Stack Overflow
Stack Overflow

Questions tagged [sigmoid]

A sigmoid function is a mathematical function having an "S" shape (sigmoid curve). Often, sigmoid function refers to the special case of the logistic function defined by the formula S ( t ) = 1 / (1 + e^-t)

Sigmoid function (Wikipedia)

256 questions
1
vote
1 answer

Activation Function to help find anomalies

So I have one column of data, all the data there is normal and without any anomalies. Let’s say the data is scattered just like the picture bellow. K-means doesn’t really work on one column. I was given the advice to plot the data and then use an…
E199504
  • 425
  • 4
  • 12
1
vote
1 answer

Adding self starting values to an nls regression in R

I have existing code for fitting a sigmoid curve to data in R. How can I used selfstart (or another method) to automatically find start values for the regression? sigmoid = function(params, x) { params[1] / (1 + exp(-params[2] * (x -…
Andrew
  • 13
  • 3
1
vote
1 answer

Why is all of the different scatter points gathered closely in the same area in logistic regression graph?

I am currently doing a project where my team and I have to pick a dataset and apply some machine learning methods on it (SLR, MLR etc.), hence for me, I am doing logical regression. My dataset is related to the top hit songs on Spotify from…
Brendan
  • 19
  • 4
1
vote
2 answers

how to create a proper sigmoid curve?

I'm trying to use logistic regression on the popularity of hits songs on Spotify from 2010-2019 based on their durations and durability, whose data are collected from an .csv file. Basically, since the popularity values of each song is numerical, I…
Brendan
  • 19
  • 4
1
vote
0 answers

[Tensorflow 1.x]multi_label classification using BERT, Invalid argument: assertion failed: [`predictions` contains negative values]

I am trying to fine tune BERT for multi-label classification.I have my own data processor,and using a pretrained BERT.I add a finetuning layer at end of pretrained BERT for my task. I have a create model function that adds a finetuning layer at end…
Aditya Vartak
  • 380
  • 1
  • 13
1
vote
1 answer

Generating Random vectors and matrices for weights and bias

I am trying to know the chance of fire based on sensors x1 and x2. y=1 For this, I am trying to generate random vectors and matrices for weights and bias but I get an error. import numpy as np np.random.seed(seed=123) w1 = np.random.rand(4,2) b1…
Louis
  • 13
  • 5
1
vote
1 answer

ResUNet Segmentation output is bad although precision and recall values are higher on training and validation

I recently have implemented the RESUNET for a parasite segmentation on blood sample images. The model is described in this papaer, https://arxiv.org/pdf/1711.10684.pdf and here is the code…
Allan Ojeda
  • 11
  • 1
1
vote
0 answers

Fitting parameters from a multiparameter model are not calculated in a crescent order

I apologise for the somewhat confusing title. I am trying to fit a specific set of data (DATA FILE HERE) to a model comprised of three sigmoidal functions, as described below. def sigmoid(p,x): x01,c1,k1,x02,c2,k2,x03,c3,k3,y0=p y = (c1 /…
Rodrigosp96
  • 59
  • 1
  • 6
1
vote
0 answers

Why my prediction is not correct, although I have high accuracy and high validation accuracy?

I'm trying to develop a model, which could be able to recognize from the audio file if the trigger word ('hello') occurs in time. I used some ideas from NG Andrew's course from Coursera, but in my case something doesn't work. I've built a…
Ania
  • 51
  • 7
1
vote
2 answers

Sigmoid function prediction generates continuous number and error when exported to DF

I am new to tensorflow so I am trying to get my hands dirty by working on a binary classification problem on kaggle. I have trained the model using sigmoid function and got a very good accuracy when tested but when I try to export the prediction to…
Oluwole
  • 13
  • 1
  • 3
1
vote
1 answer

Why do both tf.nn.relu and tf.nn.sigmoid work the same in this custom estimator

This is the guide to make a custom estimator in TensorFlow: https://www.tensorflow.org/guide/custom_estimators The hidden layers are made using tf.nn.relu: # Build the hidden layers, sized according to the 'hidden_units' param. for units in…
Dee
  • 7,455
  • 6
  • 36
  • 70
1
vote
1 answer

How to change to sigmoid to learn multi-label classification

I'm trying to use 'inception resnet v2.py' to do a multi-label classification. I used sigmoid, but the result is not good. Do you know exactly where to…
AZDDKKS
  • 41
  • 1
  • 8
1
vote
0 answers

what difference does it make to use sigmoid over softmax? (autoencoders, keras)

I came across this problem while I was training an autoencoder neural network (multilayer perceptron). Here is my code # AE encoding arch model=Sequential() model.add(Dense(units= 2000, activation= 'relu', input_shape=…
yin yang
  • 97
  • 1
  • 8
1
vote
2 answers

Can sigmoid function graph be linear?

I think I have a "dumb" question. I have a python code that calculates sigmoid function: def sigmoid(z): return 1 / (1 + np.exp(-z)) I want to see what kind of graph is sigmoid function with given data, so I change my function to this: def…
Nikas Žalias
  • 1,594
  • 1
  • 23
  • 51
1
vote
1 answer

Tensorflow : result of training data(using sigmoid) came out reversely

I tried to train my data using 'Gradient Descent Algorithm' to minimize cost value, and strangely enough, result came out differently depending on the number of steps. Below is my training code: import tensorflow as tf X =…
SJ_Lee
  • 101
  • 1
  • 8
1 2 3
…
17 18