From research to application
ABR was spun out of Professor Chris Eliasmith's Computational Neuroscience Research Group (CNRG) at the University of Waterloo about two years after the Spaun model was published. Just before that, Peter Suma had joined the CNRG to see if their approach to building neural and cognitive models might have commercial applications.
A few years earlier, the CNRG had started using their Neural Engineering Framework (NEF) and Semantic Pointer Architecture (SPA) to build models targeting neuromorphic hardware. The combination of advanced algorithms, the ability to run them on the latest hardware, and Pete's extensive business background made ABR a no-brainer. Today ABR is pushing neuromorphic computing as a new platform, demonstrating how to achieve state-of-the-art power, speed, and accuracy across a range of AI applications.
In addition to Spaun, the research team at ABR has made advances in deep spiking networks, spiking and non-spiking adaptive control, recurrent neural networks, on-line learning, spiking and non-spiking hierarchical reinforcement learning and much more. For instance, we have developed new a kind of recurrent neural network that can outperform LSTMs on a variety of tasks, while being fully implementable in spikes. We also built the first applications using Intel's new neuromorphic hardware, Loihi, and demonstrated state-of-the-art power and performance on deep learning and adaptive control applications.
As well, we have developed an inexpensive and accessible spiking hardware platform using FPGAs that can introduce new users to the world of neuromorphics. We continue to push the boundaries of cognitive computing on neuromorphic platforms and build ever larger and more functional systems driving new robotic functionality, better and more efficient video and audio processing, and high-speed action-perception applications.
1. Function above all
Most importantly, things have to work. We make products that work as we say they work, and are robustly tested. We only include features that make our products better. Similarly, if a business practice or a part of our culture isn't working, then we'll change it.
2. Failure is encouraged
Great ideas come from years of trial and error. We take risks and try things that won't end up working. We learn from these failures, most of the time. Sometimes it might take years of accumulated failure to finally succeed.
3. Be open with each other
Collaboration is key to our success. We share ideas and problems with one another; every project is a group project.
4. Be open with everyone
We value the dissemination of ideas as much as the products we develop based on those ideas. We will share code and develop it in the open. We will publish, teach, and give talks about how we do what we do.
5. Patents, not secrets
As an open company, we do need to protect our ideas somehow. We use the patent system as it was originally meant to be used. We want to foster innovation by all in our field, not stifle it.
Nothing, including this culture statement, is taken too seriously. We criticize constructively, are Canadianly polite, and recognize each other's value as people and not as workers.