دورة الذكاء الأصطناعي

Overview:

This course provides a concise introduction to the fundamental concepts in machine learning and popular machine learning algorithms. We will cover the standard and most popular supervised learning algorithms including linear regression, logistic regression, decision trees, k-nearest neighbor, an introduction to Bayesian learning and the naïve Bayes algorithm, support vector machines and kernels and neural networks. Feature reduction methods will also be discussed. We will introduce the basics of computational learning theory. In the course we will discuss various issues related to the application of machine learning algorithms. We will discuss hypothesis space, overfitting, bias and variance, tradeoffs between representational power and learnability, evaluation strategies and cross-validation. The course will be accompanied by hands-on problem solving with programming in Python and some tutorial sessions.

This course covers the basic concepts and techniques of Machine Learning from both theoretical and practical perspective. The material includes classical ML approaches such as Linear Regression and Decision Trees, more advanced approaches as Clustering and Association Rules as well as “hot” topics such as XGBoost. The students will be able to experiment with implementations of almost all algorithms discussed in class using meaningfully crafted Jupyter notebooks and practice quizzes.

Training Objectives:

Upon completion of this course, participants will be able to:

Analyze and identify significant characteristics of data sets.
Develop an understanding of training a learning algorithm including over-fitting, noise, convergence and stopping criteria.
Match a data set with the most promising inductive learning algorithms.
Understand and implement the training, testing, and validation phases of learning algorithms development and deployment.
Determine the computational complexity associated with development and execution of learning algorithms for a given data set.
Develop hands on experience with the leading set of inductive learning algorithms.
Apply machine learning algorithms for classification and functional approximation or regression.

Course Outline:

Module 01: Introduction	What is Machine Learning Use Cases Commonly used Terms	Lifecycle of a ML Project Supervised Learning Unsupervised Learning
Module 02: Data Exploration	Data Acquisition Types of Data Data Types Exploratory Data Analysis Data Pre-processing Data Quality assessment Feature Scaling Descriptive Statistics Methods to impute missing values Outlier/Anomaly Detection Data Visualization	Histogram Bar Graph Scatter Plot Pie Chart Box Plot Feature Selection Univariate Selection Feature Importance Correlation matrix and Heat map Underfitting vs Overfitting Bias-Variance Trade-off
Module 03: Evaluation metrics	Introduction Hypothesis Testing Statistical Assumptions Null Hypothesis Alternate Hypothesis One sample Z-test Z-test in Python T-test T-test in Python Pearson’s Chi Squared Test	Confusion Matrix Absolute Error Relative Error RMSE Precision, Accuracy Recall Specificity F-Score ROC/AUC
Module 04: Linear Regression	Cost Function Gradient Descent What is Regression Basic Idea Linear Regression Applications Linear Regression	Types of Errors Better Regression Models Correlation is not Causation Polynomial Linear Regression Regularization Ridge Regression LASSO Regression
Module 05: Classification	Introduction Types of Classification Algorithms Applications of Classification Algorithms Logistic Function Logistic Regression Application of Logistic Regression Types of Logistic Regression Decision Trees Working of Decision Tree	Attribute Selection measure Gini Index Information Gain Random Forests Working of RF Advantages and Disadvantages of RF algorithm Application of RF XGBoost
Module 06: Unsupervised ML	Why Unsupervised Learning Applications Clustering Types of Clustering	Singular value Decomposition Independent Component Analysis Association Rules

الجامعة

الأكاديميين

ضمان الجودة

الوحدات / المراكز

العمادات المساندة