Stephen A. Baccus Lab
Stephen A. BaccusHow retinal circuits transform visual information, adapt and compute; models that connect predictions to mechanisms.
6 lessons · ~45 minutes
Explore the labResearch topic
Interpretable machine learning
Connecting model behavior to testable scientific hypotheses.
Independent educational guide. Not affiliated with or endorsed by the universities, professors or laboratories described here. This collection reflects the material currently mapped on Socratic Learn.
Labs and groups studying related work
Professors
Lessons to understand this topic
Recommended through the concepts linked to this topic. Each lesson belongs to an existing learning series.
Core background
Neural Circuits, Vision, and Computation
From neural data to interpretable modelsDescribe a linear-nonlinear model r(t) = f(k * s(t)) and how it is evaluated on held-out data.
Supports: Interpretable machine learning
Decode Life: AI & Computational Biology
Train, validation and test setsTraining fits model parameters; validation guides choices; a held-out test estimates performance on unseen cases.
Supports: Interpretable machine learning
Important papers
Neuron 111:2742–2755 · 2023
Interpreting the retinal neural code for natural scenes: from computations to neurons
Maheswaranathan N, McIntosh LT, Tanaka H, Grant S, Kastner DB, Melander JB, Nayebi A, Brezovec LE, Wang JH, Ganguli S, Baccus SA
Why this matters: Connects predictive retinal models to interpretable computations.
DOI: 10.1016/j.neuron.2023.06.007