As stated at Part 1, ANNs are a key finding for Artificial Intelligence, especially because of models that seek to approximate the real way our brain seeks to solve problems of information representation. This is a fact, but, for a good part of science, this advance would have the potential to attain the very functionality of our mind, and other more complex systems, such as reasoning itself and perhaps even consciousness, which is undoubtedly a challenge to prove.
But in my understanding, the current growth of Deep Learning (AI/ML/DL) using ANNs has created technological myopia for the fact that we can create generic learning platforms with any kind of algorithm, and without using up even any ANN architecture, ie General Learning (GL) platforms.
For a better understanding, in Part 2 I will present a General Learning (GL) architecture model comparing with the current paradigm based on ANNs, which I define as limited intelligent systems, since they are based on the model paradigm of neural networks:
However, if we break the Layer 1 paradigm for any System with any I/O set, we have the potential to create unlimited intelligent systems:
That is Deep Learning, with or without ANNs.
Moreover, we can create systems of systems, or ecosystems, to build Artificial General Intelligence (AGI) systems, following exactly the new paradigm proposed:
That is AGI, with or without ANNs.
Rogerio Figurelli – @ 2018-12-21