آموزش مدرک کارشناسی ارشد علوم داده و هوش مصنوعی 2025 - از پایتون تا هوش مصنوعی مولد - آخرین آپدیت

سرفصل ها و درس ها

مقدمه Introduction

• Welcome Page

• Introduction to the Course

• Course Resources

پایتون برای علم داده Python for Data Science

• Welcome to the module

• Let's install Python together!!

• Google Colab, what's that?

• Let's leverage chatGPT for help!!

• Introduction to Python

• Variables & Keywords

• Datatypes Operators

• Lists

• Tuples

• Sets

• Dictionary

• Loops & Iterations

• Functions

• Map Reduce Filter

• File Handling

• Control Structures

• OOPs

• NumPy

• Pandas

• Data Visualization

• Matplotlib

• Seaborn

آمار تجاری Business Statistics

• Course Contents

• Introduction

• Types of Data (Agenda)

• Descriptive Stats

• Inferential Stats

• Qualitative Data

• Quantitative Data

• Sampling Techniques (Agenda)

• Population vs Sample

• Why Sampling is important

• Types of Sampling

• Cluster Random Sampling

• Probability Sampling

• Non probability sampling

• Population Sampling

• Why n-1 and not n

• Descriptive Analytics (Agenda)

• Measures of Central Tendency

• Mean

• Median

• Mode

• Measures of Dispersion

• Range

• IQR

• Variance Standard Deviation

• Mean Deviation

• Probability (Agenda)

• Probability

• Addition Rule

• Independent Events

• Cumulative Probability

• Conditional Probability

• Bayes Theorem 1

• Bayes Theorem 2

• Probability Distrubution (Agenda)

• Uniform Distribution

• Binomial Distribution

• Poisson Distribution

• Normal Distribution Part 1

• Normal Distribution Part 2

• Skewness

• Kurtosis

• Calculating Probability with Z-score for Normal Distribution Part 1

• Calculating Probability with Z-score for Normal Distribution Part 2

• Calculating Probability with Z-score for Normal Distribution Part 3

• Covariance & Correlation (Agenda)

• Covariance

• Correlation

• Covariance VS Correlation

• Hypothesis Testing

• Tailed Tests

• p-value

• Types of Test

• T Test

• Z Test

• Chi Square Test

• ANOVA

• Correlation Test (Practicals)

تحلیل اکتشافی داده Exploratory Data Analysis

• Course Contents

• Agenda

• DA,DS Processes

• What is EDA

• Visualization

• Steps involved in EDA (Data Sourcing)

• Steps involved in EDA (Data Cleaning)

• Handle Missing Values (Theory)

• Handle Missing Values (Practicals)

• Feature Scaling (Theory)

• Standardization Example

• Normalization Example

• Feature Scaling (Practicals)

• Outlier Treatment (Theory)

• Outlier Treatment (Practicals)

• Invalid Data

• Types of Data

• Types of Analysis

• Univariate Analysis

• Bivariate Analysis

• Multivariate Analysis

• Numerical Analysis

• Analysis Practicals

• Derived Metrics

• Feature Binning (Theory)

• Feature Binning (Practicals)

• Feature Encoding (Theory)

• Feature Encoding (Practicals)

• Case Study

• Data Exploration

• Data Cleaning

• Univariate Analysis

• Bivariate Analysis Part 1

• Bivariate Analysis Part 2

• EDA Report

SQL برای علم داده SQL for Data Science

• Course Contents

• Installation

• Data Architecture - File server vs client server

• Introduction to SQL

• Constraints in SQL

• Table Basics - DDLs

• Table Basics - DQLs

• Table Basics - DMLs

• Joins

• Data Import Export

• Aggregation Functions

• String functions

• Date Time Functions

• Regular Expressions

• Nested Queries

• Views

• Stored Procedures

• Windows Function

• SQL Python connectivity

یادگیری ماشین Machine Learning

• Agenda

• Introduction to ML

• Types of ML

• Use Cases Part 1

• Use Cases Part 2

• Pre-Requisites: Features

• Pre-Requisites: Train-Test Split

• Pre-Requisites: Feature Scaling

• Pre-Requisites: Standardization Example

• Pre-Requisites: Normalization Example

• Pre-Requisites: Feature Encoding

• Pre-Requisites: Feature Encoding (Practicals)

• Regression: Introduction to Regression Models

• Regression: Regression Metrics

• Regression: Regression Metrics (Practicals)

• Regression: Simple Linear Regression

• Regression: Multiple Linear Regression

• Regression: Linear Regression (Practicals)

