Introduction to AI

قائمتي المفضلة مشاركة

عن الدورة

course (3)

Introduction to AI Course outline 

Module 1: Environment Setup & Data Analysis
Preparing the AI development environment and understanding data fundamentals

  • Setting up Python development environments (Anaconda & Virtual Environments)

  • Advanced Python review for AI applications

  • Working with Lists, Dictionaries, Functions, and Lambda Expressions

  • Understanding data formats (CSV, JSON, Parquet)

  • Data collection and preparation techniques

  • Feature engineering and label preparation

  • Handling missing values and data cleaning

  • Statistical analysis fundamentals

  • Data visualization and pattern discovery

  • Exploratory Data Analysis (EDA)

  • Introduction to data-driven decision making

Technologies: Pandas, NumPy, Matplotlib, Seaborn

Module 2: Machine Learning Fundamentals
Building predictive and intelligent decision-making systems

  • Introduction to Machine Learning concepts

  • Supervised Learning fundamentals

  • Classification techniques and applications

  • Regression techniques and applications

  • Unsupervised Learning concepts

  • Clustering and segmentation methods

  • Dimensionality reduction techniques

  • Reinforcement Learning fundamentals

  • Agents, environments, rewards, and policies

  • Model evaluation and performance metrics

  • Overfitting and underfitting prevention techniques

  • Model deployment fundamentals

Technologies: Scikit-Learn, SciPy, Joblib, OpenAI Gym

Module 3: Deep Learning
Building intelligent systems using neural networks

  • Introduction to Artificial Neural Networks

  • Neural Network architecture and components

  • Activation functions and optimization techniques

  • Forward and Backpropagation processes

  • Understanding tensors and tensor operations

  • PyTorch fundamentals

  • Loss functions and optimization algorithms

  • Convolutional Neural Networks (CNN)

  • Recurrent Neural Networks (RNN)

  • Deep Learning model training and evaluation

  • GPU acceleration concepts

Technologies: PyTorch, CUDA, TensorBoard

Module 4: Natural Language Processing (NLP)
Enabling computers to understand and process human language

  • Introduction to Natural Language Processing

  • Text preprocessing and cleaning techniques

  • Arabic and English language processing

  • Tokenization and text normalization

  • Word Embeddings and vector representations

  • Transformer architecture fundamentals

  • Sentiment Analysis systems

  • Question Answering systems

  • Text classification techniques

  • Introduction to Large Language Models (LLMs)

  • Working with Arabic language models

Technologies: Hugging Face Transformers, NLTK, AraBERT

Module 5: Computer Vision
Teaching computers to interpret and understand visual information

  • Introduction to Computer Vision

  • Digital image processing fundamentals

  • Working with images using OpenCV

  • Convolutional Neural Networks for image analysis

  • Transfer Learning techniques

  • Using pre-trained computer vision models

  • Object detection fundamentals

  • Real-time object detection systems

  • Image augmentation techniques

  • Image classification applications

  • Modern Computer Vision workflows

Technologies: OpenCV, Pillow, Torchvision, YOLO

Module 6: Speech AI
Developing intelligent systems for speech understanding and recognition

  • Introduction to Speech Processing

  • Audio signal fundamentals

  • Sound wave representation and spectrograms

  • Feature extraction techniques (MFCC)

  • Speech-to-Text systems

  • Automatic Speech Recognition (ASR)

  • Working with Whisper models

  • Advanced speech processing using Wav2Vec2

  • Audio analysis and interpretation

  • Speech AI applications and use cases

Technologies: Librosa, Torchaudio, Whisper, SoundFile

Module 7: AI Project Development & Deployment
Applying AI concepts through real-world practical projects

  • AI project planning and development lifecycle

  • Building Reinforcement Learning agents

  • Gesture-based control systems

  • Computer Vision applications

  • Virtual Calculator development

  • AI Virtual Keyboard implementation

  • Vehicle License Plate Recognition systems

  • Image Steganography applications

  • AI Virtual Mouse development

  • People Detection, Tracking, and Counting

  • Speech Recognition projects

  • Multi-task NLP systems

  • Text Summarization applications

  • Model integration and deployment considerations

  • Final Capstone Project

Technologies: OpenCV, MediaPipe, YOLO, Transformers, Librosa, Gymnasium

إظهار المزيد

تقييمات ومراجعات الطلاب

لا يوجد تقييم حتى الآن
لا يوجد تقييم حتى الآن
Scroll to Top