AutoML-Zero: Evolving machine learning algorithms from scratch
1–10 of 47 posts
Re: AutoML-Zero: Evolving machine learning algorithms from scratch
#2Interesting, but how does it perform on standard benchmarks like image net and MNIST?
Re: AutoML-Zero: Evolving machine learning algorithms from scratch
#3Next:
- 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 monitoring
- Autocreate regulations reports
- Autocreate a data infra pipeline
- Autocreate a prediction serving endpoint
- Auto setup a meeting with relevant stakeholders on Google Calendar
- Auto deploy on Google Cloud
- Automatically buy carbon offset
- Auto fire your in-house data scientists
Re: AutoML-Zero: Evolving machine learning algorithms from scratch
#4AutoML-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 a very clear and "objective" standard, whether a program wins or loses at the game of Go.
Would this approach only deal with similarly unambiguous problems?
Edit: also, AlphaGoZero was one of the most ML ever created (at least at the time of its creation). How much computing resources would this require for more fully general learning? Will there be a limit to such an approach?
Re: AutoML-Zero: Evolving machine learning algorithms from scratch
#5Interesting, but how does it perform on standard benchmarks like image net and MNIST?
They have some cifar10 results in the paper, but only very small networks.
Re: AutoML-Zero: Evolving machine learning algorithms from scratch
#6Next: - 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…
Poor data scientists, now whose heads get cut when things go wrong and companies lose billions?
Re: AutoML-Zero: Evolving machine learning algorithms from scratch
#7AutoML-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…
> It seems like AlphaGoZero was able to do just end-to-end ML because it was able to use a very clear and "objective" standard, whether a program wins or loses at the game of Go.
Just a fun note: winning or losing at the game of Go is actually surprisingly subjective:
Re: AutoML-Zero: Evolving machine learning algorithms from scratch
#8Shouldn’t this link directly to the Readme?
https://github.com/google-research/google-research/blob/mast...
Re: AutoML-Zero: Evolving machine learning algorithms from scratch
#9Next: - 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…
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.
“So that the room will be empty.”
At that moment, Sussman was enlightened.
Re: AutoML-Zero: Evolving machine learning algorithms from scratch
#10Next: - 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…
Autodetect data health issues and auto fix them
Funy you say that cos my company is actually developing something along those lines