Papers with Code 아카이브
Information Plane
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 0
- 평가표
- 0
- 보존된 평가 기록
- 0
To obtain the Information Plane (IP) of deep neural networks, which shows the trajectories of the hidden layers during training in a 2D plane using as coordinate axes the mutual information between the input and the hidden layer, and the mutual information between the output and the hidden layer.
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Enhancing Neural Network Interpretability Through Conductance-Based Information Plane Analysis
Lightweight Conceptual Dictionary Learning for Text Classification Using Information Compression
Cauchy-Schwarz Divergence Information Bottleneck for Regression
Information Plane Analysis Visualization in Deep Learning via Transfer Entropy
End-to-End Training Induces Information Bottleneck through Layer-Role Differentiation: A Comparative Analysis with Layer-wise Training
Improving the Robustness of Quantized Deep Neural Networks to White-Box Attacks using Stochastic Quantization and Information-Theoretic Ensemble Training
SoFaiR: Single Shot Fair Representation Learning
Mutual information estimation for graph convolutional neural networks
HRel: Filter Pruning based on High Relevance between Activation Maps and Class Labels
A Comparative Genomic Analysis of Coronavirus Families Using Chaos Game Representation and Fisher-Shannon Complexity
Information flows of diverse autoencoders
A Provably Convergent Information Bottleneck Solution via ADMM
Fundamental Limits and Tradeoffs in Invariant Representation Learning
Malicious Network Traffic Detection via Deep Learning: An Information Theoretic View
The Dual Information Bottleneck
On the Information Plane of Autoencoders
On Information Plane Analyses of Neural Network Classifiers -- A Review
On Predictive Information in RNNs
Information Plane Analysis of Deep Neural Networks via Matrix-Based Renyi's Entropy and Tensor Kernels
Understanding Autoencoders with Information Theoretic Concepts
Scalable Mutual Information Estimation using Dependence Graphs
Opening the Black Box of Deep Neural Networks via Information
Distinguishing noise from chaos: objective versus subjective criteria using Horizontal Visibility Graph
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.