[Article.Ai] What is a “Supersymmetric Artificial Neural Network”?

2 min readNov 11, 2017

The “Supersymmetric Artificial Neural Network” is a Lie Superalgebra aligned algorithmic learning model (created on May 10, 2016), based on evidence pertaining to Supersymmetry in the biological brain.

To describe the significance of the “Supersymmetric Artificial Neural Network”, I will describe an informal proof of the representation power gained by deeper abstractions generatable by learning supersymmetric weights.

Remember that Deep Learning is all about representation power, i.e. how much data the artificial neural model can capture from inputs, so as to produce good guesses/hypotheses about what the input data is talking about.

Machine learning is all about the application of families of functions that guarantee more and more variations in weight space.

This means that machine learning researchers study what functions are best to transform the weights of the artificial neural network, such that the weights learn to represent good values for which correct hypotheses or guesses can be produced by the artificial neural network.

The “Supersymmetric Artificial Neural Network” is yet another way to represent richer values in the weights of the model; because supersymmetric values can allow for more information to be captured about the input space. For example, supersymmetric systems can capture potential-partner signals, which are beyond the feature space of magnitude and phase signals learnt in typical real valued neural nets and deep complex neural networks respectively. As such, a brief historical progression of geometric solution spaces for varying neural network architectures follows: