HTC Seminar Series #30 - Deep Dive into Neuroevolution - A Conversation with Kenneth Stanley
Today's HTC seminar presentation is rather long, but worth digesting in it's entirety. Alternatively titled 'Why Greatness Can't be Planned', it's both a conversation between the Machine Learning Street Talk gang and Kenneth Stanley, as well as a very in-depth exploration of Kenneth's research in neuroevolution.
The concept of 'novelty search with no clearly defined objective' is explored in detail. Another way of saying this is that following an objective may be an impediment to achieving it. Kenneth thinks that society's focus on objective and improving benchmarks is both counter productive as well as dangerous.
If all you care about is optimization algorithms and deep learning, Kenneth's viewpoints should get you thinking as well.
Let's dive in.
Here's a link to the NEAT algorithm paper.
Here's a link to the POET paper.
Here's a link to the enhanced Poet paper.
Here's a link to the Pic Breeder paper.
Kenneth thinks that Pic Breeder is a metaphor for how the ideas discussed in this seminar can apply to real life.
Here's a link to Kenneth's book 'Why Greatness Can't be Planned, The Myth of the Objective'.
1. So i have to point out that Pic Breeder looks a lot like Studio Artist MSG Evolution Editor, which looks a lot like (and takes direct inspiration from) Richard Dawkin's original image breeding experiments back at the first artificial life conference.
I was also struck by how certain aspects of Studio Artist's design actively promote the concept of exploring diversity (as opposed to relentlessly iterating on achieving a specific goal).