Questions tagged [convergence]
303 questions
1
vote
0 answers
Lax-Wendroff order of accuracy on Burgers equation
Statement of the problem
Is it possible to achieve the second order of convergence (OOC)
of Lax-Wendroff scheme applied to solve
inviscid Burgers equations with discontinuous
initial data? If no, then how to achieve OOC of 2nd order in quasilinear…
Oleg Kravchenko
- 11
- 2
1
vote
1 answer
Secant Method not converging, Matlab
I have created a program in Matlab to try to find the root of f(x) = exp(2x) + 3x - 4 (the function "fopg1" in my code). My code is as follows:
format long
tic;
for dum=1:1000;
x(1) = 0.5;
x(2) = 0.4;
err_tol = 1e-8;
iteration(1) =…
p.late
- 31
- 6
1
vote
1 answer
Converge on Best Combination of Elements
You have $10,000 to invest in stocks. You are given a list of 200 stocks, and are told to select 8 of those stocks to buy, and also indicate how many of those stocks you want to buy. You cannot spend more than $2,500 on a single stock alone, and…
Kael Eppcohen
- 177
- 1
- 2
- 10
1
vote
1 answer
Strange convergence in simple Neural Network
I've been struggling for some time with building a simplistic NN in Java. I've been working on and off on this project for a few months and I wanna finish it. My main issue is that I dunno how to implement backpropagation correctly (all sources use…
tudor balus
- 149
- 2
- 10
1
vote
0 answers
Error for convergence for Runge-Kutta in Python
I have this piece of code (I put just a part of it) in Python:
from __future__ import division
import numpy as np
from pylab import *
from numpy import linalg as LA
a =…
JohnDoe122
- 638
- 9
- 23
1
vote
0 answers
"Freaky" convergence results and svd errors with Python statsmodels.tsa.arima_model
Freaky convergence results and svd errors with statsmodels.tsa.arima_model
Below is code that does not consistently run successfully or fail
for different settings of Transform Parameters ("transparams") and
for different precision levels.
If you…
Odil
- 25
- 5
1
vote
1 answer
training vgg on flowers dataset with keras, validation loss not changing
I am doing a little experiment on VGG network with keras.
The dataset I use is the flowers dataset with 5 classes including rose, sunflower, dandelion, tulip and daisy.
There is something I could not figure out:
When I used a small CNN network(not…
xiangxiao
- 21
- 4
1
vote
0 answers
SUR: Var-Cov matrix becomes singular if maxiter>1
Could you help me with following:
I try to run 5eq simultaneously but I have problems with singularity. My coefficients become very small if maxiter>1.
If maxiter>4, R returns the error code
“Error in .solve.dgC.lu(as(a, "dgCMatrix"), b = b, tol…
jones
- 11
- 2
1
vote
3 answers
What may be the reason for loss can not go further down when training multi-class nn using keras
I am training a multi-class neural network by using keras (backend is tensorflow). I will give my settings and some codes at final position.
The description is:
When I do 10 folders cross-validation, the training loss and validation loss goes down…
iloveml
- 29
- 1
- 3
1
vote
1 answer
Keras multiple outputs : Not converging
I am building a multiple output keras model
model1 = Model(input=ip, output=[main, aux])
model1.compile(optimizer='sgd', loss={'main':cutom_loss, 'aux':'mean_squared error'}, metrics='accuracy')
model1.fit(input_data, [main_output, aux_output],…
shaaa
- 503
- 1
- 4
- 16
1
vote
2 answers
Deep Neural Network training, why is the network training not converging?
I'm using MATCONVNET DagNN. Using AlexNet architecture. The last few layers of my architecture are
[
h612
- 544
- 2
- 11
1
vote
1 answer
SciPy.optimize.least_squares() Objective Function Questions
I am trying to minimize a highly non-linear function by optimizing three unknown parameters a, b, and c0. I'm attempting to replicate some governing equations of a casino roulette ball in Python 3.
Here is the link to the research…
ddm-j
- 403
- 1
- 3
- 18
1
vote
1 answer
R neuralnet taking huge number of steps for linear function f(x)=19x
So here is the scenario:-
I ran the following code which creates neural network (uses neuralnet package in R) to approximate the function f(x)=x^2:-
set.seed(2016);
rm(list=ls());
# Prepare Training…
Dhiraj
- 3,396
- 4
- 41
- 80
1
vote
0 answers
Rerun of Neural Network does not converge
I have a Convolutional Neural Network for semantic segmentation, implemented in Keras with Tensorflow backend. The architecture is of type encoder-decoder, using convolutional layers and max-pooling in the encoding part and deconvolutional layers…
Florin Lucaciu
- 91
- 4
1
vote
1 answer
Chef: Lazy evaluation of variable argument
We have a situation with Mapr client install. We would like to be able to copy a customized hive-site.xml file which resides under /opt/mapr/hive/hive-x.y/conf/ dir. The issue is that we wouldn't know the hive version number until after a set of…
S.A
- 85
- 1
- 1
- 7