• Regression: Multiple Linear Regression (Practicals)

• Regression: Polynomial Regression

• Regression: Polynomial Regression (Practicals)

• Regression: Bias Variance Tradeoff

• Regression: Ridge Regression

• Regression: Lasso Regression

• Regression: Lasso & Ridge Regression (Practicals)

• Classification: Introduction to Classification

• Classification: Types of Classification

• Classification: Log Loss

• Classification: Confusion Matrix

• Classification: AUC ROC Curve

• Classification: Classification Report

• Classification: kNN Classifier

• Classification: kNN Classifier Example

• Classification: Practicals Part 1

• Classification: kNN Classifier (Practicals)

• Classification: Decision Tree

• Classification: Decision Tree (Entropy based)

• Classification: Decision Tree (gini based)

• Classification: Decision Tree (Practicals)

• Classification: Decision Tree (Visualizing)

• Classification: Random Forest Classifier

• Classification: Random Forest Classifier (Practicals)

• Classification: Naive Bayes Classifier

• Classification: SVM Classifier Part 1

• Classification: SVM Classifier Part 2

• Classification: Logistic Regression

• Classification: Practicals so far

• Classification: Issues in Classification (Part 1)

• Classification: Issues in Classification (Part 2)

• Classification: Project

• Ensemble: Introduction to Ensemble Learning

• Ensemble: Bagging

• Ensemble: Bagging vs Random Forest

• Ensemble: Bagging (Practicals #1)

• Ensemble: Bagging (Practicals #2)

• Ensemble: Boosting

• Ensemble: Ada Boost

• Ensemble: Gradient Boost

• Ensemble: CF vs LF

• Ensemble: Cross Entropy

• Ensemble: Xtreme Gradient Boosting (XGB)

• Ensemble: Project

• Clustering: Introduction to Clustering

• Clustering: kMeans Clustering

• Clustering: kMeans Clustering (Practicals)

• Clustering: Hierarchical Clustering

• Clustering: Hierarchical Clustering (Practicals)

• Clustering: Mean Shift Clustering

• Feature Engineering: Introduction

• Feature Engineering: RFE and SFS

• Feature Engineering: RFE (Practicals)

• Feature Engineering: Successive Feature Selection

• Feature Engineering: Chi-Square

• Feature Engineering: Chi-Square (Practicals)

• Feature Engineering: Principal Component Analysis

• Feature Engineering: Principal Component Analysis (Practicals)

• Feature Engineering: Linear Discriminant Analysis

• Feature Engineering: Linear Discriminant Analysis (Practicals)

• Feature Engineering: kPCA & QDA

• Feature Engineering: kPCA & QDA (Practicals)

• Hyper Parameter Optimization: Basics

• Hyper Parameter Optimization: Manual HPO

• Hyper Parameter Optimization: GridSearch vs RandomizedSearch

• Hyper Parameter Optimization: Manual HPO (Practicals)

• Hyper Parameter Optimization: RandomizedSearchCV (Practicals)

• Hyper Parameter Optimization: GridSearchCV (Practicals)

تحلیل سری زمانی و پیش بینی Time Series Analysis & Forecasting

• Introduction to TSA

• Time Series vs Regression

• Time Series Analysis

• Anomaly Detection

• Components of Time Series

• Decomposition

• Decomposition (Practicals)

• Additive/Multiplicative Decomposition

• Stationarity

• Testing TS Stationarity

• Transformation

• Introduction to Pre-Processing

• Handle Missing Value

• Handle Missing Value (Practicals)

• Outlier Treatment

• 3-Sigma Technique

• Feature Scaling

• Feature Scaling: Standardization

• Feature Scaling: Normalization

• Feature Scaling (Practicals)

• Feature Encoding

• Feature Encoding (Practicals)

• Models - Algorithms

• Models - ARIMA Part 1

• Models - ARIMA Part 2

• Models - AR Theory

• Models - MA Theory

• Models - ACF/PACF Plots

• Models - Find p,d,q in ARIMA

• Models - ARIMA (Practicals Part 1)

• Models - ARIMA (Practicals Part 2)

• Models - ARIMA (Final)

• Models - Decomposition

• Models - ACF/PACF

• Models - Best Transformation

• Models - Grid Search (Part 1)

• Models - Grid Search (Part 2)

• Models - Final Model Building

• Models - Facebook Prophet (Part 1)

• Models - Facebook Prophet (Part 2)

• Models - Facebook Prophet (Part 3)

• Models - Multi Variate Time Series Analysis

• Models - Facebook Prophet (Uni vs Multi)

