Search Results for author: Konrad Paul Kording

Found 9 papers, 3 papers with code

Learning domain-specific causal discovery from time series

no code implementations12 Sep 2022 Xinyue Wang, Konrad Paul Kording

Causal discovery (CD) from time-varying data is important in neuroscience, medicine, and machine learning.

Causal Discovery Meta-Learning +1

Nothing makes sense in deep learning, except in the light of evolution

no code implementations20 May 2022 Artem Kaznatcheev, Konrad Paul Kording

These deconstraints can be very helpful to both the particular algorithm in how it handles challenges in implementation and the overall field of DL in how easy it is for new ideas to be generated.

Hyperparameter Optimization

Do biological constraints impair dendritic computation?

1 code implementation4 Mar 2021 Ilenna Simone Jones, Konrad Paul Kording

Computations on the dendritic trees of neurons have important constraints.

Can Single Neurons Solve MNIST? The Computational Power of Biological Dendritic Trees

1 code implementation2 Sep 2020 Ilenna Simone Jones, Konrad Paul Kording

If dendritic trees can be nonlinear, biological neurons may have far more computational power than their artificial counterparts.

Neurons and Cognition

PDE constraints on smooth hierarchical functions computed by neural networks

no code implementations18 May 2020 Khashayar Filom, Konrad Paul Kording, Roozbeh Farhoodi

Our approach is a step toward formulating an algebraic description of functional spaces associated with specific neural networks, and may provide new, useful tools for constructing neural networks.

On functions computed on trees

no code implementations4 Apr 2019 Roozbeh Farhoodi, Khashayar Filom, Ilenna Simone Jones, Konrad Paul Kording

Any function can be constructed using a hierarchy of simpler functions through compositions.

Towards learning-to-learn

no code implementations1 Nov 2018 Benjamin James Lansdell, Konrad Paul Kording

Yet, in analogy with GOFAI, there is no reason to believe that humans are particularly good at defining such learning systems: we may expect learning itself to be better if we learn it.

BIG-bench Machine Learning

Efficient Multi-Person Pose Estimation with Provable Guarantees

no code implementations21 Nov 2017 Shaofei Wang, Konrad Paul Kording, Julian Yarkony

We test our approach on the MPII-Multiperson dataset, showing that our approach obtains comparable results with the state-of-the-art algorithm for joint node labeling and grouping problems, and that NBD achieves considerable speed-ups relative to a naive dynamic programming approach.

Multi-Person Pose Estimation

Cannot find the paper you are looking for? You can Submit a new open access paper.