Re:Neuromorphic computing implementation of pole balancing
by parkerm7 on Monday September 12, 2016 @12:10PM
(#12480908)
Learning algorithms remain a big issue in neuromorphic computing. So far, we have had some success with evolutionary optimization algorithms. The nice aspect of EO at the this stage of the game is that EO can reveal useful patterns and network features which could guide later learning systems.
I am working on a project right now which will require a more complex network interacting with many real world sensors, so it should be interesting to see how EO performs for such a problem. Our EO has been demonstrated to scale on parallel machines as large as ORNL's Titan, but I readily acknowledge that much more work needs to be done with learning algorithms.
Re:Neuromorphic computing implementation of pole balancing
by dharma1 on Monday September 12, 2016 @03:01AM
(#12477739)
http://www.scholarpedia.org/article/Spike-timing_dependent_p...
But it kind of requires the structure of the cortical columns to already be in place - which has happened through genetics/evolution in biology.
Biologically plausible backpropagation could also work, but I haven't seen anyone successfully apply it in SNN's
Currently, fixed architecture ANNs can solve the cartpole problem very quickly already with Q-learning or policy gradient methods: https://gym.openai.com/envs/CartPole-v0
It seems like some kind of neuromorphic networks are going to be necessary for the long term AI 'dream', but there really needs to be something better then evolutionary algorithms for training, those just don't scale.