• Introduction to Metrics

• Forecasting Evaluation Metrics

• Mean Squarred Error

• Root Mean Squarred Error

• Mean Absolute Percentage Error

• Project 1 - Energy Forecasting Part 1

• Project 1 - Energy Forecasting Part 2

• Project 1 - Energy Forecasting Part 3

• Project 2 - Stock Market Prediction Part 1

• Project 2 - Stock Market Prediction Part 2

• Project 2 - Stock Market Prediction Part 3

• Project 3 - Demand Forecasting Part 1

• Project 3 - Demand Forecasting Part 2

• Project 3 - Demand Forecasting Part 3

• Project 3 - Demand Forecasting Part 4

• Project 3 - Demand Forecasting Part 5

• Project 3 - Demand Forecasting Part 6

یادگیری عمیق و شبکه‌های عصبی Deep Learning & Neural Networks

• Introduction

• Introduction to Deep Learning

• Understanding Deep Learning

• What is a Neuron

• Activation Functions

• Activation Function: Step Function

• Activation Function: Linear Function

• Activation Function: Sigmoid Function

• Activation Function: TanH Function

• Activation Function: ReLu Function

• Backpropagation & Forward Pass

• Gradient Descent

• Artificial Neural Networks: Intuition

• Artificial Neural Networks: Practicals

• Artificial Neural Networks: Hyper Parameter Optimization

• Convolutional Neural Networks: What is CNN

• Convolutional Neural Networks: Steps in CNN

• Convolutional Neural Networks: Architecture Explained

• Convolutional Neural Networks: Image Augmentation

• Convolutional Neural Networks: Batch size vs iterations vs epochs

• Convolutional Neural Networks: Practicals

• Convolutional Neural Networks: Model Summary & Parameters

• Convolutional Neural Networks: Project (X-Ray detection)

• Recurrent Neural Networks: Basics

• Recurrent Neural Networks: Types of RNN

• Recurrent Neural Networks: Vanishing Gradient & Exploding Gradient Problem

• Recurrent Neural Networks: LSTMs

• Recurrent Neural Networks: LSTMs (Practicals)

• Pre-Trained Models

• Pre-Trained Models (Practicals)

• Pre-Trained Models: VGG16

• Pre-Trained Models: MobileNet

• Transfer Learning

• Project: Pneumonia Detection from X-Ray Images

پردازش زبان طبیعی Natural Language Processing

• Course Contents

• Intro to NLP: Introduction

• Intro to NLP: Introduction continued

• Intro to NLP: Key Challenges

• Intro to NLP: Linguistics

• NLP Basics: Case Folding

• NLP Basics: SCR

• NLP Basics: Handling Contractions

• NLP Basics: Tokenization

• NLP Basics: Stop Word Removal

• NLP Basics: nGrams

• NLP Basics: Vectorization

• NLP Basics: Word Embeddings

• NLP Basics: Bag of Words

• NLP Basics: Bag of Words (Practicals)

• NLP Basics: TF-IDF

• NLP Basics: TF-IDF (Practicals)

• NLP Basics: Part of Speech Tagging and Named Entity Recognition

• NLP Basics: NER (Practicals)

• Word Embeddings: Word2Vec Introduction

• Word Embeddings: Word2Vec Part 2

• Word Embeddings: Pre-Trained Word2Vec

• Word Embeddings: Word2Vec Intuition

• Word Embeddings: Word2Vec - Check X Features

• Word Embeddings: Word2Vec CBOW

• Word Embeddings: Word2Vec Skip Grams

• Word Embeddings: GloVe

• Word Embeddings: FastText

• Word Embeddings: Cosine Similarity

• Neural Networks: LSTMs Part 1

• Neural Networks: LSTMs Part 2 (Architecture)

• Neural Networks: LSTMs Part 3 (Deep Dive)

• Neural Networks: LSTMs Part 4 (Pointwise Operations)

• Neural Networks: LSTMs Part 5 (forget gate)

• Neural Networks: LSTMs Part 6 (inpute gate)

• Neural Networks: LSTMs Part 7 (output gate)

• Neural Networks: LSTMs Part 8 (Practicals #1)

• Neural Networks: LSTMs Part 9 (Practicals #2)

• Neural Networks: LSTMs Part 10 (Practicals #3)

• Neural Networks: GRU Part 1

• Neural Networks: GRU Part 2

• Neural Networks: GRU Part 3 (reset gate)

• Neural Networks: GRU Part 4 (update gate)

• Neural Networks: GRU Part 5 (Practicals)

