News for hackers. Stuff that matters.
Re:Gödel Machine by nickelcitymario on Thursday March 28, 2019 @04:46PM (#19516430)
Honest question:

Has this been put into practice in any AI to date?

Does TensorFlow count as a Gödel Machine? ML is basically the machine deciding its own weights right? Is that the same thing? Or have we not crossed into "writing its own code" territory?

And if we haven't, why not? This seems like the kind of thing we already have the technology for.

Re:Gödel Machine by Voloskaya on Thursday March 28, 2019 @05:12PM (#19516677)
In typical ML you just learn the weights. But the architecture stays fixed, and since we don't have an architecture that can realistically solve well enough all tasks, it shouldn't count as Godel machine.

Meta-learning, where you also learn hyper-parameters (including potentially the architecture) are closer to that, see for example:

- Google Vizier: https://ai.google/research/pubs/pub46180

- Microsoft neural architecture search: https://github.com/Microsoft/nni

But this is still far from a true Godel machine.

Re:Gödel Machine by jimfleming on Thursday March 28, 2019 @05:24PM (#19516786)
Hyperparameter optimization (including architectures) is not really meta-learning. Meta-learning, also known as "learning to learn", is more like MAML[0], RL2[1], L2RL[2], etc.

0. https://arxiv.org/abs/1703.03400

1. https://arxiv.org/abs/1611.02779

2. https://arxiv.org/abs/1611.05763

Re:Gödel Machine by jimfleming on Thursday March 28, 2019 @05:08PM (#19516627)
> Has this been put into practice in any AI to date?

Meta-learning is an active subfield of research in machine learning. Gödel machines may overlap with program synthesis as well which is another subfield.

> Does TensorFlow count as a Gödel Machine?

No. TF is itself is static and not self-improving. Most standard machine learning models are also not typically self-improving, though you can implement meta-learning with TF.

A big challenge with meta-learning is scale. It's relatively easy to solve multi-armed bandit problems but complex tasks are still challenging.

Re:Gödel Machine by api on Thursday March 28, 2019 @07:27PM (#19517667)
Some attempts at evolutionary AI / genetic programming might technically count given that they can achieve program synthesis almost ex nihilo, but the computational requirements to do anything interesting are monstrous. So far neural networks that can learn weights but whose architectures are tuned for specific problems have far eclipsed the performance of things like GP for real world applications.