Introduction to Deep Learning

كورس لتعليم اساسيات خوارزميات التعلم العميق والشبكات العصبية وتعلم الاله للمبتدئين وحتى المستوى المتقدم

سواء كنت طالباً فى علوم الحاسب او طالباً  فى الهندسة أو مبرمجاً وتعشق مجال الذكاء الاصطناعى , فإن هذا الكورس سيساعدك علي فهم أساسيات التعلم العميق و الوصول إلى مستوى محترف

وسوف يركز هذا الكورس على الجوانب النظرية وراء الخوارزميات والنماذج المنتشره هذه الايام للتعلم العميق

This course is focus on the theoretical aspects of the recent deep learning methods.

Section 1: Introduction to Machine learning & Deep learning

  Lecture 1: Introduction to Deep learning

  · Brief history of Deep learning

  · Motivation

  Lecture 2: What is Machine Learning?

  · Machine leaning Definition

  · Traditional Programming vs Machine learning

  · AI vs Machine learning vs Deep learning

  Lecture 3: Types of Machine Learning

  · Supervised, unsupervised, and reinforcement learning

  · Classification vs Regression

  · Clustering and dimensionality reduction

  Lecture 4: Machine Learning & Deep learning Applications

  Lecture 5: Steps to Build a Machine Learning System

  · Data collection, feature extraction, modelling, estimation, and validation.

  · for example, how to develop an image categorization system.

  Lecture 6: K-Nearest Neighbors (KNN) Model

Section 2: Linear Regression

  Lecture 7: Univariate Linear Regression

  Lecture 8: Cost Function Intuition

  Lecture 9: Gradient Descent Algorithm

  Lecture 10: Linear Regression with Multiple Variables

Section 3: Logistic Regression

  Lecture 11: Introduction to Logistic Regression

Lecture 12: Cost function

  Lecture 13: Multi-Class Classification

Section 4: Neural Networks

  Lecture 14: Introduction to Neural Networks Part 1

  · Definition of Neural Networks

  · Artificial Neuron

  · Types of Activation Functions

  Lecture 15: Introduction to Neural Networks Part 2

  · Neural Network Architectures

  · Capacity of Single Neuron\Neural Network

  · Multi-layer Neural Networks

  · Softmax Activation Function

  Lecture 16: Biological Neural Networks