• Neural Networks: Bi-Directional LSTMs

Transformer و هوش مصنوعی مولد Transformers & Generative AI

• Course Contents

• Transformer Types

• Introduction to Transformers

• Self Attention

• Encoder Architecture

• Contextual Embeddings

• Decoder Architecture

• Introduction to BERT

• Configurations of BERT

• BERT: Fine Tuning

• BERT: Pre Tuning (Masked LM)

• BERT: Input Embeddings

• ARLM vs AELM

• RoBERTa

• DistilBERT

• AlBERT

• Introduction to GPT (Decoder Only)

• GPT Architecture

• GPT Masked Multi Head Attention

• GPT Blocks

• GPT Training

• LLM Basics: Tokens

• LLM Basics: Context Window

• LLM Basics: Prompt

• LLM Basics: Prompt Engineering

• LLM Basics: Prompt Tuning

• LLM Basics: Prompt Structures

• RAGs: Introduction to RAG

• RAGs: RAGs چیست و چرا؟ RAGs: What and Why

• RAGs: موارد استفاده RAGs: Use Cases

• RAGs: توضیح مقاله RAGs: Paper Explanation

• RAGs: توضیح معماری RAGs: Architecture Explanation

• RAGs: بررسی دقیق معماری RAGs: Detailed Architecture Walkthrough

• RAGs: موارد استفاده عملی RAGs: Practical Use Cases

• LangChain LangChain

• مقدمه ای بر مهندسی پرامپت (Prompt Engineering) Introduction to Prompt Engineering

• انواع پرامپتینگ (Prompting) Types of Prompting

• محدودیت های Few Shot Few Shot Limitations

• پرامپتینگ زنجیره تفکر (Chain of Thoughts Prompting) Chain of Thoughts Prompting

• پایگاه داده های برداری (Vector Databases) Vector Databases

• پایگاه داده برداری در مقابل اندیس برداری (Vector Index) Vector Database vs Vector Index

• نحوه کار پایگاه داده های برداری How Vector Databases works

• پایگاه داده برداری (عملی) Vector Database (Practicals)

• LSH LSH

• بررسی اجمالی مدل: Ollama Model Overview: Ollama

• شروع به کار: Ollama Getting Started: Ollama

• تست مدل: Ollama Model Testing: Ollama

• پیاده سازی پایتون: Ollama Python Implementation: Ollama

• سیستم های RAG: Ollama RAG Systems: Ollama

• سیستم های RAG (عملی): Ollama RAG Systems (Practicals): Ollama

• بررسی اجمالی مدل: API های LLM Model Overview: LLM APIs

• سیستم های RAG با xAI: API های LLM RAG Systems with xAI: LLM APIs

• سیستم های RAG با xAI (عملی): API های LLM RAG Systems with xAI (Practicals): LLM APIs

هوش مصنوعی مولد (پیشرفته) Generative AI (Advanced)

• مقدمه ای بر Fine Tuning Introduction to Fine Tuning

• RAGs در مقابل Fine-Tuning RAGs vs Fine-Tuning

• چه زمانی از RAGs استفاده کنیم در مقابل چه زمانی از مدل های Fine-Tuned استفاده کنیم When to use RAGs vs When to use Fine-Tuned models

• Fine Tuning Fine Tuning

• PEFT و Quantization PEFT and Quantization

• LoRA (فاز I - رتبه پایین) LoRA (Phase I - Low Rank)

• LoRA (فاز II - آداپتورها) LoRA (Phase II - Adapters)

• LoRA (فاز III - رتبه پایین + آداپتورها) LoRA (Phase III - Low Rank + Adapters)

• qLoRA (آداپتورهای رتبه پایین کوانتیزه شده) qLoRA (Quanitzed Low Rank Adapters)

ارزیابی RAG و معیارهای ارزیابی RAG Assessment and Evaluation Metrics

• مقدمه Introduction

• مقدمه ای بر ارزیابی RAG Introduction to RAG Evaluation

• معیارهای N-Gram (BLEU) N-Gram Metrics (BLEU)

• معیارهای N-Gram (ROUGE) N-Gram Metrics (ROUGE)

• معیارهای N-Gram (METEOR) N-Gram Metrics (METEOR)

• معیارهای ذاتی (امتیاز PPL) Intrinsic Metrics (PPL Score)

• معیارهای ذاتی (امتیاز PPL) عملی Intrinsic Metrics (PPL Score) Practicals

• معیارهای مبتنی بر مدل (BARTScore در مقابل BERTScore) Model-based Metrics (BARTScore vs BERTScore)

