Like so many companies operating in the AI space, Literal Labs wants to revolutionize artificial intelligence, but it may stand a better chance than most.
The startup is working on a piece of technology known as the Tsetlin machine which it claims offers an AI approach that is up to 10,000 times more energy-efficient and up to 1,000 times faster than traditional GPU training.
Named after Soviet mathematician Michael Lvovitch Tsetlin, the Tsetlin machine is a pattern learning automaton based on propositional logic. This means it can perform tasks such as classification, regression, and convolution, and produce interpretable and explainable results. Unlike neural networks, a Tsetlin Machine has lower computational complexity, uses fewer resources, and does not suffer from local optima or vanishing gradients.
Recruitments from Arm
Literal Labs, previously known as Mignon Technologies Ltd., was founded by Professor Alex Yakovlev and Rishad Shafik, both from the University of Newcastle. The company’s technology focuses on developing and training Tsetlin machine models specific to customer datasets, resulting in an optimized machine model that can be deployed onto target hardware. The output is a Tsetlin machine model that can run on industry-standard hardware or can be accelerated using Literal Labs processors.
EE News Europe reports that the company recently recruited two industry veterans, Noel Hurley, former vice president at processor IP licensor Arm, and Jem Davies, who led the graphics and AI business groups at Arm. Hurley has joined Literal Labs as its CEO, while Davies has taken a position as a non-executive director.
While Literal Labs’ business model has not been disclosed yet, it could potentially license software and hardware IP, similar to Arm, or sell its own chiplets or packaged ICs as a fabless chip company. Regardless, the success of the startup will hinge on proving the claimed efficiency of Tsetlin machines in performing various tasks.
With the recruitment of Hurley and Davies, Literal Labs seems to be moving closer to commercial conversations, indicating a potentially bright future for the Tseltin machine.
