I've recently been embracing the idea of co-evolutionary pressure. Reading the article I thought that if it was just the dryness, bacteria would have evolved to tap such a rich energy source. Hence the biology of bees must have something to do with the preservative nature of honey. I'm feeling vindicated!
I think co-evolution should be investigated for encoder-decoder architecture training.
The idea being that you pair multiple decoders with each encoder, and multiple encoders with each decoder (randomly sample if large populations). The selective pressure is a feedback loop between the encoder and decoder populations that requires the members to produce and interpret the latent vector as well as possible. In theory, this creates a form of generalization pressure wherein the encoders and decoders must perform well with a wide range of possible up/down stream states. I think with large enough populations, this could be robust to premature convergence and overfitting.
Peteragain|7 months ago
bob1029|7 months ago
The idea being that you pair multiple decoders with each encoder, and multiple encoders with each decoder (randomly sample if large populations). The selective pressure is a feedback loop between the encoder and decoder populations that requires the members to produce and interpret the latent vector as well as possible. In theory, this creates a form of generalization pressure wherein the encoders and decoders must perform well with a wide range of possible up/down stream states. I think with large enough populations, this could be robust to premature convergence and overfitting.