Andrew Sansom

Include a section on gradient-free optimization in the README file

1

**Is your feature request related to a problem? Please describe.** Currently, the README file is not clear about gradient-free optimization and why back-propagation isn't necessary in a gradient-free optimizer. This...

**Is your feature request related to a problem? Please describe.** Currently, the README file does not include a list of Particle swarm optimizers.

Check for a key in each parameter group to ignore when adjusting parameters

1

A frequent use case in training parameters is leaving some parameters fixed and changing others. Currently the only way to do that in this optimizer is to feed solely trainable...

**Is your feature request related to a problem? Please describe.** PSO algorithms are generally gradient-free, so performing back propagation and zeroing gradients should have no effect on PSO steps. We...

**Is your feature request related to a problem? Please describe.** A clear and concise description of what the problem is. Ex. I'm always frustrated when [...] Currently, we deal with...

Probably using python semantic release https://github.com/relekang/python-semantic-release **Is your feature request related to a problem? Please describe.** A clear and concise description of what the problem is. Ex. I'm always frustrated...

**Is your feature request related to a problem? Please describe.** A clear and concise description of what the problem is. Ex. I'm always frustrated when [...] **Describe the solution you'd...

**Is your feature request related to a problem? Please describe.** This algorithm is linear in the number of particles in a swarm. For large swarms, this makes it very slow....