expertise needed
deep learning
Requires access to and understanding of a neural network's internals: gradients, activations, attention weights and layers. Narrower than ml-engineering, which would keep training, adaptation and operation.
16 techniques
| Goals | Models | Data Types | Description | |||
|---|---|---|---|---|---|---|
| Integrated Gradients | Algorithmic | Architecture/neural Networks Architecture/neural Networks/transformer +4 | Image Tabular Text | Integrated Gradients assigns input features scores for a prediction relative to a chosen reference input, called the... | ||
| DeepLIFT | Algorithmic | Requirements/model Internals Architecture/neural Networks +2 | Any | DeepLIFT (Deep Learning Important FeaTures) explains a single prediction of a neural network by dividing the difference... | ||
| Layer-wise Relevance Propagation | Algorithmic | Requirements/model Internals Architecture/neural Networks +3 | Any | Layer-wise Relevance Propagation (LRP) explains a neural network's prediction by working backwards from the output to... | ||
| Gradient Saliency | Algorithmic | Architecture/neural Networks Requirements/differentiable +2 | Image | Gradient saliency (also called vanilla gradient saliency) is the simplest gradient-based explanation for image... | ||
| Gradient-weighted Class Activation Mapping | Algorithmic | Architecture/neural Networks/convolutional Requirements/architecture Specific +3 | Image | Grad-CAM (Gradient-weighted Class Activation Mapping) draws a heatmap over an image showing which regions most raise a... | ||
| Attention Weight Analysis | Algorithmic | Architecture/neural Networks/recurrent Architecture/neural Networks/transformer +2 | Image Text | Attention weight analysis reads the weights an attention-based neural network assigns to the parts of its input, to see... | ||
| Neuron Activation Analysis | Algorithmic | Architecture/neural Networks Requirements/model Internals +1 | Text | Neuron activation analysis examines when individual neurons in a neural network respond strongly. The analyst runs a set... | ||
| Causal Mediation Analysis in Language Models | Algorithmic | Architecture/neural Networks/transformer Architecture/neural Networks/transformer/llm +3 | Text | Causal mediation analysis traces which internal components of a language model carry the effect of a change in the input... | ||
| Fair Adversarial Networks | Algorithmic | Architecture/model Agnostic Paradigm/supervised +1 | Tabular | Fair Adversarial Networks is a pre-processing method, proposed by Cevora (2020), that rewrites a dataset so that a... | ||
| Learning Adversarially Fair and Transferable Representations | Algorithmic | Architecture/neural Networks Paradigm/parametric +4 | Image Tabular | Learning Adversarially Fair and Transferable Representations (LAFTR) trains an encoder that turns each record into a... | ||
| Differentially Private Stochastic Gradient Descent | Algorithmic | Architecture/neural Networks Paradigm/parametric +2 | Any | Differentially private stochastic gradient descent (DP-SGD) trains a neural network, or another model fitted by gradient... | ||
| Linear Bound Propagation Verification | Algorithmic | Architecture/neural Networks Requirements/white Box | Image Tabular | Linear bound propagation verification proves that a trained neural network meets a stated property for every input in a... | ||
| SMT-Based Neural Network Verification | Algorithmic | Architecture/neural Networks Architecture/neural Networks/feedforward +1 | Tabular | SMT-based neural network verification decides exactly whether any input in a defined region can make a trained neural... | ||
| Sanity Checks for Saliency Maps | Testing | Architecture/neural Networks Requirements/white Box +1 | Image Tabular Time-series | Sanity checks for saliency maps are two randomisation tests that show whether an explanation method's output depends on... | ||
| GNNExplainer | Algorithmic | Architecture/neural Networks Requirements/gradient Access +2 | Graph | GNNExplainer explains one prediction of a graph neural network, a model that passes information along the edges of a... | ||
| Sparse Autoencoder Feature Analysis | Algorithmic | Architecture/neural Networks/transformer Architecture/neural Networks/transformer/llm +2 | Text | Sparse autoencoder feature analysis looks for human-interpretable units inside a neural network, usually a language... |
Rows per page
Page 1 of 1