Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

AutoML-Zero: Evolving machine learning algorithms from scratch

github.com

Post reply on HN
Print view View original

11–20 of 47 posts

Re: AutoML-Zero: Evolving machine learning algorithms from scratch

#11

Post by neximo64 »

manually wrote: post #3

Next: - Autosuggest database tables to use - Automatically reserve parallel computing resources - Autodetect data health issues and auto fix them - Autodetect concept drift and auto fix it - Auto engineer features and interactions - Autodetect leakage and fix it - Autodetect unfairness and auto fix it - Autocreate more weakly-labelled training data - Autocreate descriptive statistics and model eval stats - Autocreate…

Would be funny but most of those things are already on AutoML Tables, including the carbon offset

https://cloud.google.com/automl-tables

Re: AutoML-Zero: Evolving machine learning algorithms from scratch

#13

Post by jmmcd »

lokimedes wrote: post #12

Reminds me of https://www.nutonian.com/products/eureqa/ which I used quite productively to model multivariate distributions from data back in the 2000’s. Funny how everything stays the same, but with a new set of players on the bandwagon.

Not really similar. Nutonian did straight-up genetic programming symbolic regression. This does genetic programming to discover ML algorithms.

Re: AutoML-Zero: Evolving machine learning algorithms from scratch

#14

Post by westurner »

manually wrote: post #9
otagekki wrote: post #6

Earlier quoted context omitted.

Poor data scientists, now whose heads get cut when things go wrong and companies lose billions?

In the days when Sussman was a novice, Minsky once came to him as he sat hacking at the PDP-6. “What are you doing?”, asked Minsky. “I am training a randomly wired neural net to play Tic-Tac-Toe” Sussman replied. “Why is the net wired randomly?”, asked Minsky. “I do not want it to have any preconceptions of how to play”, Sussman said. Minsky then shut his eyes. “Why do you close your eyes?”, Sussman asked his teacher…

Is this an argument in favor of unjustified magic constant arbitrary priors?

Re: AutoML-Zero: Evolving machine learning algorithms from scratch

#15

Post by westurner »

neximo64 wrote: post #11
manually wrote: post #3

Next: - Autosuggest database tables to use - Automatically reserve parallel computing resources - Autodetect data health issues and auto fix them - Autodetect concept drift and auto fix it - Auto engineer features and interactions - Autodetect leakage and fix it - Autodetect unfairness and auto fix it - Autocreate more weakly-labelled training data - Autocreate descriptive statistics and model eval stats - Autocreate…

Would be funny but most of those things are already on AutoML Tables, including the carbon offset https://cloud.google.com/automl-tables

> Would be funny but most of those things are already on AutoML Tables, including the carbon offset

GCP datacenters are 100% offset with PPAs. Are you referring to different functionality for costing AutoML instructions in terms of carbon?

...

I'd add:

- Setup a Jupyter Notebook environment

> Jupyter Notebooks are one of the most popular development tools for data scientists. They enable you to create interactive, shareable notebooks with code snippets and markdown for explanations. Without leaving Google Cloud's hosted notebook environment, AI Platform Notebooks, you can leverage the power of AutoML technology.

> There are several benefits of using AutoML technology from a notebook. Each step and setting can be codified so that it runs the same every time by everyone. Also, it's common, even with AutoML, to need to manipulate the source data before training the model with it. By using a notebook, you can use common tools like pandas and numpy to preprocess the data in the same workflow. Finally, you have the option of creating a model with another framework, and ensemble that together with the AutoML model, for potentially better results.

https://cloud.google.com/blog/products/ai-machine-learning/u...

Re: AutoML-Zero: Evolving machine learning algorithms from scratch

#16

Post by deepsun »

manually wrote: post #3

Next: - Autosuggest database tables to use - Automatically reserve parallel computing resources - Autodetect data health issues and auto fix them - Autodetect concept drift and auto fix it - Auto engineer features and interactions - Autodetect leakage and fix it - Autodetect unfairness and auto fix it - Autocreate more weakly-labelled training data - Autocreate descriptive statistics and model eval stats - Autocreate…

- Auto-negotiate proper metrics to use with stakeholders.

Re: AutoML-Zero: Evolving machine learning algorithms from scratch

#17

Post by westurner »

joe_the_user wrote: post #4

AutoML-Zero aims to automatically discover computer programs that can solve machine learning tasks, starting from empty or random programs and using only basic math operations. If this system is not using human bias, who is it choosing what good program is? Surely, human labeling data involves humans adding their bias to the data? It seems like AlphaGoZero was able to do just end-to-end ML because it was able to use…

Is the question "Does AutoML-Zero minimize or maximize a cost function with error as a primary component, instead of using a binary win/lose classifier like AlphaGoZero?"

https://en.wikipedia.org/wiki/AlphaZero

Re: AutoML-Zero: Evolving machine learning algorithms from scratch

#18

Post by Icathian »

manually wrote: post #9
otagekki wrote: post #6

Earlier quoted context omitted.

Poor data scientists, now whose heads get cut when things go wrong and companies lose billions?

In the days when Sussman was a novice, Minsky once came to him as he sat hacking at the PDP-6. “What are you doing?”, asked Minsky. “I am training a randomly wired neural net to play Tic-Tac-Toe” Sussman replied. “Why is the net wired randomly?”, asked Minsky. “I do not want it to have any preconceptions of how to play”, Sussman said. Minsky then shut his eyes. “Why do you close your eyes?”, Sussman asked his teacher…

I miss the codeless code. Wish someone would take up that mantle.

Re: AutoML-Zero: Evolving machine learning algorithms from scratch

#19

Post by perl4ever »

westurner wrote: post #15
neximo64 wrote: post #11

Earlier quoted context omitted.

Would be funny but most of those things are already on AutoML Tables, including the carbon offset https://cloud.google.com/automl-tables

> Would be funny but most of those things are already on AutoML Tables, including the carbon offset GCP datacenters are 100% offset with PPAs. Are you referring to different functionality for costing AutoML instructions in terms of carbon? ... I'd add: - Setup a Jupyter Notebook environment > Jupyter Notebooks are one of the most popular development tools for data scientists. They enable you to create interactive, sh…

This sounds like the sort of thing that would be useful outside of data science. Which leads to the question of whether it needs to be generalized, or redone differently for different specializations. Which in turn seems like the sort of question that it's tricky to answer with AI.

Re: AutoML-Zero: Evolving machine learning algorithms from scratch

#20

Post by perl4ever »

westurner wrote: post #14
manually wrote: post #9

Earlier quoted context omitted.

In the days when Sussman was a novice, Minsky once came to him as he sat hacking at the PDP-6. “What are you doing?”, asked Minsky. “I am training a randomly wired neural net to play Tic-Tac-Toe” Sussman replied. “Why is the net wired randomly?”, asked Minsky. “I do not want it to have any preconceptions of how to play”, Sussman said. Minsky then shut his eyes. “Why do you close your eyes?”, Sussman asked his teacher…

Is this an argument in favor of unjustified magic constant arbitrary priors?

A sufficiently large amount of random data contains all the magic constants you could want.
Post reply on HN