Weight and bias initialization routines for Sigmoidal Feedforward Network

2020 ◽  
Author(s):  
Apeksha Mittal ◽  
Amit Prakash Singh ◽  
Pravin Chandra
Keyword(s):  
Feedforward Network

Adding Lateral Inhibition to a Simple Feedforward Network Enables It to Perform Exclusive-Or

1998 ◽  
Vol 10 (2) ◽  
pp. 277-280
Author(s):  
Leslie S. Smith
Keyword(s):  
Lateral Inhibition ◽  
Recurrent Network ◽  
External Input ◽  
Output Function ◽  
Output Unit ◽  
Feedforward Network ◽  
Point Attractor ◽  
Exclusive Or

A simple laterally inhibited recurrent network that implementse xclusive-or is demonstrated. The network consists of two mutually inhibitory units with logistic output function, each receiving one external input and each connected to a simple threshold output unit. The mutually inhibitory units settle into a point attractor. We investigate the range of steepness of the logistic and the range of inhibitory weights for which the network can perform exclusive-or.

Toward heterogeneity in feedforward network with synaptic delays based on FitzHugh–Nagumo model

2018 ◽  
Vol 32 (01) ◽  
pp. 1750274 ◽  
Author(s):  
Ying-Mei Qin ◽  
Cong Men ◽  
Jia Zhao ◽  
Chun-Xiao Han ◽  
Yan-Qiu Che
Keyword(s):  
Neuronal Excitability ◽  
Temporal Coding ◽  
Feedforward Network ◽  
Firing Patterns ◽  
In Vivo Experiments ◽  
Connection Probability ◽  
Rate Coding

We focus on the role of heterogeneity on the propagation of firing patterns in feedforward network (FFN). Effects of heterogeneities both in parameters of neuronal excitability and synaptic delays are investigated systematically. Neuronal heterogeneity is found to modulate firing rates and spiking regularity by changing the excitability of the network. Synaptic delays are strongly related with desynchronized and synchronized firing patterns of the FFN, which indicate that synaptic delays may play a significant role in bridging rate coding and temporal coding. Furthermore, quasi-coherence resonance (quasi-CR) phenomenon is observed in the parameter domain of connection probability and delay-heterogeneity. All these phenomena above enable a detailed characterization of neuronal heterogeneity in FFN, which may play an indispensable role in reproducing the important properties of in vivo experiments.

scholarly journals A NEW MULTILAYER FEEDFORWARD NETWORK BASED ON TRIMMED MEAN NEURON MODEL

2015 ◽  
Vol 25 (6) ◽  
pp. 587-602 ◽  
Author(s):  
Ufuk Yolcu ◽  
Eren Bas ◽  
Erol Egrioglu ◽  
Cagdas Hakan Aladag
Keyword(s):  
Neuron Model ◽  
Feedforward Network ◽  
Trimmed Mean ◽  
Multilayer Feedforward Network

scholarly journals Detecting Generic Music Features with Single Layer Feedforward Network using Unsupervised Hebbian Computation

2020 ◽  
Vol 12 (2) ◽  
pp. 1-20
Author(s):  
Sourav Das ◽  
Anup Kumar Kolya
Keyword(s):  
Neural Network ◽  
Feature Detection ◽  
Feature Recognition ◽  
Hebbian Learning ◽  
Feature Learning ◽  
Single Layer ◽  
Feedforward Network ◽  
New Information ◽  
Unsupervised Training ◽  
And Performance

In this work, the authors extract information on distinct baseline features from a popular open-source music corpus and explore new recognition techniques by applying unsupervised Hebbian learning techniques on our single-layer neural network using the same dataset. They show the detailed empirical findings to simulate how such an algorithm can help a single layer feedforward network in training for music feature learning as patterns. The unsupervised training algorithm enhances the proposed neural network to achieve an accuracy of 90.36% for successful music feature detection. For comparative analysis against similar tasks, they put their results with the likes of several previous benchmark works. They further discuss the limitations and thorough error analysis of the work. They hope to discover and gather new information about this particular classification technique and performance, also further understand future potential directions that could improve the art of computational music feature recognition.

Diffusion Approximation of State-Dependent G-Networks Under Heavy Traffic

2008 ◽  
Vol 45 (2) ◽  
pp. 347-362 ◽  
Author(s):  
Saul C. Leite ◽  
Marcelo D. Fragoso
Keyword(s):  
Differential Equation ◽  
Stochastic Differential Equation ◽  
Diffusion Approximation ◽  
Numerical Experiments ◽  
Heavy Traffic ◽  
Weak Sense ◽  
Feedforward Network ◽  
State Dependent ◽  
Number Of Customers

This paper is concerned with the characterization of weak-sense limits of state-dependent G-networks under heavy traffic. It is shown that, for a certain class of networks (which includes a two-layer feedforward network and two queues in tandem), it is possible to approximate the number of customers in the queue by a reflected stochastic differential equation. The benefits of such an approach are that it describes the transient evolution of these queues and allows the introduction of controls, inter alia. We illustrate the application of the results with numerical experiments.

scholarly journals Synaptic mechanisms for motor variability in a feedforward network

2020 ◽  
Vol 6 (25) ◽  
pp. eaba4856
Author(s):  
Guo Zhang ◽  
Ke Yu ◽  
Tao Wang ◽  
Ting-Ting Chen ◽  
Wang-Ding Yuan ◽  
...  
Keyword(s):  
State Transition ◽  
Behavioral Variability ◽  
Noise Levels ◽  
Feedforward Network ◽  
Rhythmic Motor ◽  
System A ◽  
Synaptic Noise ◽  
Variable Activity ◽  
Transition Points ◽  
Synaptic Mechanisms

Behavioral variability often arises from variable activity in the behavior-generating neural network. The synaptic mechanisms underlying this variability are poorly understood. We show that synaptic noise, in conjunction with weak feedforward excitation, generates variable motor output in the Aplysia feeding system. A command-like neuron (CBI-10) triggers rhythmic motor programs more variable than programs triggered by CBI-2. CBI-10 weakly excites a pivotal pattern-generating interneuron (B34) strongly activated by CBI-2. The activation properties of B34 substantially account for the degree of program variability. CBI-10– and CBI-2–induced EPSPs in B34 vary in amplitude across trials, suggesting that there is synaptic noise. Computational studies show that synaptic noise is required for program variability. Further, at network state transition points when synaptic conductance is low, maximum program variability is promoted by moderate noise levels. Thus, synaptic strength and noise act together in a nonlinear manner to determine the degree of variability within a feedforward network.

Sign in / Sign up

Export Citation Format

Share Document