The most popular and comprehensive Open Source ECM platform
Let us know more
Artificial Intelligence: Learning to Speak the Language of the Brain
Researchers in Artificial Intelligence are striving to emulate the computational power and energy efficiency of the human brain. The brain consumes only small amounts of power and is able to process data that may take computers hours or days.
The secret? Scientists have identified a phenomenon in the brain called spiking neurons which can make the brain super efficient. Neurons in the brain aren’t continuously firing and passing along information; they fire only after reaching a certain threshold of stimuli.
Sander Bohté, neural computation researcher, said that “the communication between neurons in classical neural networks is continuous and easy to handle from a mathematical perspective. Spiking neurons look more like the human brain and communicate only sparingly and with short pulses. This, however, means that the signals are discontinuous and much more difficult to handle mathematically.”
Andrew Duncombe, student at Brown University, said that “except for maybe some pure math people, most people’s brains don’t run on linear algebra. They run using spikes and neural synapses. Depending on the intensity and frequency of those incoming spikes, the neuron itself will fire and spike out and send its information to other neurons. It is on this premise that spiking neural networks (SNNs) is being investigated. This information is not encoded as integers, but as spikes transmitted between neurons. This greatly reduces the complexity of the computations we need to perform.”
Friedemann Zenke, neuroscientist, said that “my main motivation to think about spiking neural networks is because it’s the language the brain speaks. If you want to understand the signals that we can measure from the brain, we need to learn the language.”
