
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
- 20S proteasomes secreted by the malaria parasite promote its growthon February 19, 2021 at 8:06 am
Plasmodium falciparum secretes extracellular vesicles (EVs) while growing inside red blood cells (RBCs). Here the authors show that these EVs contain assembled and functional 20S proteasome complexes ...
- Machine learning identifies candidates for drug repurposing in Alzheimer’s diseaseon February 15, 2021 at 2:34 am
Clinical trials of novel therapeutics for Alzheimer’s Disease (AD) have provided largely negative results, so far. Here, the authors present a machine learning framework that quantifies potential ...
- Artificial Brain Gives Robots Unprecedented Sensing Capabilitieson February 11, 2021 at 4:00 pm
They tasked a robot equipped with both artificial skin and vision sensors to classify various opaque containers containing differing amounts of liquid. They also tested ... In both tests, the spiking ...
- A new framework for robotics applications that merges reservoir computing with origamion February 11, 2021 at 4:00 pm
Reservoir computing is a highly promising computational framework based on artificial recurrent neural networks (RNNs). Over the past few years, this framework was successfully applied to a variety of ...
- Women in Science 2021on February 11, 2021 at 1:33 am
Download this eBook to explore various methods used to study the neural transcriptome, how gene expression analysis can provide detailed information about the central nervous system and how single ...
Go deeper with Google Headlines on:
Liquid neural network
Go deeper with Bing News on:
Liquid network
- Heranba Industrieson February 22, 2021 at 7:47 pm
The company also manufacture and sell general insect control chemicals to governmental authorities like municipalities by participating in public health tenders issued by them and to pest management ...
- 'More valuable than liquid gold': Pharmacists propose a simple solution to vaccine shortageson February 22, 2021 at 3:37 pm
The FDA says leftover Covid-19 vaccine cannot be combined because neither Moderna nor Pfizer’s products contain preservatives to prevent contamination.
- Liquid Telecommunications bond offering is fourth recent digital and telecommunications financing by PIDG company Emerging Africa Infrastructure Fundon February 22, 2021 at 4:41 am
The Emerging Africa Infrastructure Fund (EAIF), a Private Infrastructure Development Group (PIDG) ( company, has committed to buy up to US$50,000,000 of a bond issue by ...
- From ‘liquid to lips’: Black-owned Lehigh Valley distiller Russell Fletcher looks to grow in Pa. and beyondon February 22, 2021 at 4:10 am
"The goal is for the product to be a focus,” says Russell Fletcher II, owner of Mishka Premium Vodka made in Allentown ...
- Spirit, Liquid secure semifinals spots in IEM Worlds playoffson February 21, 2021 at 5:04 pm
Team Spirit and Team Liquid each won their upper-bracket round-three group finals on Sunday to advance straight to the semifinals of the Intel Extreme Masters ...