Search Results for author: Jonathan Cohen

Found 10 papers, 4 papers with code

Beyond Transformers for Function Learning

no code implementations19 Apr 2023 Simon Segert, Jonathan Cohen

The ability to learn and predict simple functions is a key aspect of human intelligence.

Abstractors and relational cross-attention: An inductive bias for explicit relational reasoning in Transformers

1 code implementation1 Apr 2023 Awni Altabaa, Taylor Webb, Jonathan Cohen, John Lafferty

An extension of Transformers is proposed that enables explicit relational reasoning through a novel module called the Abstractor.

Inductive Bias Relational Reasoning

Generalization to Out-of-Distribution transformations

no code implementations29 Sep 2021 Shanka Subhra Mondal, Zack Dulberg, Jonathan Cohen

Humans understand a set of canonical geometric transformations (such as translation, rotation and scaling) that support generalization by being untethered to any specific object.

Translation

Modelling the development of counting with memory-augmented neural networks

1 code implementation21 May 2021 Zack Dulberg, Taylor Webb, Jonathan Cohen

Learning to count is an important example of the broader human capacity for systematic generalization, and the development of counting is often characterized by an inflection point when children rapidly acquire proficiency with the procedures that support this ability.

Systematic Generalization

Learning Canonical Transformations

no code implementations17 Nov 2020 Zachary Dulberg, Jonathan Cohen

Humans understand a set of canonical geometric transformations (such as translation and rotation) that support generalization by being untethered to any specific object.

Translation

Novel Edge and Density Metrics for Link Cohesion

no code implementations6 Mar 2020 Cetin Savkli, Catherine Schwartz, Amanda Galante, Jonathan Cohen

We present a new metric of link cohesion for measuring the strength of edges in complex, highly connected graphs.

Community Detection

Thyroid Cancer Malignancy Prediction From Whole Slide Cytopathology Images

no code implementations29 Mar 2019 David Dov, Shahar Kovalsky, Jonathan Cohen, Danielle Range, Ricardo Henao, Lawrence Carin

We consider preoperative prediction of thyroid cancer based on ultra-high-resolution whole-slide cytopathology images.

Multiple Instance Learning

cuDNN: Efficient Primitives for Deep Learning

3 code implementations3 Oct 2014 Sharan Chetlur, Cliff Woolley, Philippe Vandermersch, Jonathan Cohen, John Tran, Bryan Catanzaro, Evan Shelhamer

To address this problem, we have created a library similar in intent to BLAS, with optimized routines for deep learning workloads.

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