Robocop (2014): what does this new movie can teach us about AI evolution

Neural Networks (NNs), or Artificial Neural Networks (ANNs), started as a big promise, and their models were quite simple compared to the models we have today: it was a simple neuron with binary outputs based on thresholds. In layman terms, it would read values as input, sum them weighted by parameters (called learning weights, where the knowledge is stored), and compared to a threshold: if it is higher, the output is one (it simulated the firing of a neuron in biology, which follows similar patterns). Except for the big hope people placed on them, they could, and still, can only separate binary boundaries: yes or no, sick or no, guilty or no. Nonetheless, do not fall prey to the common trap that simplicity as being easy: boundaries can be hard even for complex decision processes, such as release or not a patient under healthcare, or release or not a prisoner after some appeals to do so. From one side, we had some people from neuroscience seeing on the models possible explanations for their biological phenomena (i.e., in silico simulations, it was quite appealing that we could simplify the brain workings using such a simple model, based on summations). On the other hand, applied mathematical and computer scientists looking for new solutions for their complex problems out of the box (e.g., XOR problem[1], it is a problem simple for humans, but hard for machines).