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
- Researchers Use Artificial Intelligence Supported Neural Networks To Reason Like The Human Brain
A neural network, a series of algorithms that strives to recognize underlying relationships in a set of given data with ...
- AI That Can Learn Cause-and-Effect: These Neural Networks Know What They’re Doing
A certain type of artificial intelligence agent can learn the cause-and-effect basis of a navigation task during training. Neural networks can learn to solve all sorts of problems, from identifying ...
- Cutting through the noise: AI enables high-fidelity quantum computing
More information: Yuta Matsumoto et al, Noise-robust classification of single-shot electron spin readouts using a deep neural network, npj Quantum Information (2021). DOI: 10.1038/s41534-021-00470-7 ...
- deep learning
At the molecular level, glass looks like a liquid. But an artificial neural network has picked up on hidden structure in its molecules that may explain why glass is rigid like a solid. The problem of ...
- Network Dynamics Underlying the Formation of Sparse, Informative Representations in the Hippocampus
During development, activity-dependent processes increase the specificity of neural responses to stimuli, but the role that this type of process plays in adult plasticity is unclear. We examined the ...
Go deeper with Google Headlines on:
Liquid neural network
Go deeper with Bing News on:
- Liquid Avatar Technologies Named Digital Innovation Partner for L.A. Comic Con (December 3-5, 2021)
Liquid Avatar Technologies Inc. (CSE:LQID) / (OTC:LQAVF) / (FRA:4T51) / (CNSX:LQID.CN), a global blockchain, digital identity and fintech solutions company, today announces that Liquid Avatar will be ...
- Lucence and Yemaachi Launch the AMBER Study to Detect and Characterize Genomic Alterations in Breast Cancer in Women in Africa and Expand Liquid Biops
Companies’ work part of a long-term commitment to diversifying clinical trials and expanding access to precision diagnostics globallyPALO ALTO, Calif. & ACCRA, Ghana--(BUSINESS ...
- Liquid Intelligent scoops top regional accolade
PAN-African telecommunications group, Liquid Intelligent Technologies, has been named the Best African Wholesale Carrier for the 10th-year running at the Global Carrier Awards ceremony held in London ...
- The Role of White Label Cryptocurrency Exchange Providers In Making the $2 Trillion Industry More Liquid
The cryptocurrency market is now valued at over $2 trillion. Bitcoin is the most dominant, controlling roughly 50 percent of the sphere’s valuation. Q3 2021 hedge fund letters, conferences ...
- Liquid Media’s iNDIEFLIX Provides Statewide Edutainment Programming to Help Address Mental ...
Liquid Media Group Ltd. (the “Company,” “Liquid Media” or “Liquid”) (Nasdaq: YVR) today announced a partnership between iNDIEFLIX, now a member of the Liquid Media Group family of companies, the ...