Search Results for author: Thomas Trappenberg

Found 6 papers, 1 papers with code

LogAvgExp Provides a Principled and Performant Global Pooling Operator

no code implementations2 Nov 2021 Scott C. Lowe, Thomas Trappenberg, Sageev Oore

We seek to improve the pooling operation in neural networks, by applying a more theoretically justified operator.

Logical Activation Functions: Logit-space equivalents of Probabilistic Boolean Operators

no code implementations22 Oct 2021 Scott C. Lowe, Robert Earle, Jason d'Eon, Thomas Trappenberg, Sageev Oore

Consequently, we construct efficient approximations named $\text{AND}_\text{AIL}$ (the AND operator Approximate for Independent Logits), $\text{OR}_\text{AIL}$, and $\text{XNOR}_\text{AIL}$, which utilize only comparison and addition operations, have well-behaved gradients, and can be deployed as activation functions in neural networks.

Compositional Zero-Shot Learning Image Classification +1

Representational Rényi heterogeneity

1 code implementation10 Dec 2019 Abraham Nunes, Martin Alda, Timothy Bardouille, Thomas Trappenberg

Unfortunately, numbers equivalent heterogeneity measures for non-categorical data require {a priori} (A) categorical partitioning and (B) pairwise distance measurement on the observable data space, thereby precluding application to problems with ill-defined categories or where semantically relevant features must be learned as abstractions from some data.

Skin cancer detection based on deep learning and entropy to detect outlier samples

no code implementations10 Sep 2019 Andre G. C. Pacheco, Abder-Rahman Ali, Thomas Trappenberg

We describe our methods that achieved the 3rd and 4th places in tasks 1 and 2, respectively, at ISIC challenge 2019.

Classifier with Hierarchical Topographical Maps as Internal Representation

no code implementations20 Dec 2014 Thomas Trappenberg, Paul Hollensen, Pitoyo Hartono

In this study we want to connect our previously proposed context-relevant topographical maps with the deep learning community.

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