Random Graph-Based Neuromorphic Learning with a Layer-Weaken Structure

11/17/2021
by   Ruiqi Mao, et al.
9

Unified understanding of neuro networks (NNs) gets the users into great trouble because they have been puzzled by what kind of rules should be obeyed to optimize the internal structure of NNs. Considering the potential capability of random graphs to alter how computation is performed, we demonstrate that they can serve as architecture generators to optimize the internal structure of NNs. To transform the random graph theory into an NN model with practical meaning and based on clarifying the input-output relationship of each neuron, we complete data feature mapping by calculating Fourier Random Features (FRFs). Under the usage of this low-operation cost approach, neurons are assigned to several groups of which connection relationships can be regarded as uniform representations of random graphs they belong to, and random arrangement fuses those neurons to establish the pattern matrix, markedly reducing manual participation and computational cost without the fixed and deep architecture. Leveraging this single neuromorphic learning model termed random graph-based neuro network (RGNN) we develop a joint classification mechanism involving information interaction between multiple RGNNs and realize significant performance improvements in supervised learning for three benchmark tasks, whereby they effectively avoid the adverse impact of the interpretability of NNs on the structure design and engineering practice.

READ FULL TEXT

page 4

page 6

page 7

page 9

research
01/01/2019

MaD: Mapping and debugging framework for implementing deep neural network onto a neuromorphic chip with crossbar array of synapses

Neuromorphic systems or dedicated hardware for neuromorphic computing is...
research
10/26/2019

Bayesian Graph Convolutional Neural Networks Using Non-Parametric Graph Learning

Graph convolutional neural networks (GCNN) have been successfully applie...
research
03/27/2023

Open the box of digital neuromorphic processor: Towards effective algorithm-hardware co-design

Sparse and event-driven spiking neural network (SNN) algorithms are the ...
research
07/10/2015

A Trainable Neuromorphic Integrated Circuit that Exploits Device Mismatch

Random device mismatch that arises as a result of scaling of the CMOS (c...
research
07/21/2019

Shallow Unorganized Neural Networks using Smart Neuron Model for Visual Perception

The recent success of Deep Neural Networks (DNNs) has revealed the signi...
research
05/10/2020

Optimal Distribution of Spiking Neurons Over Multicore Neuromorphic Processors

In a multicore neuromorphic processor embedding a learning algorithm, a ...
research
12/24/2020

Sensitivity – Local Index to Control Chaoticity or Gradient Globally

In this paper, we propose a fully local index named "sensitivity" for ea...

Please sign up or login with your details

Forgot password? Click here to reset