Learn artificial intelligence and machine learning fundamentals through a comprehensive university-level course featuring practical C# programming examples and the Accord.NET framework. Master core AI/ML concepts starting with introductory principles and progressing through supervised learning techniques including decision trees, K-nearest neighbors (KNN), and neural networks. Implement hands-on projects using cross-validation, model training and testing methodologies, and accuracy measurement techniques. Explore advanced topics such as multilayer perceptron training, feature selection and normalization, data preprocessing, and TF-IDF text processing methods. Develop expertise in supervised evaluation using K-fold cross validation and multiclass classification systems. Understand learning-to-rank algorithms including pointwise, pairwise, and listwise ranking approaches. Study optimization techniques through gradient descent, loss functions, regularization methods (L1/L2), and handling sparse and missing data. Examine support vector machines (SVM) with large and soft margin classifiers, conditional probability, probabilistic models, and joint distribution concepts. Master logistic regression and ensemble learning methods including bagging, boosting, and AdaBoost algorithms. Conclude with unsupervised learning techniques focusing on clustering algorithms, hierarchical clustering, and K-means implementation, plus bonus content on speech-to-text transcription using OpenAI Whisper models.

Syllabus

#AI & #ML Lecture 1 : Introduction to Artificial Intelligence (AI) and Machine Learning (ML)
#AI & #ML Lecture 2 : Introduction to Machine Learning & Decision Trees, Supervised Learning
#AI & #ML Lecture 3 : Practical Example of Decision Trees with C# and Accord.NET, Cross Validation
#AI & #ML Lecture 4 : Proper Model Training & Testing, KNN Algorithm & Practical Example, Accuracy
#AI & #ML Lecture 5 : Learning a Linear Classifier, Perceptron Learning & Hyperplanes, KNN, Neural
#AI & #ML Lecture 6 : A Real Full Practical Example of How to Do Multilayer Perceptron Training 1/2
#AI & #ML Lecture 7 : A Real Full Practical Example of How to Do Multilayer Perceptron Training 2/2
#AI & #ML Lecture 8: Feature Selection & Normalization, Data Pre-Processing, TF-IDF, Text Processing
#AI & #ML Lecture 9 : Supervised Evaluation, K-Fold Cross Validation & Multiclass Classification
#AI & #ML Lecture 10: What Is Learning To Rank (LTR), Pointwise, Pairwise, and Listwise Ranking
#AI & #ML Lecture 11 : Gradient Descent, Loss Function, Sparse & Missing Data, Regularization, L1 L2
#AI & #ML Lecture 12 : Large & Soft Margin Classifiers, Support Vector Machines (SVM), Loss Function
#AI & #ML Lecture 13: Conditional Probability & Probabilistic Models, Joint Distribution, Random Var
#AI & #ML Lecture 14: Logistic Regression & Ensemble Learning - Bagging & Boosting - AdaBoost
#AI & #ML Lecture 15: Unsupervised Learning, Clustering Algorithms, Hierarchical Clustering, K-Means
How to do Free Speech-to-Text Transcription Better Than Google Premium API with OpenAI Whisper Model