups To Watch In 2021 Based On Crunchbaseon January 10, 2021 at 8:36 pm
Throughout 2020, venture capital firms continued expanding into new global markets, with London, New York, Tel Aviv, Toronto, Boston, Seattle and Singapore startups receiving increased funding.
- OPPO to launch MediaTek Dimensity 1000+ SoC powered Reno 5 Pro 5G on Jan 18on January 4, 2021 at 10:38 pm
OPPO Reno 5 Pro 5G will bring live HDR and ultra-night video features, which will be part of the phone's industry-first artificial intelligence-based 'AI Highlight Video' feature ...
Go deeper with Google Headlines on:
Artificial intelligence-based models
Go deeper with Bing News on:
- Data and Artificial Intelligence: The Only Way is Ethicson January 14, 2021 at 10:16 am
In the third episode of Data Capital, we examine the thorny issue of how to ensure data and artificial intelligence (AI) are used effectively - but not abused.
- Feces and algorithms: Artificial Intelligence to map our intestinal bacteriaon January 14, 2021 at 9:45 am
Both past and present-day scientists have suspected the intestines of playing a role in various diseases. Present-day studies focus on the intestinal flora's role in physical diseases such as diabetes ...
- Ping An Uses Artificial Intelligence to Drive New ESG Investment Strategieson January 14, 2021 at 9:41 am
Access to data from alternative sources can uncover hidden risks and opportunities PR Newswire HONG KON ...
- Machine Learning and Artificial Intelligence Integration Drives the Growth of the Global Natural Language Processing Market at a CAGR of 18.4%on January 14, 2021 at 7:15 am
In 2019, the global natural language processing market reached USD 9.2 Billion and it is expected to grow at a ...
- Humans won't be able to control artificial intelligence, scientists warnon January 13, 2021 at 10:43 am
Some smart robots can perform complex tasks on their own, without the programmers understanding how they learned them.