I not sure if this was posted before, as I haven't seen this before...as Peter explains...

Are Better Machine Training Approaches Ahead?

Van der Made also pointed out that, unlike current ANNs, the brain leverages feedback as it operates. “The brain contains many feedback connections. Even STDP learning works by feeding the timing difference between the inputs and output of a neuron back to adjust synaptic weights.”


“Reward learning is derived from animal behaviour,” said Brainchip’s van der Made. “An animal learns something and is given a reward, such as food. This reinforces the behaviour, and the animal has learned that the way to get food is to perform the same trick. In computer hardware, this method was used to reinforce learning, by rewarding or punishing the learning algorithm. But there are some problems with this method. The reward comes after the action, sometimes way after the action, and the algorithm has to remember which action is associated with which reward or punishment. And how can you define the higher concept of ‘reward’ to an abstract, low-level algorithm?”

https://semiengineering.com/are-better-machine-training-approaches-ahead/