| Description: |
Many contemporary machine learning/AI methods require extensive computation for training which consumes a great deal of time and energy resource. Their inference mechanism also tends to have a large energy-latency product. We will discuss methods that can learn in a single-pass. This usually also promotes an ability to learn continuously and, if necessary, forget earlier information if it is considered that the problem is changing over time.
It might be a good idea for participants to watch the NICE 2022 video as some background to BitBrain so that we can start with a shared basic foundation for the ideas:
https://flagship.kip.uni-heidelberg.de/jss/HBPm?mI=235&publicVideoID=8944. |