A new neural network for optimal time series processing - Livestream

We have recently discovered a new kind of neural network, called a Legendre Memory Unit (LMU) that is provably optimal for compressing streaming time series data. In this talk, I describe this network, and a variety of state-of-the-art results that have been set using the LMU. I will include recent results on speech and language applications that demonstrate significant improvements over transformers. I will also describe the new ASIC design we have developed to implement this architecture directly in hardware, enabling new large-scale functionality at extremely low power and latency.

Register at weblink to attend

Speaker: Chris Eliasmith, Applied Brain Research