Efficient Similarity-Preserving Unsupervised Learning using Modular Sparse Distributed Codes and Novelty-Contingent Noise.
Rod RinkusPublished in: CoRR (2020)
Keyphrases
- unsupervised learning
- cooperative
- lightweight
- noise reduction
- missing data
- structural similarity
- similarity measure
- sparse data
- distributed environment
- machine learning
- similarity function
- data sets
- model selection
- signal to noise ratio
- semi supervised
- active learning
- edit distance
- noise level
- novelty detection
- high dimensional
- distance computation