activity
20182021
most citedInternal representation dynamics and geometry in recurrent neural networks

3 citations · 4 across the 4 of their papers we have counts for

collaborators
Showing cs.LGShow all

15 papers · 1 filter

cs.LG20232 cited

Inferring dynamic regulatory interaction graphs from time series data with perturbations

Dhananjay Bhaskar, Sumner Magruder, Edward De Brouwer +4

Complex systems are characterized by intricate interactions between entities that evolve dynamically over time. Accurate inference of these dynamic relationships is crucial for und…

cs.LG20223 cited

Reliability of CKA as a Similarity Measure in Deep Learning

MohammadReza Davari, Stefan Horoi, Amine Natik +3

Comparing learned neural representations in neural networks is a challenging but important problem, which has been approached in different ways. The Centered Kernel Alignment (CKA)…

cs.LG2021

Towards a Taxonomy of Graph Learning Datasets

Renming Liu, Semih Cantürk, Frederik Wenkel +10

Graph neural networks (GNNs) have attracted much attention due to their ability to leverage the intrinsic geometries of the underlying data. Although many different types of GNN mo…

cs.LG2021

Hierarchical graph neural nets can capture long-range interactions

Ladislav Rampášek, Guy Wolf

Graph neural networks (GNNs) based on message passing between neighboring nodes are known to be insufficient for capturing long-range interactions in graphs. In this project we stu…

cs.LG2021

Diffusion Earth Mover's Distance and Distribution Embeddings

Alexander Tong, Guillaume Huguet, Amine Natik +5

We propose a new fast method of measuring distances between large numbers of related high dimensional datasets called the Diffusion Earth Mover's Distance (EMD). We model the datas…

cs.LG20201 cited

Advantages of biologically-inspired adaptive neural activation in RNNs during learning

Victor Geadah, Giancarlo Kerg, Stefan Horoi +2

Dynamic adaptation in single-neuron response plays a fundamental role in neural coding in biological neural networks. Yet, most neural activation functions used in artificial netwo…