Adapt Machine Learning Algorithm for overridden decisions

See also questions close to this topic

• Is there a way to name a tensorflow variable based on the value of another tensor-variable

  I want to be able to do the following

  n = str(tf.constant(2))
  v = tf.get_variable(name=n, shape=(256,256), initializer=tf.contrib.layers.xavier_initializer())
  

  but doing this is converts n to a string representation of tensorflow variable i.e

  "<tf.Tensor 'Const_4:0' shape=() dtype=int32>"
  
• MNIST data denormalising does not give me back the same

  This is part of my learning. I Understood the normalization is really helping to improve accuracy, and hence divided by 255 the mnist values. This will divide all the pixels by 255, and hence all the pixels of 28*28 will have the values in range from 0.0 to 1.0 .

  Now i tired to multiply the same with 255,this essentially means we should get the original value back. but when i display the picture, both the original and de-normalised pictures are different.

  (trainX, trainY), (testX, testY) = mnist.load_data()
  
  
  plt.subplot(2,2,1)
  plt.imshow(trainX[143])
  
  trainX /= 255
  
  plt.subplot(2,2,2)
  plt.imshow(trainX[143])
  
  
  trainX *= 255
  
  plt.subplot(2,2,3)
  plt.imshow(trainX[143])
  plt.show()
  

  OUtput:

  

  What am i missing?. Anything related to float and int data type of the input data?
• Which is best way of logging to file in C?

  I'm dealing with some deep learning model written in C.
  I wanna make some log file to check it later.
  log will be a line for each step.
  Each step will take few seconds.

  Sometimes I use keyboard interrupt to stop procedure

  Ways I thought are:

  // Way 1
  fp = fopen("log.txt", "a");
  for each step:
    fprintf(fp, "Log content\n");  
  flose(fp);
  

  I think way 1 may have lower file open/close overhead.
  But when I use keyboard interrupt to stop procedure, log file will be never closed properly.
  Is it OK?
  Or can pass file pointer as argument of the my own signal handler?

  // Way 2
  for each step:
    fp = fopen("log.txt", "a");
    fprintf(fp, "Log content\n");  
    fclose(fp);
  

  I think way 2 will have file open/close overhead for each step, could this slow down whole performance?
  Could it be crucial?

  // Way 3
  for each step:
    fprintf(buffer, "### Log content ###");  
  
    if step % 100 == 0:
      fp = fopen("log.txt", "a");
      fprintf(fp, buffer);  
      fclose(fp);
      flush buffer;
  

  for way 3, i consider 2 ways of buffer:
  1. array of string
  2. one long string with line feed between items

  Which way works best?
  It depends?

  Or if there is a good library for logging, could you recommend it to me?
• def get_data command not being recognized in python

  File "Predicting_stock", line 9
      def get_data(HistoricalQuotes.csv):
                                   ^
  SyntaxError: invalid syntax
  
• Is all the hype for AI/Machine Learning just hype or are there real opportunities in this field for everyone?

  I finished all the challenges on freecodecamp about a month and a half back. Since then I've worked on my own projects, cloned a couple. I really enjoy designing front end and writing backend equally. So I knew I would love to be a full-stack engineer. But lately, something else has been grabbing my attention. AI/Deep Learning/Machine Learning. I love everything about it. It's really cool to see the demos people upload, how they train their own neural networks. So I guess my question really is, is all the hype just hype or are there real opportunities in this field for everyone? What kind of salary(I understand it varies with the role, but what range of salary) can one expect? If I was to start learning Machine Learning/Deep Learning, how would you suggest I get started? Any input is much appreciated. Thank you!
• How to use minimum and maximum elements needed as input of a neural network?

  I'm trying to develop a neural network to predict the concrete number of certain elements that are part of a group of different elements, and I would like to use as inputs the minimum or/and maximum of its that could be available to do it.

  Example:

  PROBLEM

  I want to predict the number of carrots, onions and steaks that I would need to get the best dish for my nutritional needs.

  DATASET

  For that, I have in my dataset a group of recipes with the ingredients that compound each of it and its nutritional contributions.

  INPUTS

  Nutritional needs and available ingredients (a maximum).

  QUIZZ

  How should I use this data?

  [nutritional needs, ingredients needed, available ingredients(maximum)]

  • [nutritional needs] as X.

  • [ingredients needed] as hypothesis (ŷ).

  • How to deal with [available ingredients]?

  If I put it in the dataset with the same value of the [ingredients needed] could drive to the NN to bias that [ingredients needed] = [available ingredients]

  Thanks mates!