Wafer inspection is becoming more challenging and costly with sub 30 nm process, more complex designs and new materials. The ability to detect defects is increasingly difficult with existing inspection tools.
Wafer processing includes increased metrology between the various processing steps. Metrology equipment is used to verify that the wafers have not been damaged by previous processing steps. Virtual metrology increasingly is used to predict wafer properties based on statistical methods without performing the physical measurements.
In the inspection process, an image is taken of a die. An image of another die then is taken and the two images compared.. A difference in the images typically indicates a defect.
These inspection steps require increasingly expensive tools and they slow production, costing time and money.
Neuromorphic technology is a crucial enabler for cognitive computing and artificial intelligence. It is an architecture of memories which react to input patterns and can be compared to the brain because of its low power requirements, scalability, and instantaneous internal communications.
A neuromorphic chip is a fully parallel silicon neural network, It is a chain of identical elements (i.e. neurons) which can store and process information simultaneously. They are addressed in parallel and have their own “genetic” material to learn and recall patterns without running a single line of code and without reporting to any supervising unit.
Another result of the parallel architecture of the neuromorphic chip is its constant learning and recognition time regardless of the number of connected neurons, as well as the ability to expand the size of the neural network by cascading chips.
We are developing, with our industry partners, neuromorphic-enabled systems that support rapid low-cost wafer inspection. Use neuromorphic inspection to improve your manufacturing.