Skip to main content

Machine Learning Concept

 What is Machine Learning? 

Machine Learning is a first stage of Artificial Intelligence, where programmers create algorithms (models) and provide data which allows machines to learn by themselves. Fields where machine learning used today are Robotics, Recommendation System, Virtual Reality, Speech to Text and Text to Speech conversion, Face Recognition also Image processing and Motion analyzing.

So far, we have created approx 40000 Exabytes of data. we can only process only 10,000 Exabytes of data while machines can process 20,000 Exabytes of data. Hence, if we want to process all 40,000 Exabytes of data, then we need to use machine learning algorithms. 

 We encounter machine learning models every day in to days life. for example, when Netflix recommends a show, they used a model based on what users have watched to predict what they would like. When Amazon chooses a price for an item, they used a model based on how similar items have sold in the past.



Machine Learning : sub field of Artificial Intelligence, to create algorithms which allows machines to learn by themselves. low consumption of time and less work flow than traditional coding, making rule and logic

Artificial Intelligence :   Intelligence represented by machine ; the field where machine can behave like humans.

Deep Learning : sub field of Machine Learning, uses neural networks as a learning and work on multiple layers. Don't need to feature extraction ; use for large and complex data like images and videos
task : image classification , text embedding

Supervised learning : train both featured and labeled data

Unsupervised learning : train only featured data, there is no labeled data

Reinforcement learning : machines learn through feedback and experiences, using a trial-and-error method

Feature scaling : standardize or equalize the numeric features

Regression model :  used for predicting a real value for continuous type data. mean , median

Classification : categorical data. mode , voting

Gradient Descent : An optimization algorithm for finding a local minima of a differentiable function. Simply used to find the values of a coefficients or weight that minimize a cost function as far as possible.

Probability : is the quantity mostly familiar with which deals predicting new data given a known model
'posterior probabilities' : because they are determined after the results of the model are known. 

Likelihood : is deals with fitting models given some known data  are the posterior values for the fixed data points with distributions that can be moved. assume that already assumed, indicate how likely the event under consideration is to occur given each and every a prior probability.

Prior probabilities :  exist before we gain any information from the model itself.


Read More...

Comments

Post a Comment

Popular posts from this blog

Classification & Confusion Matrix & Accuracy Paradox

Classification  work on voting the object belongs from which classes has more probability  There are two types of classification : Binary classification : There are two classes we have ex: male-female , cat-dog , yes-not  Multiple classification :   There are classes more than two we have ex: traffic signs , face recognition , flower race  , Digit Recognition Confusion matrix :  Confusion matrix is one type of technique to evaluate the model accuracy for classification problem. In this technique we consider how many of positive and negative data points we predict correctly. The main consideration terms are accuracy, precision and recall The accuracy was an appealing matric, because it was a single number. Here precision and recall(sensitivity) are two numbers. So to get the final score (accuracy) of our model we use F1 score, so that we have a single number. Here is the F1 score's mathematical formula: F1 = 2x precision x recall / (precision ...
Post a Comment
Read more

Multiple classification from many of directories

  # %%  Import nessacary libraries import  numpy  as  np import  pandas  as  pd import  cv2 import  matplotlib.pyplot  as  plt import  os import  glob # %%   Keras Tensorflow libraries from  keras  import  layers from  keras.models  import  Model from  keras.optimizers  import  RMSprop , Adam , Nadam from  keras.preprocessing.image  import  ImageDataGenerator from  keras.layers  import  Input, BatchNormalization, Dense, Dropout, Conv2D, Flatten, GlobalAveragePooling2D, LeakyReLU from  keras.preprocessing.image  import  ImageDataGenerator, img_to_array, load_img # %%  Path path  =   r 'G:/Machine Learning/Project/Lego Mnifigures Classification/dataset' open_dir  =  os....
Post a Comment
Read more

Digit Recognition

Here you can import digit dataset from scikit learn library which is in-built, So you don't need to download from other else Note: If you use visual code, I recommend you to turn your color theme to Monokai because it has a few extra and important keyword and attractive colors than other theme.   # %%  Import libraries import  numpy  as  np import  pandas  as  pd import  matplotlib.pyplot  as  plt import  random  # %%   Load dataset from  sklearn.datasets  import  load_digits dataset  =  load_digits() dataset.keys() output: d ict_keys(['data', 'target', 'target_names', 'images', 'DESCR']) You have to check all to direct print them Here DESCR is a description of dataset # %%   divide the dataset into input and target inputs  =  dataset.data target  =  dataset.target # %% ...
Post a Comment
Read more