Large Neural Networks Learning from Scratch with Very Few Data and without Explicit Regularization.
Christoph LinseThomas MartinetzPublished in: ICMLC (2023)
Keyphrases
- neural network
- prior knowledge
- data sets
- data collection
- data sources
- synthetic data
- data processing
- learning algorithm
- bayesian methods
- input data
- data points
- data analysis
- high dimensional data
- database
- original data
- raw data
- high quality
- data structure
- knowledge acquisition
- learning process
- image data
- end users
- fuzzy logic
- learning systems
- background knowledge
- experimental data
- active learning
- prior information
- probability distribution