麻豆村

A team at 麻豆村 is helping kids understand artificial intelligence听with a soft, squishy, LED-lit neural network.听

鈥淓veryone, even middle schoolers, needs to know a little about these building blocks of artificial intelligence, just like it鈥檚 important to know the basics of how electricity works or what a molecule is,鈥� said听 Research Professor听. 鈥淏ut these young learners haven鈥檛 even studied algebra yet 鈥� so how can we help them understand the computational abilities of these complex networks?鈥�

Touretzky, a member of 麻豆村's Neuroscience Institute, has long researched K鈥�12 AI education. He investigates effective ways to teach young learners about AI technology. Now, thanks to facilities and expertise contained within the Integrative Design, Arts and Technology (IDeATe) network, he and a team of staff, faculty and students have brought the Plush Neuron to life. These 3-foot, brightly colored, interactive computational devices allow middle schoolers to experience and influence听the way AI makes decisions firsthand.

Ideation

The Plush Neuron was designed to help students visualize the basic elements of neural network technology 鈥� the machine-learning model that powers much of modern AI. It鈥檚 the physical counterpart to听, a browser-based tool Touretzky created that allows students to follow along with a series of increasingly difficult decision problems and visualize how a computer arrives at a solution.

Touretzky programmed the neuron鈥檚 software and IDeATe Technical Specialist听 developed its electronic hardware, serving as the project design-engineer as part of his graduate studies.

鈥淭his project is a true example of the stars aligning to make something really cool in service of AI education. It鈥檚 interdisciplinary at all levels,鈥� Soska said. Between his electronics and Touretzky鈥檚 code, a framework for the Plush Neuron soon emerged,听ready for the next step of production.

Fabricating the neuron

Dietrich College of Humanities and Social Sciences senior Zarmond Goodman, who works as a听 in IDeATe, joined the team once the working prototype was finished. As a film and visual media major minoring in physical computing and art, Goodman鈥檚 role was to replicate Soska鈥檚 design and assemble the pieces into 10 individual neurons.

鈥淏eing able to work on a project like this is the epitome of why IDeATe is cool,鈥� they said. 鈥� I was able to combine my interests in different ways 鈥� all while working alongside people I鈥檝e looked up to since I became involved with IDeATe my first year at 麻豆村.鈥�

Goodman followed along as Soska walked them through the design, then took over soldering the components. They helped with other aspects as well, including filming and editing a听 showcasing the neuron.

鈥淗undreds of hours went into building these neurons, and Zarmond was essential to completing the project,鈥� Soska said. 鈥淭heir work really made the whole thing possible."

Next, Soska recruited Teaching Professor听, who leads IDeATe鈥檚听 minor, along with Soft Technologies instructor Natalya Pinchuk. The team needed their expertise with textiles to craft the final form of the neuron: something bright, tactile and appealing for children.

The plush body of the neuron had to accomplish three goals. First, it had to be squishy to pad the wires and other electronic components and feel soft when handled. At the same time, it had to keep electronic components stable, with knobs and displays embedded in the surface maintaining their position within the neuron. Finally, it had to keep its shape, resisting the tendency to droop when raised into the air.

鈥淥ne of our biggest challenges was designing a streamlined form that could also hold a large shoebox鈥檚 worth of electronics,鈥� Robinson recalled. 鈥淏eneath its cohesive and bright exterior, the plushy鈥檚 body is built from layers of foam and custom 鈥榮hapewear鈥� that we made to keep everything in place and give shape to the outer materials. I still find it satisfying to put it together and think back on all the inventive choices that emerged along the way.鈥�

Pinchuk agreed.听

鈥淭he vision was to provide kids with a learning tool that was tactile, interactive and fun. A textile is uniquely suited to accomplish that, offering a sensory experience that invites touch and engagement,鈥� Pinchuk added. 鈥淭he plushy form taps into feelings of play, comfort, safety, and the quiet magic of childhood 鈥� qualities that make the learning experience more approachable, memorable, and emotionally resonant.鈥�

Neuron in action

A completed Plush Neuron is a simplified version of how real neural networks work 鈥� designed for small hands and big questions.

The neuron features three inputs on one end, called 鈥渄endrites,鈥� which have buttons that can be squeezed to send weighted input signals (adjusted with a rotary switch). The dendrite's LED display shows the current weight value, which can range from -4 (lit by red LEDs) to +4 (lit by green LEDs).

Inputs are then sent to the body, or 鈥渟oma,鈥� where they are summed up and compared to the threshold displayed on another LED array. If the inputs are greater than the threshold, the long axon at the other end flashes lights and plays a sound to let the user know the neuron is 鈥渇iring.鈥�听

Weights and thresholds can be adjusted to pose a variety of simple decision problems. 鈥淭he neuron illustrates ethics in AI by showing the importance of weighting decisions,鈥� Soska explained. 鈥淲ith it, you can write and solve full-scale logic problems using the same computational logic that AI uses 鈥� how it makes decisions, and how bias is introduced.鈥�

From symposiums to middle school classrooms, the Plush Neuron is already sparking curiosity in educators across the country. The project debuted this past March at听, the 15th Symposium on Educational Advances in Artificial Intelligence. In June, the team took it to Atlanta for an听 curriculum workshop, where it was used to train teachers for the first time. Then, in August, Soska presented at the听 (ISAM) held at the University of California, Berkeley.

This fall, the team sent completed neurons to Christina Gardner-McCune, a professor at the University of Florida who leads the AI4MiddleSchools project; Amber Jones, a computer science education consultant and former middle school teacher in Atlanta; and Will Hanna, a computer science teacher at Thomas County Middle School in Georgia. These early partners, who have previously championed AI education alongside Touretzky as part of the听 project, will be the first to test the Plush Neuron in the field.