
Revisiting Graph Neural Networks: All We Have is LowPass Filters
Graph neural networks have become one of the most important techniques t...
read it

Machine Learning for Scent: Learning Generalizable Perceptual Representations of Small Molecules
Predicting the relationship between a molecule's structure and its odor ...
read it

Deep Iterative and Adaptive Learning for Graph Neural Networks
In this paper, we propose an endtoend graph learning framework, namely...
read it

Graph Structure of Neural Networks
Neural networks are often represented as graphs of connections between n...
read it

A Unified Deep Learning Formalism For Processing Graph Signals
Convolutional Neural Networks are very efficient at processing signals d...
read it

Robust neural circuit reconstruction from serial electron microscopy with convolutional recurrent networks
Recent successes in deep learning have started to impact neuroscience. O...
read it

Rethinking Table Parsing using Graph Neural Networks
Document structure analysis, such as zone segmentation and table parsing...
read it
Generalizable Machine Learning in Neuroscience using Graph Neural Networks
Although a number of studies have explored deep learning in neuroscience, the application of these algorithms to neural systems on a microscopic scale, i.e. parameters relevant to lower scales of organization, remains relatively novel. Motivated by advances in wholebrain imaging, we examined the performance of deep learning models on microscopic neural dynamics and resulting emergent behaviors using calcium imaging data from the nematode C. elegans. We show that neural networks perform remarkably well on both neuronlevel dynamics prediction, and behavioral state classification. In addition, we compared the performance of structure agnostic neural networks and graph neural networks to investigate if graph structure can be exploited as a favorable inductive bias. To perform this experiment, we designed a graph neural network which explicitly infers relations between neurons from neural activity and leverages the inferred graph structure during computations. In our experiments, we found that graph neural networks generally outperformed structure agnostic models and excel in generalization on unseen organisms, implying a potential path to generalizable machine learning in neuroscience.
READ FULL TEXT
Comments
There are no comments yet.