The goals are to save money (over $4 million for a single training run of a natural language model) and reduce CO2 emissions.
- By Pure AI Editors
- 06/02/2021
Also, less CO2 is emitted, which is a good thing because one researcher said: "The current approach for building ML models is not sustainable and we will hit a ceiling soon, if not already."
- By Pure AI Editors
- 05/03/2021
Calculating dataset similarity is difficult but is useful for several scenarios and can potentially save millions of dollars in ML computing costs and even greatly reduce carbon footprints.
- By Pure AI Editors
- 04/08/2021
One of the main reasons for the increased interest in the tricky field of ML model calibration is the fact that the more complex a model is, the more likely the model is to not be well-calibrated.
- By Pure AI Editors
- 03/03/2021
The challenge is that when new data arrives periodically, a new prediction model trained using the existing model (a "warm-start"), the resulting new model performs worse than a model trained from scratch (a "cold-start").
- By Pure AI Editors
- 02/01/2021
By adding random noise to an image to be classified, and then removing the noise using a custom neural denoiser, standard image classification models are less likely to be successfully attacked.
- By Pure AI Editors
- 01/05/2021
The Pure AI Editors explain two different approaches to solving the surprisingly difficult problem of computing the similarity -- or "distance" -- between two machine learning datasets, useful for prediction model training and more.
- By Pure AI Editors
- 12/01/2020
"I think it's safe to say that the application of ML techniques to biology scenarios will bring new breakthroughs, some of which will be very surprising and unexpected," says a machine learning expert.
- By Pure AI Editors
- 11/05/2020
The Pure AI editors keep you abreast of the latest machine learning advancements by explaining a new neural-based architecture for solving reinforcement learning (RL) problems. WMG uses a deep neural technique developed for natural language processing problems called Transformer architecture, and it significantly outperformed baseline RL techniques in experiments on several difficult benchmark problems.
- By Pure AI Editors
- 09/02/2020
The Pure AI editors explain a new paper that describes how a computer program can automatically generate a machine learning algorithm, which can create a machine learning prediction model.
- By Pure AI Editors
- 08/19/2020