ExplainableAI.jl
ExplainableAI.jl copied to clipboard
Add LRP support for nested Chains
This will be the first step towards #10 by allowing nested model structures.
This requires the following changes:
- [ ] new internal representation of rules, e.g. via
LRPRulesChain/LRPRulesParallelto support graphs - [ ] treat chains the same way as layers by adding
lrp!(Rₖ, r::AbstractLRPRule, c::Chain, aₖ, Rₖ₊₁), which can be called recursively. This will require a different approach to pre-allocating activations and relevances than the one currently used in the call to the analyzer. - [ ]
Compositemight require a refactoring - [ ] Update
lrp/show.jl