Communications of the ACM
Neuromorphic Circuit Simulates Associative Learning
Synaptic transistors in a neuromorphic circuit send signals between terminals to form an artificial synapse.
Credit: Northwestern University
Researchers at Northwestern University and the University of Hong Kong have developed a computing device that is capable of learning by association.
The researchers successfully conditioned a neuromorphic circuit to associate light with pressure. They describe their work in "Mimicking Associative Learning Using an Ion-Trapping Non-Volatile Synaptic Organic Electrochemical Transistor," published in the journal Nature Communications.
The device's novel organic, electrochemical "synaptic transistors" simultaneously process and store information. The researchers demonstrated that the transistor can mimic the short-term and long-term plasticity of synapses in the human brain, building on memories to learn over time.
Conventional, digital computing systems have separate processing and storage units. "If we can bring those two separate functions together, we can save space and save on energy costs," says Xudong Ji, a postdoctoral researcher at Northwestern's McCormick School of Engineering.
From Northwestern University
View Full Article
No entries found