• No products in the cart.

Students

3

Lectures

127

Course Duration

Unlimited Duration

Updated

March 9, 2023

Artificial Intelligence is a technique for building systems that mimic human behavior or decision-making. Machine Learning is a subset of AI that uses data to solve tasks. These solvers are trained models of data that learn based on the information provided to them.
Profile Photo
Annapurna Singh
0
24

Courses

490

Students

Machine learning is a branch of artificial intelligence (AI) and computer science which focuses on the use of data and algorithms to imitate the way that humans learn, gradually improving its accuracy.Artificial intelligence (AI) and machine learning are often used interchangeably, but machine learning is a subset of the broader category of AI.

Put in context, artificial intelligence refers to the general ability of computers to emulate human thought and perform tasks in real-world environments, while machine learning refers to the technologies and algorithms that enable systems to identify patterns, make decisions, and improve themselves through experience and data.

Computer programmers and software developers enable computers to analyze data and solve problems — essentially, they create artificial intelligence systems — by applying tools such as:

  • Machine learning
  • Deep learning
  • Neural networks
  • Computer vision
  • Natural language processing


    • What is machine learning? Unlimited
    • Why this Course? Unlimited
    • What is the difference between artificial intelligence and machine learning? Unlimited
    • Humans use the remember-formulate Unlimited
    • How do humans think? Unlimited
    • How do machines think? Unlimited
    • Summary Unlimited
    • Module 1. What is AI and machine learning Deck Unlimited
    • Types of machine learning Unlimited
    • What is the difference between labelled and unlabelled data? Unlimited
    • What is supervised learning? Unlimited
    • Regression models predict numbers Unlimited
    • Classification models predict a state Unlimited
    • What is unsupervised learning? Unlimited
    • Clustering algorithms split a dataset into similar groups Unlimited
    • Dimensionality reduction simplifies data Unlimited
    • What is reinforcement learning? Unlimited
    • Summary Unlimited
    • Linear regression Unlimited
    • The problem Unlimited
    • The remember step Unlimited
    • the linear regression algorithm Unlimited
    • A simple trick Unlimited
    • The square trick Unlimited
    • Using the linear regression algorithm in our dataset Unlimited
    • Summary Unlimited
    • Optimizing the training process Unlimited
    • The model evaluation graph Unlimited
    • Regularization Unlimited
    • Movie recommendations Unlimited
    • Measuring how complex a model Unlimited
    • The Regularization parameter Unlimited
    • An intuitive way to see regularization Unlimited
    • Summary Unlimited
    • The perceptron algorithm Unlimited
    • The problem Unlimited
    • Simple sentiment analysis classifier Unlimited
    • A slightly more complicated planet Unlimited
    • More general cases Unlimited
    • The error function Unlimited
    • The perceptron trick Unlimited
    • The perceptron algorithm Unlimited
    • Coding the perceptron trick Unlimited
    • Applications of the perceptron algorithm Unlimited
    • Summary Unlimited
    • Logistic regression Unlimited
    • The sigmoid function Unlimited
    • The error functions Unlimited
    • More on the log loss error function Unlimited
    • An example with a discrete perceptron & continuous perceptron Unlimited
    • Coding the logistic regression algorithm Unlimited
    • The softmax function Unlimited
    • Summary Unlimited
    • Accuracy and its friends Unlimited
    • Coronavirus and spam email Unlimited
    • How to fix the accuracy problem? Unlimited
    • The confusion matrix Unlimited
    • how many did we correctly classify? Unlimited
    • CALCULATING THE F- SCORE Unlimited
    • A metric that tells us how good our model is Unlimited
    • the ROC curve Unlimited
    • Summary Unlimited
    • The naive Bayes algorithm Unlimited
    • A story with Bayes Theorem Unlimited
    • Spam detection model Unlimited
    • The probability that any email is spam Unlimited
    • What the math just happened? Unlimited
    • What about two words? Unlimited
    • Building a spam detection model Unlimited
    • Data preprocessing Unlimited
    • Finding the priors Unlimited
    • Finding the posteriors with Bayes theorem Unlimited
    • Summary Unlimited
    • Decision trees Unlimited
    • The problem Unlimited
    • First step to build the model Unlimited
    • Next and final step Unlimited
    • Building the tree Unlimited
    • Accuracy Unlimited
    • Gini impurity Unlimited
    • Building our decision tree using Gini index Unlimited
    • Features with more categories, such as Dog/Cat/Bird Unlimited
    • Continuous features, such as a number Unlimited
    • Coding a decision tree with sklearn Unlimited
    • A slightly larger example Unlimited
    • Summary Unlimited
    • Neural Networks Unlimited
    • The problem Unlimited
    • Perceptrons and how to combine them Unlimited
    • A trick to improve our training Unlimited
    • The architecture of a neural network Unlimited
    • Training neural networks Unlimited
    • How to code a neural network in Keras Unlimited
    • Other more complicated architectures and some sci-fi applications Unlimited
    • Summary Unlimited
    • Combining models to maximize results Ensemble learning Unlimited
    • Why an ensemble of learners? Unlimited
    • Building random forests by joining several trees Unlimited
    • Coding a random forest in sklearn Unlimited
    • A big picture of AdaBoost Unlimited
    • A detailed (mathematical) picture of AdaBoost Unlimited
    • Coding AdaBoost in Sklearn Unlimited
    • Summary Unlimited
    • Support vector machines and the kernel method Unlimited
    • A new error function Unlimited
    • Classification error function Unlimited
    • Distance error function Unlimited
    • The C parameter Unlimited
    • Coding a simple SVM Unlimited
    • The kernel method Unlimited
    • The radial basis function (rbf) kernel Unlimited
    • Radial basis functions Unlimited
    • The gamma parameter Unlimited
    • Summary Unlimited
    • Putting it in practice Unlimited
    • The features of our dataset Unlimited
    • Using pandas to load the dataset Unlimited
    • Cleaning up our dataset Unlimited
    • Dropping columns with missing data Unlimited
    • Turning categorical data into numerical data Unlimited
    • Binning Unlimited
    • Saving for future use Unlimited
    • Training our models Unlimited
    • TESTING EACH MODEL’S ACCURACY Unlimited
    • Grid search Unlimited
    • Using K-fold cross-validation Unlimited
    • Summary Unlimited

Popular Courses

top
Managed by Ernesto.net © 2021. All rights reserved.