Ggtcf

Expressing logarithmic equations without logs

How to check whether module is loaded with custom configurations?

Why is gluten-free baking possible?

Confusion about Complex Continued Fraction

I can't die. Who am I?

In the late 1940’s to early 1950’s what technology was available that could melt a LOT of ice?

Does an unused member variable take up memory?

Can one live in the U.S. and not use a credit card?

Having the player face themselves after the mid-game

What stops an assembly program from crashing the operating system?

Which classes are needed to have access to every spell in the PHB?

Was it really inappropriate to write a pull request for the company I interviewed with?

What ability score modifier does a javelin's damage use?

Is there a difference between equilibrium and steady state?

Has a sovereign Communist government ever run, and conceded loss, on a fair election?

Does "Until when" sound natural for native speakers?

Specifying a starting column with colortbl package and xcolor

Why is there an extra space when I type "ls" in the Desktop directory?

Do items de-spawn?

Is it possible to avoid unpacking when merging Association?

What problems would a superhuman have whose skin is constantly hot?

What can I do if someone tampers with my SSH public key?

What do *foreign films* mean for an American?

What materials can be used to make a humanoid skin warm?

How to plot slope from a simple perceptron

0

I want to plot the slope y = mx+b when the weights change but i don't know how to get the value of m and b

Here is the code:

import numpy as np
import matplotlib.pyplot as plt

def sign(x):
 return 1 if x > 0 else 0

def get_mse(predicted_data, targets):
 error = predicted_data - targets
 return np.square(error).sum()/len(targets)

fit_data = np.array([[1,0,0],
 [1,0,1],
 [1,1,0],
 [1,1,1],])

targets = np.array([0,0,0,1])
weights = np.array([0,0,0])
lr = 1
epochs = 10

mse_hist = []

for _ in range(epochs):
 model_outputs = []
 for i in range(len(targets)):
 y = (fit_data[i] * weights).sum()
 y = sign(y)
 error = targets[i] - y
 weights = weights + fit_data[i] * error * lr

 model_outputs.append(y)
 mse = get_mse(model_outputs, targets)
 mse_hist.append(mse)

Here the plot of the slope should be, at least that's what i think so

 print("Weights:", weights)
 print("Mse:", mse_hist[-1])
 plt.plot(mse_hist)
 plt.xlabel('Iterations')
 plt.ylabel('Mean Squared Error')
 plt.pause(0.5)

plt.show()

input_data = ([1,1,1])
prediction = (input_data * weights).sum()
prediction = sign(prediction)
print("Prediction:", prediction)

Thanks for the help

python-3.x neural-network google-colaboratory perceptron

share|improve this question

edited Mar 7 at 5:17

Rodrigo Arce Villa

asked Mar 6 at 8:00

Rodrigo Arce VillaRodrigo Arce Villa

33

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  Please fix indentation at bottom of first snippet. I'm guessing you want to indent into the loop, but I am unsure.
  
  – kabanus
  Mar 6 at 8:04
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  oh, sorry i didn't notice it, i have fixed it Thanks
  
  – Rodrigo Arce Villa
  Mar 7 at 5:17
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  What do you consider as variabels in y = mx+b? Two guesses: 1) your perceptron output is fit_data[i] * weights, there is no b. 2) you are trying to visualise weights + fit_data[i] * error * lr? Is there the original code/tutorial link that you are using as source?
  
  – EPo
  Mar 7 at 6:56
  

  
  
  
  

add a comment | 

0

I want to plot the slope y = mx+b when the weights change but i don't know how to get the value of m and b

Here is the code:

import numpy as np
import matplotlib.pyplot as plt

def sign(x):
 return 1 if x > 0 else 0

def get_mse(predicted_data, targets):
 error = predicted_data - targets
 return np.square(error).sum()/len(targets)

fit_data = np.array([[1,0,0],
 [1,0,1],
 [1,1,0],
 [1,1,1],])

targets = np.array([0,0,0,1])
weights = np.array([0,0,0])
lr = 1
epochs = 10

mse_hist = []

for _ in range(epochs):
 model_outputs = []
 for i in range(len(targets)):
 y = (fit_data[i] * weights).sum()
 y = sign(y)
 error = targets[i] - y
 weights = weights + fit_data[i] * error * lr

 model_outputs.append(y)
 mse = get_mse(model_outputs, targets)
 mse_hist.append(mse)

Here the plot of the slope should be, at least that's what i think so

 print("Weights:", weights)
 print("Mse:", mse_hist[-1])
 plt.plot(mse_hist)
 plt.xlabel('Iterations')
 plt.ylabel('Mean Squared Error')
 plt.pause(0.5)

plt.show()

input_data = ([1,1,1])
prediction = (input_data * weights).sum()
prediction = sign(prediction)
print("Prediction:", prediction)

Thanks for the help

python-3.x neural-network google-colaboratory perceptron

share|improve this question

edited Mar 7 at 5:17

Rodrigo Arce Villa

asked Mar 6 at 8:00

Rodrigo Arce VillaRodrigo Arce Villa

33

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  Please fix indentation at bottom of first snippet. I'm guessing you want to indent into the loop, but I am unsure.
  
