#neural network interpretability — AI News & Research

🔬 Research Distill.pub 13 min read

Branch Specialization

When a neural network layer is divided into multiple branches, neurons self-organize into coherent groupings.

#neural network interpretability #branch specialization #network architecture

🕐 5 years ago

Read →

🔬 Research Distill.pub 34 min read

Exploring the baseline input hyperparameter, and how it impacts interpretations of neural network behavior.

#neural network interpretability #feature attribution #integrated gradients

🕐 6 years ago

Read →

🔬 Research Distill.pub 27 min read

Detailed derivations and open-source code to analyze the receptive fields of convnets.

#convolutional neural networks #receptive fields #neural network interpretability

🕐 6 years ago

Read →