74 results on '"Quanshi Zhang"'
Search Results
2. Disentangling Regional Primitives for Image Generation.
3. Alignment Between the Decision-Making Logic of LLMs and Human Cognition: A Case Study on Legal LLMs.
4. Towards the Dynamics of a DNN Learning Symbolic Interactions.
5. Quantifying In-Context Reasoning Effects and Memorization Effects in LLMs.
6. Defining and Extracting generalizable interaction primitives from DNNs.
7. Two-Phase Dynamics of Interactions Explains the Starting Point of a DNN Learning Over-Fitted Features.
8. Does a Neural Network Really Encode Symbolic Concept?
9. Technical Note: Defining and Quantifying AND-OR Interactions for Faithful and Concise Explanation of DNNs.
10. Concept-Level Explanation for the Generalization of a DNN.
11. Bayesian Neural Networks Tend to Ignore Complex and Sensitive Concepts.
12. Explaining How a Neural Network Play the Go Game and Let People Learn.
13. Where We Have Arrived in Proving the Emergence of Sparse Symbolic Concepts in AI Models.
14. Understanding and Unifying Fourteen Attribution Methods with Taylor Interactions.
15. Towards Attributions of Input Variables in a Coalition.
16. HarsanyiNet: Computing Accurate Shapley Values in a Single Forward Propagation.
17. Can the Inference Logic of Large Language Models be Disentangled into Symbolic Concepts?
18. Towards Theoretical Analysis of Transformation Complexity of ReLU DNNs.
19. Why Adversarial Training of ReLU Networks Is Difficult?
20. RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL.
21. Defects of Convolutional Decoder Networks in Frequency Representation.
22. Batch Normalization Is Blind to the First and Second Derivatives of the Loss.
23. Proving Common Mechanisms Shared by Twelve Methods of Boosting Adversarial Transferability.
24. Quantifying the Knowledge in a DNN to Explain Knowledge Distillation for Classification.
25. Interpreting Attributions and Interactions of Adversarial Attacks.
26. A Game-Theoretic Taxonomy of Visual Concepts in DNNs.
27. Game-theoretic Understanding of Adversarially Learned Features.
28. Proceedings of ICML 2021 Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI.
29. Visualizing the Emergence of Intermediate Visual Patterns in DNNs.
30. Interpreting Representation Quality of DNNs for 3D Point Cloud Processing.
31. A Hypothesis for the Aesthetic Appreciation in Neural Networks.
32. Interpretable Compositional Convolutional Neural Networks.
33. Towards Axiomatic, Hierarchical, and Symbolic Explanation for Deep Models.
34. Trap of Feature Diversity in the Learning of MLPs.
35. Discovering and Explaining the Representation Bottleneck of DNNs.
36. Learning Baseline Values for Shapley Values.
37. Rapid detection and recognition of whole brain activity in a freely behaving Caenorhabditis elegans.
38. A Unified Approach to Interpreting and Boosting Adversarial Transferability.
39. Explaining Knowledge Distillation by Quantifying the Knowledge.
40. Interpreting Hierarchical Linguistic Interactions in DNNs.
41. Interpreting Multivariate Interactions in DNNs.
42. Deep Quaternion Features for Privacy Protection.
43. Rotation-Equivariant Neural Networks for Privacy Protection.
44. Interpreting and Boosting Dropout from a Game-Theoretic View.
45. Game-Theoretic Interactions of Different Orders.
46. Achieving Adversarial Robustness via Sparsity.
47. Interpreting and Disentangling Feature Components of Various Complexity from DNNs.
48. Proceedings of AAAI 2019 Workshop on Network Interpretability for Deep Learning.
49. 3D-Rotation-Equivariant Quaternion Neural Networks.
50. Quantifying Layerwise Information Discarding of Neural Networks.
Catalog
Books, media, physical & digital resources
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.