• چارچوب RAGAS (ارزیابی RAG) RAGAS Framework (RAG Assessment)

• (عملی) ارزیابی Rag توسط RAGAS (PRACTICALS) Rag Evaluation by RAGAS

• (عملی) ارزیابی Rag توسط BLEU, ROUGE (PRACTICALS) Rag Evaluation by BLEU, ROUGE

• (عملی) ارزیابی Rag توسط BERTScore, BARTScore (PRACTICALS) Rag Evaluation by BERTScore, BARTScore

استقرار ML/DL ML/DL Deployment

• مبانی استقرار Deployment Basics

• مقدمه ای بر Flask Introduction to Flask

• برنامه پایه Flask Flask Basic App

• ساخت مدل (پیش بینی سرطان سینه) Model Building (Breast Cancer Prediction)

• برنامه Flask (پیش بینی سرطان سینه) Flask App (Breast Cancer Prediction)

• AWS AWS

• استقرار AWS (پیش بینی سرطان سینه) AWS Deployment (Breast Cancer Prediction)

مبانی مهندسی داده Data Engineering Basics

• مقدمه ای بر مهندسی داده Introduction to Data Engineering

• ETL چیست؟ What is ETL

• ابزارهای ETL ETL Tools

• انبار داده چیست؟ What is Data Warehouse

• مزایای انبار داده Benefits of Data Warehouse

• ساختار انبار داده Data Warehouse Structure

• چرا به Staging نیاز داریم؟ Why do we need Staging

• Data Mart چیست؟ What are Data Marts

• Data Lake Data Lake

• Data lake در مقابل Data Warehouse Data lake vs Data Warehouse

• عناصر Datalake Elements of Datalake

پروژه های هوش مصنوعی مولد Generative AI Projects

• ChatScholar (پروژه EdTech) ChatScholar (EdTech Project)

• چت بات RAG تحقیقاتی Research RAG Chatbot

• پردازش خودکار ادعاهای هوش مصنوعی با استفاده از Gen AI Automated AI Claims Processing using Gen AI

• چت بات Multi PDF RAG ساخته شده بر روی داده های وب Scraped Multi PDF RAG Chatbot built on Web Scraped Data

• مربی شغلی هوش مصنوعی: قسمت 1 AI Career Coach: Part 1

• مربی شغلی هوش مصنوعی: قسمت 2 AI Career Coach: Part 2

• مربی شغلی هوش مصنوعی: قسمت 3 AI Career Coach: Part 3

• چت بات پایداری (GROK AI) Sustainability Chatbot (GROK AI)

آمادگی مصاحبه (بخش جدید) Interview Prep (NEW SECTION)

• آمادگی مصاحبه ML ML Interview Prep

• مصاحبه ML شماره 1 ML Interview #1

• مصاحبه ML شماره 2 ML Interview #2

• مصاحبه ML شماره 3 ML Interview #3

• مصاحبه ML شماره 4 ML Interview #4

• مصاحبه ML شماره 5 ML Interview #5

• مصاحبه ML شماره 6 ML Interview #6

• مصاحبه ML شماره 7 ML Interview #7

• مصاحبه ML شماره 8 ML Interview #8

• مصاحبه ML شماره 9 ML Interview #9

• مصاحبه ML شماره 10 ML Interview #10

• مصاحبه DL شماره 1 DL Interview #1

• مصاحبه DL شماره 2 DL Interview #2

• مصاحبه DL شماره 3 DL Interview #3

• مصاحبه DL شماره 4 DL Interview #4

• مصاحبه DL شماره 5 DL Interview #5

• مصاحبه DL شماره 6 DL Interview #6

• مصاحبه DL شماره 7 DL Interview #7

• مصاحبه DL شماره 8 DL Interview #8

• مصاحبه DL شماره 9 DL Interview #9

• مصاحبه DL شماره 10 DL Interview #10

• مصاحبه Gen AI شماره 1 Gen AI Interview #1

• مصاحبه Gen AI شماره 2 Gen AI Interview #2

• مصاحبه Gen AI شماره 3 Gen AI Interview #3

• مصاحبه Gen AI شماره 4 Gen AI Interview #4

• مصاحبه Gen AI شماره 5 Gen AI Interview #5

• مصاحبه Gen AI شماره 6 Gen AI Interview #6

• مصاحبه Gen AI شماره 7 Gen AI Interview #7

• مصاحبه Gen AI شماره 8 Gen AI Interview #8

• مصاحبه Gen AI شماره 9 Gen AI Interview #9

• مصاحبه Gen AI شماره 10 Gen AI Interview #10