Stefan Mihalas
5 papers · 2016–2024 · 2 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🏃
Academic Marathon · Sprint
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(12)
🏆
Keyword Champion
Venues
Top co-authors
Research topics
Keywords
information theory
(1)
multivariate gaussian
(1)
brain connectivity
(1)
gradient descent
(1)
bias correction
(1)
matrix completion
(1)
neural population
(1)
bayesian network
(1)
recurrent neural network
(1)
weight initialization
(1)
partial information decomposition
(1)
credit assignment
(1)
probabilistic circuit
(1)
backpropagation through time
(1)
lazy learning
(1)
neural network initialization
(1)
spline regression
(1)
low-rank factorization
(1)
eligibility trace
(1)
biological neural network
(1)
Papers
How connectivity structure shapes rich and lazy learning in neural circuits
ICLR 2024
Efficient approximation of neural population structure and correlations with probabilistic circuits
ICLR 2023
Gaussian Partial Information Decomposition: Bias Correction and Application to High-dimensional Data
NeurIPS 2023
Biologically-plausible backpropagation through arbitrary timespans via local neuromodulators
NeurIPS 2022
High resolution neural connectivity from incomplete tracing data using nonnegative spline regression
NeurIPS 2016