Corpus ID: 197430748

Differentiable Disentanglement Filter: an Application Agnostic Core Concept Discovery Probe

@article{Barzdins2019DifferentiableDF,
  title={Differentiable Disentanglement Filter: an Application Agnostic Core Concept Discovery Probe},
  author={Guntis Barzdins and Eduards Sidorovics},
  journal={ArXiv},
  year={2019},
  volume={abs/1907.07507}
}
It has long been speculated that deep neural networks function by discovering a hierarchical set of domain-specific core concepts or patterns, which are further combined to recognize even more elaborate concepts for the classification or other machine learning tasks. Meanwhile disentangling the actual core concepts engrained in the word embeddings (like word2vec or BERT) or deep convolutional image recognition neural networks (like PG-GAN) is difficult and some success there has been achieved… Expand

References

SHOWING 1-10 OF 22 REFERENCES
Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification
  • 9,613
  • PDF
Challenging Common Assumptions in the Unsupervised Learning of Disentangled Representations
  • 416
  • PDF
SPINE: SParse Interpretable Neural Embeddings
  • 53
  • Highly Influential
  • PDF
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
  • 16,976
  • PDF
Understanding the difficulty of training deep feedforward neural networks
  • 9,921
  • PDF
Towards Conceptual Compression
  • 181
  • Highly Influential
  • PDF
Linguistic Regularities in Continuous Space Word Representations
  • 2,719
  • PDF
Neural scene representation and rendering
  • 293
  • PDF
...
1
2
3
...