This piece is in continuation to the previous blog on the OpenCog and AGI. In this piece we will understand a core element of the OpenCog system i.e. the Atomspace which is the information storage and retrieval system used in the framework. …

Overview

While we think, it's about using networks to solve worldly problems and call it AI. Extrapolating the networks of networks to solve all the problems in the world is an endless sheet which humans will keep on stitching since there is no upper bound on the intelligence, something which has…

Well, I wouldn’t have been writing this article if evolution wouldn’t have been a phenomenon that we as a human civilisation would have experienced and found in the nature. I believe the most sophisticated algorithm on the planet is evolution which has no defined objective but still is progressing and…

Continuing on the paradigm of the Neuro mechanics functioning theories of the brain. Another star in the universe twinkles quite bright, the cell assembly and correlation theory. It was proposed by Donald O Hebb.

Synaptic plasticity basically says if axon of cell A is near enouth to excite cell B…

Continuing in the paradigm of the theories(refer to previous blogs on the same Free energy principle and Bayesian Brain hypothesis) in concern with the brain’s neurological functioning. A theory right which speaks for a special case of free energy principle is the infomax principle.

Infomax Principle

The principle optimises the…

Continuing on to another fascinating theory in the field of Neuroscience, Bayesian Brain Hypothesis. As we all are aware of the fact Bayesian Statistics in the Probabilistic methodology to update belief with evidence using conditional probability on your priors. It shouldn’t be a Brainer to expect a theory extrapolating the…

Since the boom of the era of Artificial Intelligence I have come across a lot of Literature on the Perceptron based Deep Learning Architectures which speaks for how these models are learning the human cognition phenomenons using the mathematical approximation methods. I was not able to accept the fact that…

Convolution Neural networks are a breed of neural network-based representation learning architecture that used convolution operation to downsample a large N-dimensional feature map while keeping the important information intact in the low dimensional representations. I will not get into the details of what are CNNs, how do they work. What…