atlas

Research map / Architectures and efficiency / RNNs and normalization

From deep learning to mechanistic understanding in neuroscience: the structure of retinal prediction

NeurIPS 2019 · Architectures and efficiency › RNNs and normalization · approach: Brain-inspired network comparison · 45 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
reduce the CNN to three important subunits (1 OFF, 2 ON) found by attribution (ablation)retina CNN model · omitted stimulus responseperiod-dependent shift in burst peakHelped
use only one ON/OFF pathway pair (slow ON, fast OFF) from the CNN (ablation)retina CNN model · latency codingreproduction of latency shift with contrastHelped
keep only cell types 2 and 3 across x positions (288 units reduced) (ablation)retina CNN model · motion reversalreproduction of burst with fixed latencyHelped
remove cell-type 2 inhibition (keep only cell type 3) (ablation)reduced retina model · motion reversalfixed latency of reversal responseHurt
add direction-sensitive inhibition from second cell type to the excitatory cell type (ablation)reduced retina model · motion anticipationadvance of response toward leading edgeHelped

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy