AutoML-Zero: Evolving Machine Learning Algorithms From Scratch · HackerPapers discussions

AutoML-Zero: Evolving Machine Learning Algorithms From Scratch — mentioned by westurner

Fri, 10 Jul 2020 01:54:34 GMT

"AutoML-Zero: Evolving Machine Learning Algorithms From Scratch" (2020) https://arxiv.org/abs/2003.03384 https://scholar.google.com/scholar?cluster=11748751662887361... How does this compare to MOSES (OpenCog/asmoses) or PLN? https://github.com/opencog/asmoses https://scholar.google.com/scholar?hl=en&as_sdt=0%2C43&q=%22... (2007)

Paper and discussion history. A mention is not an endorsement.

AutoML-Zero: Evolving Machine Learning Algorithms From Scratch — HN submission

Mon, 01 Jun 2020 15:33:28 GMT

Evolving Machine Learning Algorithms from Scratch

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

AutoML-Zero: Evolving Machine Learning Algorithms From Scratch — HN submission

Sun, 31 May 2020 18:38:11 GMT

Evolving Machine Learning Algorithms from Primitive Mathematical Operations

4 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

AutoML-Zero: Evolving Machine Learning Algorithms From Scratch — HN submission

Mon, 25 May 2020 15:00:42 GMT

AutoML-Zero: Evolving Machine Learning Algorithms from Scratch

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

AutoML-Zero: Evolving Machine Learning Algorithms From Scratch — mentioned by gwern

Thu, 21 May 2020 00:31:58 GMT

I think you are underselling the potential of a model which deeply understand programming. Imagine combining such a model with something like AutoML-Zero: https://arxiv.org/abs/2003.03384 It may not be 'creative', but used as tab-completion, it's not being rewarded or incentivized or used in any way which would expose its abilities towards creating a new sort algorithm.

Paper and discussion history. A mention is not an endorsement.

AutoML-Zero: Evolving Machine Learning Algorithms From Scratch — mentioned by jzer0cool

Fri, 24 Apr 2020 12:02:22 GMT

Here is a paper they referenced in the article: 2003) AutoML-Zero: Evolving Machine Learning Algorithms From Scratch - https://arxiv.org/abs/2003.03384. Although I could not finish reading all of it yet, I think here algorithms mutating is another dimension which can mutate, which then effects of course new topologies, weights, and other factors.

Paper and discussion history. A mention is not an endorsement.

AutoML-Zero: Evolving Machine Learning Algorithms From Scratch — HN submission

Thu, 23 Apr 2020 12:26:11 GMT

AutoML-Zero: Evolving Machine Learning Algorithms from Scratch

1 point; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

AutoML-Zero: Evolving Machine Learning Algorithms From Scratch — HN submission

Sat, 18 Apr 2020 14:43:47 GMT

AutoML-Zero: Evolving Machine Learning Algorithms from Scratch

5 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

AutoML-Zero: Evolving Machine Learning Algorithms From Scratch — HN submission

Fri, 17 Apr 2020 02:08:58 GMT

AutoML-Zero: Evolving Machine Learning Algorithms from Scratch

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

AutoML-Zero: Evolving Machine Learning Algorithms From Scratch — HN submission

Thu, 16 Apr 2020 08:44:11 GMT

AutoML-Zero: Evolving Machine Learning Algorithms from Scratch

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

AutoML-Zero: Evolving Machine Learning Algorithms From Scratch — HN submission

Tue, 14 Apr 2020 09:40:51 GMT

AutoML-Zero: Evolving Machine Learning Algorithms from Scratch

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.

AutoML-Zero: Evolving Machine Learning Algorithms From Scratch — mentioned by vidarh

Wed, 11 Mar 2020 07:52:26 GMT

The paper [1] cites Koza among a total of 102 citations. "An early example of a symbolically discovered optimizer is that of Bengio et al. [8], who represent F as a tree: the leaves are the possible inputs to the optimizer (i.e. the xi above) and the nodes are one of {+, −, ×, ÷}. F is then evolved, making this an example of genetic programming [36]. Our search method is similar to genetic programming but we choose to represent the program as a sequence of instructions—like a programmer would type it—rather than a tree. " "[36]" is "Koza, J. R. and Koza, J. R. Genetic programming: on the…

Paper and discussion history. A mention is not an endorsement.

AutoML-Zero: Evolving Machine Learning Algorithms From Scratch — HN submission

Wed, 11 Mar 2020 00:43:32 GMT

AutoML-Zero: Evolving Machine Learning Algorithms from Scratch

2 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.