Implementing AI Algorithms from Scratch

Overview

What you'll learn

• Implement neural network components such as perceptrons, activation functions, and multi-layer structures
• Build unsupervised learning algorithms including k-means, mini-batch k-means, PCA, and DBSCAN
• Construct ensemble methods such as bagging, random forests, AdaBoost, and gradient boosting
• Develop optimization algorithms including stochastic gradient descent, momentum, RMSProp, and Adam
• Create classification models such as logistic regression, k-nearest neighbors, Naive Bayes, and decision trees
• Evaluate models and clusters using metrics such as AUC-ROC, homogeneity, completeness, and v-measure
• Implement simple and multiple linear regression with gradient descent

Skills you'll practise

Artificial Neural NetworksDecision Tree LearningAI AlgorithmsUnsupervised LearningK-Means ClusteringBoostingMachine Learning FrameworksRandom Forest AlgorithmAlgorithmsMechanicsForecastingMachine Learning AlgorithmsLogistic RegressionEnsemble MethodsMathematicsArtificial Intelligence

Advantages and disadvantages

Some points apply to every course of this kind; see how we rank.

Before you start

Intermediate: Coding and Data Algorithms (Numpy, Python, Scikit-learn) Beginner: Deep Learning and Neural Networks (Numpy, Python, Scikit-learn) Intermediate: Machine Learning Model Development (Numpy, Python, Scikit-learn)