MIT researchers have developed a neural liquid network that varies its equations’ parameters, enhancing its ability to analyze time series data
Image: Jose Luis Olivares MIT
The new type of neural network could aid decision making in autonomous driving and medical diagnosis.
MIT researchers have developed a type of neural network that learns on the job, not just during its training phase. These flexible algorithms, dubbed “liquid” networks, change their underlying equations to continuously adapt to new data inputs. The advance could aid decision making based on data streams that change over time, including those involved in medical diagnosis and autonomous driving.
“This is a way forward for the future of robot control, natural language processing, video processing — any form of time series data processing,” says Ramin Hasani, the study’s lead author. “The potential is really significant.”
The research will be presented at February’s AAAI Conference on Artificial Intelligence. In addition to Hasani, a postdoc in the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL), MIT co-authors include Daniela Rus, CSAIL director and the Andrew and Erna Viterbi Professor of Electrical Engineering and Computer Science, and PhD student Alexander Amini. Other co-authors include Mathias Lechner of the Institute of Science and Technology Austria and Radu Grosu of the Vienna University of Technology.
Time series data are both ubiquitous and vital to our understanding the world, according to Hasani. “The real world is all about sequences. Even our perception — you’re not perceiving images, you’re perceiving sequences of images,” he says. “So, time series data actually create our reality.”
He points to video processing, financial data, and medical diagnostic applications as examples of time series that are central to society. The vicissitudes of these ever-changing data streams can be unpredictable. Yet analyzing these data in real time, and using them to anticipate future behavior, can boost the development of emerging technologies like self-driving cars. So Hasani built an algorithm fit for the task.
Hasani designed a neural network that can adapt to the variability of real-world systems. Neural networks are algorithms that recognize patterns by analyzing a set of “training” examples. They’re often said to mimic the processing pathways of the brain — Hasani drew inspiration directly from the microscopic nematode, C. elegans. “It only has 302 neurons in its nervous system,” he says, “yet it can generate unexpectedly complex dynamics.”
Hasani coded his neural network with careful attention to how C. elegans neurons activate and communicate with each other via electrical impulses. In the equations he used to structure his neural network, he allowed the parameters to change over time based on the results of a nested set of differential equations.
This flexibility is key. Most neural networks’ behavior is fixed after the training phase, which means they’re bad at adjusting to changes in the incoming data stream. Hasani says the fluidity of his “liquid” network makes it more resilient to unexpected or noisy data, like if heavy rain obscures the view of a camera on a self-driving car. “So, it’s more robust,” he says.
There’s another advantage of the network’s flexibility, he adds: “It’s more interpretable.”
Hasani says his liquid network skirts the inscrutability common to other neural networks. “Just changing the representation of a neuron,” which Hasani did with the differential equations, “you can really explore some degrees of complexity you couldn’t explore otherwise.” Thanks to Hasani’s small number of highly expressive neurons, it’s easier to peer into the “black box” of the network’s decision making and diagnose why the network made a certain characterization.
“The model itself is richer in terms of expressivity,” says Hasani. That could help engineers understand and improve the liquid network’s performance.
Hasani’s network excelled in a battery of tests. It edged out other state-of-the-art time series algorithms by a few percentage points in accurately predicting future values in datasets, ranging from atmospheric chemistry to traffic patterns. “In many applications, we see the performance is reliably high,” he says. Plus, the network’s small size meant it completed the tests without a steep computing cost. “Everyone talks about scaling up their network,” says Hasani. “We want to scale down, to have fewer but richer nodes.”
Hasani plans to keep improving the system and ready it for industrial application. “We have a provably more expressive neural network that is inspired by nature. But this is just the beginning of the process,” he says. “The obvious question is how do you extend this? We think this kind of network could be a key element of future intelligence systems.”
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
Liquid neural network
- Top Stocks To Buy Now? 4 Renewable Energy Stocks For Your Watchliston August 26, 2021 at 12:36 pm
Top Renewable Energy Stocks To Check Out In The Stock Market Today. When considering what stocks to buy today, investors may want to consider renewable energy stocks now. For th ...
- Optellum Announces Strategic Collaboration With The Lung Cancer Initiative At Johnson & Johnson, Applying AI To Transform Early Lung Cancer Treatmenton August 26, 2021 at 10:48 am
Legal Newswire POWERED BY LAW.COM Optellum, a lung-health AI company, has entered a strategic collaboration with the Lung Cancer Initiative at Johnson & Johnson*. Through the collaboration, Optellum ...
- J&J lung cancer initiative will use Optellum’s ‘digital biomarker’ techon August 26, 2021 at 5:29 am
UK artificial intelligence specialist Optellum joins J&J's Lung Cancer Initiative with Boston University, which aims to improve lung cancer survival rates through prevention and early intervention ...
- The boiling crisis and how to avoid iton August 25, 2021 at 12:13 pm
It's rare for a pre-teen to become enamored with thermodynamics, but those consumed by such a passion may consider themselves lucky to end up at a place like MIT. Madhumitha Ravichandran certainly ...
- Your Brain Is Not a Computer. It Is a Transduceron August 25, 2021 at 11:24 am
A new theory of how the brain works — neural transduction theory — might upend everything we know about consciousness and the universe itself.
Go deeper with Google Headlines on:
Liquid neural network
Go deeper with Bing News on:
- Liquid creates direct internet access from Africa to USA via new POP connection to Miamion August 26, 2021 at 8:23 am
African businesses and consumers will now be able to benefit from a direct connection to the USA as Liquid Intelligent Technologies opens an Internet Point of Presence in Miami, connecting to the ...
- New Liquid POP links Africa directly to USA internet resourceson August 26, 2021 at 3:27 am
Liquid Intelligent Technologies is opening a new Internet Point of Presence in Miami that will connect to its African network via the South Atlantic SACS and MONET subsea cables.
- Liquid Intelligent Technologies creates direct access to USA internet resources via a new POP connection to Miamion August 26, 2021 at 1:01 am
African businesses and consumers will now be able to benefit from a direct connection to the USA as Liquid Intelligent Technologies ( opens an Internet Point of Presence in Miami, connecting to the ...
- Cyber Attack on Crypto Exchange Liquid Results in Loss of $97 Million in Ethereum Tokens and Other Assetson August 25, 2021 at 9:00 am
Crypto exchange Liquid, one Japan's most popular exchanges, is now short $97 million in total assets after a cyber attack that pulled funds directly from the wallets of some of its customers.
- Wyoming data center adopts Submer liquid cooling and Lumen networkon August 25, 2021 at 5:04 am
Wyoming Hyperscale has adopted Submer liquid cooling, and signed for networking from Lumen (formerly CenturyLink), in a bid to create an efficient hyperscale data center in a remote stretch of ...