The team tested their new neural network on an important task: keeping self-driving cars in their lanes. Credit: Ramin Hasani
Artificial intelligence (AI) can become more efficient and reliable if it is made to mimic biological models. New approaches in AI research are hugely successful in experiments.
Artificial intelligence has arrived in our everyday lives—from search engines to self-driving cars. This has to do with the enormous computing power that has become available in recent years. But new results from AI research now show that simpler, smaller neural networks can be used to solve certain tasks even better, more efficiently, and more reliably than ever before.
An international research team from TU Wien (Vienna), IST Austria and MIT (USA) has developed a new artificial intelligence system based on the brains of tiny animals, such as threadworms. This novel AI-system can control a vehicle with just a few artificial neurons. The team says that system has decisive advantages over previous deep learning models: It copes much better with noisy input, and, because of its simplicity, its mode of operation can be explained in detail. It does not have to be regarded as a complex “black box”, but it can be understood by humans. This new deep learning model has now been published in the journal Nature Machine Intelligence.
Learning from nature
Similar to living brains, artificial neural networks consist of many individual cells. When a cell is active, it sends a signal to other cells. All signals received by the next cell are combined to decide whether this cell will become active as well. The way in which one cell influences the activity of the next determines the behavior of the system—these parameters are adjusted in an automatic learning process until the neural network can solve a specific task.
“For years, we have been investigating what we can learn from nature to improve deep learning,” says Prof. Radu Grosu, head of the research group “Cyber-Physical Systems” at TU Wien. “The nematode C. elegans, for example, lives its life with an amazingly small number of neurons, and still shows interesting behavioral patterns. This is due to the efficient and harmonious way the nematode’s nervous system processes information.”
“Nature shows us that there is still lots of room for improvement,” says Prof. Daniela Rus, director of MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL). “Therefore, our goal was to massively reduce complexity and enhance interpretability of neural network models.”
“Inspired by nature, we developed new mathematical models of neurons and synapses,” says Prof. Thomas Henzinger, president of IST Austria.
“The processing of the signals within the individual cells follows different mathematical principles than previous deep learning models,” says Dr. Ramin Hasani, postdoctoral associate at the Institute of Computer Engineering, TU Wien and MIT CSAIL. “Also, our networks are highly sparse—this means that not every cell is connected to every other cell. This also makes the network simpler.”
Autonomous Lane Keeping
To test the new ideas, the team chose a particularly important test task: self-driving cars staying in their lane. The neural network receives camera images of the road as input and is to decide automatically whether to steer to the right or left.
“Today, deep learning models with many millions of parameters are often used for learning complex tasks such as autonomous driving,” says Mathias Lechner, TU Wien alumnus and PhD student at IST Austria. “However, our new approach enables us to reduce the size of the networks by two orders of magnitude. Our systems only use 75,000 trainable parameters.”
Alexander Amini, PhD student at MIT CSAIL explains that the new system consists of two parts: The camera input is first processed by a so-called convolutional neural network, which only perceives the visual data to extract structural features from incoming pixels. This network decides which parts of the camera image are interesting and important, and then passes signals to the crucial part of the network – a “control system” that then steers the vehicle.
Both subsystems are stacked together and are trained simultaneously. Many hours of traffic videos of human driving in the greater Boston area were collected, and are fed into the network, together with information on how to steer the car in any given situation—until the system has learned to automatically connect images with the appropriate steering direction and can independently handle new situations.
The control part of the system (called neural circuit policy, or NCP), which translates the data from the perception module into a steering command, only consists of 19 neurons. Mathias Lechner explains that NCPs are up to 3 orders of magnitude smaller than what would have been possible with previous state-of-the-art models.
Causality and Interpretability
The new deep learning model was tested on a real autonomous vehicle. “Our model allows us to investigate what the network focuses its attention on while driving. Our networks focus on very specific parts of the camera picture: The curbside and the horizon. This behavior is highly desirable, and it is unique among artificial intelligence systems,” says Ramin Hasani. “Moreover, we saw that the role of every single cell at any driving decision can be identified. We can understand the function of individual cells and their behavior. Achieving this degree of interpretability is impossible for larger deep learning models.”
“To test how robust NCPs are compared to previous deep models, we perturbed the input images and evaluated how well the agents can deal with the noise,” says Mathias Lechner. “While this became an insurmountable problem for other deep neural networks, our NCPs demonstrated strong resistance to input artifacts. This attribute is a direct consequence of the novel neural model and the architecture.”
“Interpretability and robustness are the two major advantages of our new model,” says Ramin Hasani. “But there is more: Using our new methods, we can also reduce training time and the possibility to implement AI in relatively simple systems. Our NCPs enable imitation learning in a wide range of possible applications, from automated work in warehouses to robot locomotion. The new findings open up important new perspectives for the AI community: The principles of computation in biological nervous systems can become a great resource for creating high-performance interpretable AI—as an alternative to the black-box machine learning systems we have used so far.”
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
- Deep Learning Goes to Boot Camp: The U.S. Army wants to Team Humans and Robots on the Battlefield
I should probably not be standing this close,” I think to myself, as the robot slowly approaches a large tree branch on the floor in front of me. It's not the size of the branch that makes me ...
- Deep Learning's Diminishing Returns: The Cost of Improvement is Becoming Unsustainable
Deep learning is now being used to translate between languages, predict how proteins fold, analyze medical scans, and play games as complex as Go, to name just a few applications of a technique that ...
- Cognex VisionPro Software Breaks Down Barriers Between Deep Learning and Traditional Vision
VisionPro 10.0 and VisionPro Deep Learning 2.0 are two new releases in the VisionPro line of vision software from Cognex.
- Deep Learning Market Valuations and Expected Future Returns by 2027
Portland United States Global Deep Learning Market gives comprehensive research offering detailed regional analysis and growth outlook The Deep Learning market forecast 2021 2027 report highlight the ...
- Deep Learning Software Market is Booming Worldwide with IBM, Microsoft, Nvidia
The global Deep Learning Software market focuses on encompassing major statistical evidence for the Deep Learning Software industry as it offers our readers a value addition on guiding them in ...
Go deeper with Google Headlines on:
Go deeper with Bing News on:
- Scientists Map Brain Circuit That Drives Activity in Fertile Females
Mouse study identifies specific neurons and a signaling pathway to regions of the hindbrain that mediate sexual reproductive activity and physical activity that appear to influence activity behaviors ...
- Plaque-induced neurite abnormalities: Implications for disruption of neural networks in Alzheimer’s disease
The brains of Alzheimer’s disease patients contain extracellular Aβ amyloid deposits (senile plaques). Although genetic evidence causally links Aβ deposition to the disease, the mechanism by which Aβ ...
- Locally produced neurosteroids regulate the emerging reproductive neural circuitry in the embryonic mouse brain
The onset of puberty, the developmental stage at which adolescents reach sexual maturity, is known to be associated with the activity of a specific class of neurons, namely gonadotropin-releasing ...
- Neural Networks: What they are, and why they might be vital to AML
A twenty-first-century arms race – that’s how some scholars and financial publications describe the efforts of regulatory bodies and financial criminals to stay ahead of each other. On one hand, ...
- These neural networks know what they’re doing
MIT researchers have demonstrated that a special class of deep learning neural networks is able to learn the true cause-and-effect structure of a navigation task during training.