Login / Signup
Codebook Features: Sparse and Discrete Interpretability for Neural Networks.
Alex Tamkin
Mohammad Taufeeque
Noah D. Goodman
Published in:
CoRR (2023)
Keyphrases
</>
neural network
feature vectors
image features
low level
pattern recognition
co occurrence
feature set
genetic algorithm
image processing
vector quantization
feature extraction
multiscale
recurrent neural networks
extracted features
continuous variables
global exponential stability