'AI brain scans' reveal how synthetic intelligence think
In Brief
- Graphcore has produce a series of images that show what it looks like when its development chip runs various AI software, such as Microsoft Research's ResNet-34 architecture.
- Looking at these images is similar to looking at a scan from a brain to see how it works as both processes involve connections between different parts of a system.
Graphcore has taken some mesmerizing images of its Intelligent Processing Units (IPUs) in action. While the images may look like a psychedelic dream or even similar to a human brain scan, they’re actually graphs of the AI’s computations.
Graphcore used its development chip running various AI software to produce these stunning images of what occurs as processes run. For example, the first image below shows how the Graphcore IPU processed Microsoft Research’s ResNet-34 architecture.
Before executing any processes, machine learning systems go through a phase in which the programming creates a graph of all the computations necessary to complete a process. The system then uses that graph to complete those processes. Essentially, what we are seeing in Graphcore’s images is a top-down view of layers upon layers of computations that are executed in passes running back and forth across the data. These passes and the connections between them are color coded to produce images like the second one below.
Nigel Toon, Graphcore’s CEO said, “The striking similarity to scans of the brain highlights that what your brain is doing is something very similar. Your brain has neurons, and synapses connecting those neurons together, and you’re effectively modeling something very similar in this machine learning world as well. What you’re seeing is how the graph operates on the processor, so it would be analogous to taking a scan from a brain to see how it works.”
