For billions of years of evolution, biological intelligent agents have mastered the power to find optimal solutions in deceptive environments that we encounter in our daily interactions with the real world. We can easy navigate themselves through the maze of a big city subways and roadways. But for artificial intelligent systems, this is too difficult to be easily solved using the optimal computing resources. This is especially true for offline autonomous agents that are not backed by super power of cloud servers.
The main problem here is related to the fact that reliable maze navigation requires the development of a…
The most popular method of Artificial Neural Networks (ANN) training -at the time of this essay writing — is to use some form of Gradient Descent (GD) combined with error back propagation wrt objective function defining our learning goal. This methodology was invented about 30 years ago by Geoffrey Hinton and become a foundation of all modern research activities in the Deep Machine Learning (ML) and the Artificial Intelligence (AI). But despite the fact that it gives imence power in areas of pattern recognition (feature or representation learning) it has considerable weakness:
AI, Neuroevolution, Genetic Algorithms, Synthetic Cognitive Systems