  – kabanus
  Mar 6 at 8:04
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  oh, sorry i didn't notice it, i have fixed it Thanks
  
  – Rodrigo Arce Villa
  Mar 7 at 5:17
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  What do you consider as variabels in y = mx+b? Two guesses: 1) your perceptron output is fit_data[i] * weights, there is no b. 2) you are trying to visualise weights + fit_data[i] * error * lr? Is there the original code/tutorial link that you are using as source?
  
  – EPo
  Mar 7 at 6:56
  

  
  
  
  

add a comment | 

I want to plot the slope y = mx+b when the weights change but i don't know how to get the value of m and b

Here is the code:

import numpy as np
import matplotlib.pyplot as plt

def sign(x):
 return 1 if x > 0 else 0

def get_mse(predicted_data, targets):
 error = predicted_data - targets
 return np.square(error).sum()/len(targets)

fit_data = np.array([[1,0,0],
 [1,0,1],
 [1,1,0],
 [1,1,1],])

targets = np.array([0,0,0,1])
weights = np.array([0,0,0])
lr = 1
epochs = 10

mse_hist = []

for _ in range(epochs):
 model_outputs = []
 for i in range(len(targets)):
 y = (fit_data[i] * weights).sum()
 y = sign(y)
 error = targets[i] - y
 weights = weights + fit_data[i] * error * lr

 model_outputs.append(y)
 mse = get_mse(model_outputs, targets)
 mse_hist.append(mse)

Here the plot of the slope should be, at least that's what i think so

 print("Weights:", weights)
 print("Mse:", mse_hist[-1])
 plt.plot(mse_hist)
 plt.xlabel('Iterations')
 plt.ylabel('Mean Squared Error')
 plt.pause(0.5)

plt.show()

input_data = ([1,1,1])
prediction = (input_data * weights).sum()
prediction = sign(prediction)
print("Prediction:", prediction)

Thanks for the help

python-3.x neural-network google-colaboratory perceptron

share|improve this question

edited Mar 7 at 5:17

Rodrigo Arce Villa

asked Mar 6 at 8:00

Rodrigo Arce VillaRodrigo Arce Villa

33

import numpy as np
import matplotlib.pyplot as plt

def sign(x):
 return 1 if x > 0 else 0

def get_mse(predicted_data, targets):
 error = predicted_data - targets
 return np.square(error).sum()/len(targets)

fit_data = np.array([[1,0,0],
 [1,0,1],
 [1,1,0],
 [1,1,1],])

targets = np.array([0,0,0,1])
weights = np.array([0,0,0])
lr = 1
epochs = 10

mse_hist = []

for _ in range(epochs):
 model_outputs = []
 for i in range(len(targets)):
 y = (fit_data[i] * weights).sum()
 y = sign(y)
 error = targets[i] - y
 weights = weights + fit_data[i] * error * lr

 model_outputs.append(y)
 mse = get_mse(model_outputs, targets)
 mse_hist.append(mse)

 print("Weights:", weights)
 print("Mse:", mse_hist[-1])
 plt.plot(mse_hist)
 plt.xlabel('Iterations')
 plt.ylabel('Mean Squared Error')
 plt.pause(0.5)

plt.show()

input_data = ([1,1,1])
prediction = (input_data * weights).sum()
prediction = sign(prediction)
print("Prediction:", prediction)

share|improve this question

edited Mar 7 at 5:17

Rodrigo Arce Villa

asked Mar 6 at 8:00

Rodrigo Arce VillaRodrigo Arce Villa

33

share|improve this question

edited Mar 7 at 5:17

Rodrigo Arce Villa

asked Mar 6 at 8:00

Rodrigo Arce VillaRodrigo Arce Villa

33

asked Mar 6 at 8:00

Rodrigo Arce VillaRodrigo Arce Villa

33

asked Mar 6 at 8:00

Rodrigo Arce VillaRodrigo Arce Villa

33