SLEAP: A deep learning system for multi-animal pose tracking

TD Pereira, N Tabris, A Matsliah, DM Turner, J Li… - Nature …, 2022 - nature.com
The desire to understand how the brain generates and patterns behavior has driven rapid
methodological innovation in tools to quantify natural animal behavior. While advances in …

tf. data: A machine learning data processing framework

DG Murray, J Simsa, A Klimovic, I Indyk - ar** DNN programs
with intricate control flow logic (eg, loops, branches, and recursion) has become increasingly …

Flan: an expressive and efficient datalog compiler for program analysis

S Abeysinghe, A Xhebraj, T Rompf - Proceedings of the ACM on …, 2024 - dl.acm.org
Datalog has gained prominence in program analysis due to its expressiveness and ease of
use. Its generic fixpoint resolution algorithm over relational domains simplifies the …

Lima: Fine-grained lineage tracing and reuse in machine learning systems

A Phani, B Rath, M Boehm - … of the 2021 International Conference on …, 2021 - dl.acm.org
Machine learning (ML) and data science workflows are inherently exploratory. Data
scientists pose hypotheses, integrate the necessary data, and run ML pipelines of data …

Backpropagation with callbacks: Foundations for efficient and expressive differentiable programming

F Wang, J Decker, X Wu, G Essertel… - Advances in Neural …, 2018 - proceedings.neurips.cc
Training of deep learning models depends on gradient descent and end-to-end
differentiation. Under the slogan of differentiable programming, there is an increasing …