Dendritic Tree

Dendritic trees, the branching structures of neurons, are increasingly recognized as crucial for neural computation, going beyond simple signal summation. Current research focuses on developing biologically-inspired artificial neural network models that incorporate dendritic nonlinearities and complex branching topologies, such as tree-based architectures and spiking neural networks with dendritic compartments, to improve efficiency and performance in machine learning tasks. These efforts aim to bridge the gap between biological and artificial neural networks, leading to more efficient and powerful algorithms for various applications, including brain-computer interfaces and neuromorphic computing. The improved understanding of dendritic computation promises advancements in both theoretical neuroscience and practical applications of artificial intelligence.

Papers

June 26, 2024

CoDA: Interactive Segmentation and Morphological Analysis of Dendroid Structures Exemplified on Stony Cold-Water Corals
Kira Schmitt, Jürgen Titschack, Daniel Baum
Interactive Segmentation Coral Reef Morphological Analysis Coda Detector Dendritic Tree Dendritic Like Structure Coral Video Segmentation

March 29, 2024

Biologically-Plausible Topology Improved Spiking Actor Network for Efficient Deep Reinforcement Learning
Duzhen Zhang, Qingyu Wang, Tielin Zhang, Bo Xu
Deep Reinforcement Learning Human Topology Dendritic Tree

March 4, 2024

Toward Neuromic Computing: Neurons as Autoencoders
Larry Bull
Supervised Autoencoder Back Propagation Single Neuron Level Auto Encoder Model Individual Neuron Neuromorphic Platform Dendritic Tree

February 26, 2024

ELiSe: Efficient Learning of Sequences in Structured Recurrent Networks
Laura Kriener, Kristin Völk, Ben von Hünerbein, Federico Benitez, Walter Senn, Mihai A. Petrovici
LeArning Abstract Development Activity Reservoir Computing Recurrent Network Kill Chaos Neural Structure Dendritic Tree

October 26, 2023

Neuromorphic Online Clustering and Classification
J. E. Smith
Classification Code Neuromorphic Architecture Online Clustering Neural Point Dendritic Tree Active Dendrite

June 21, 2023

Mitigating Communication Costs in Neural Networks: The Role of Dendritic Nonlinearity
Xundong Wu, Pengfei Zhao, Zilin Yu, Lei Ma, Ka-Wa Yip, Huajin Tang, Gang Pan, Tiejun Huang
Neural Network Integral Role Communication Cost Dendritic Tree Dendritic Like Structure Dendritic Neuron

June 14, 2023

The Expressive Leaky Memory Neuron: an Efficient and Expressive Phenomenological Neuron Model Can Solve Long-Horizon Tasks
Aaron Spieler, Nasim Rahaman, Georg Martius, Bernhard Schölkopf, Anna Levina
Neuron Model Long Horizon Task Leaky ReLU Dendritic Tree

June 7, 2023

Correlative Information Maximization: A Biologically Plausible Approach to Supervised Deep Neural Networks without Weight Symmetry
Bariscan Bozkurt, Cengiz Pehlevan, Alper T Erdogan
Large Scale Back Propagation Balancing Weight Biological Neural Network Supervised Deep Learning Dendritic Tree

May 25, 2023

Dendritic Integration Based Quadratic Neural Networks Outperform Traditional Aritificial Ones
Chongming Liu, Songting Li, Douglas Zhou
Brain Inspired Quadratic Neural Network Artificial Neural Network Neural Structure Dendritic Tree

November 21, 2022

Learning on tree architectures outperforms a convolutional feedforward network
Yuval Meir, Itamar Ben-Noam, Yarden Tzach, Shiri Hodassman, Ido Kanter
Neural Network LeArning Abstract Deep Learning Architecture Convolutional Layer Feed Forward Dendritic Tree

February 4, 2022

Backpropagation Neural Tree
Varun Ojha, Giuseppe Nicosia
Dendritic Tree Neural Tree

Dendritic Tree

Papers

CoDA: Interactive Segmentation and Morphological Analysis of Dendroid Structures Exemplified on Stony Cold-Water Corals

Biologically-Plausible Topology Improved Spiking Actor Network for Efficient Deep Reinforcement Learning

Toward Neuromic Computing: Neurons as Autoencoders

ELiSe: Efficient Learning of Sequences in Structured Recurrent Networks

Neuromorphic Online Clustering and Classification

Mitigating Communication Costs in Neural Networks: The Role of Dendritic Nonlinearity

The Expressive Leaky Memory Neuron: an Efficient and Expressive Phenomenological Neuron Model Can Solve Long-Horizon Tasks

Correlative Information Maximization: A Biologically Plausible Approach to Supervised Deep Neural Networks without Weight Symmetry

Dendritic Integration Based Quadratic Neural Networks Outperform Traditional Aritificial Ones

Learning on tree architectures outperforms a convolutional feedforward network

Backpropagation Neural Tree