#syntheticdatageneration — Public Fediverse posts

I scaled up the popular Palmer Penguins machine learning dataset from 344 rows to 100k rows using adversarial random forest, with an accuracy of 88%.

Now, you have more rows of data with which to train your classification models.

You can download it here, along with R & Python scripts, to load and view the dataset: https://ieee-dataport.org/documents/palmer-penguins-100k-0

Have a dataset you want to scale up? Say hello!

#machinelearning #randomforest #rstats #python #datascience #datasets #syntheticdatageneration #ai

I spoke to Chris Stokel-Walker for Scientific American about whether researchers can use generative AI, especially large language models, to replace human participants.

My short answer: no. My long answer:
https://www.scientificamerican.com/article/can-ai-replace-human-research-participants-these-scientists-see-risks/

#LargeLanguageModels #ScientificAmerican #ChrisStokelWalker #GenerativeAI #LLMs #HumanResearch #SyntheticData #SyntheticDataGeneration #SimulatedData #DataSimulation #AItools #AIinResearch #ResearchTools #ResearchMethods #AcademicMastodon #ResearchEthics

It's been a pleasure to present our #DeepLearning from Trajectory Data review paper at #BMDA2023

https://www.datastories.org/bmda23/BMDA23Program.html

Our review covers 8 use cases:
1. #LocationClassification
2. #ArrivalTimePrediction
3. #TrafficFlow #prediction
4. #Trajectory prediction
5. Trajectory #classification
6. Next location prediction
7. #AnomalyDetection
8. #SyntheticDataGeneration

The price for most surprising approach 🏆 goes to natural language #NLP #Transfomers for #Traffic volume prediction

#EDBT2023