Kolmogorov Width Decay and Poor Approximators in Machine Learning: Shallow Neural Networks, Random Feature Models and Neural Tangent Kernels.
Weinan EStephan WojtowytschPublished in: CoRR (2020)
Keyphrases
- neural network
- machine learning
- pattern recognition
- kernel methods
- network architecture
- neural network model
- connectionist models
- neural model
- machine learning algorithms
- data mining
- machine learning methods
- natural language processing
- probabilistic model
- artificial intelligence
- machine learning approaches
- model selection
- neural nets
- artificial neural networks
- statistical methods
- fuzzy logic
- learning rules
- decision trees
- back propagation
- information extraction
- image features
- learning tasks
- feature extraction
- multilayer perceptron
- recurrent neural networks
- computer vision
- knowledge acquisition
- machine learning models
- neural models
- learning algorithm
- tangent distance