Our proprietary, brain-like algorithms are core to our co-design expertise:

• The building blocks of a brain-inspired computer (link): This paper provides a blueprint on the rules to follow to build a brain-inspired computer. This is foundational for our long-term roadmap to artificial brains. 

• Training End-to-End Analog Neural Networks with Equilibrium Propagation (link): This paper shows that the pathway to gain massive energy efficiency is by using analog hardware and bio-inspired algorithms.

• Activity-difference training of deep neural networks using memristor crossbars (link): We projected that we can achieve over a 10,000x efficiency gains over GPUs. 

Combining processing and memory—in-memory computing—is a critical element of our technology platform that enables dramatic gains in efficiency.

• Scaleable In-Memory Computing Architectures for Sparse Matrix Multiplication (link): We demonstrate the scalability of our roadmap by exploiting brain-like sparsity patterns and 3-dimensional integration. Built with TSMC 180nm technology.

See our Learn More section to get more information on our generation 1 product and/or to connect with our team.