Data Science and AI Bootcamp

Python Basics

• Introduction to Python: history, features, and advantages
• Expressions and operators: arithmetic, assignment, comparison, and logical
• Understanding type() function and type inference
• Introduction to data structures: lists, tuples, and dictionaries

• Working with arithmetic operators: addition, subtraction, multiplication, division, modulus, and exponentiation
• Using comparison operators: equal to, not equal to, greater than, less than, etc.
• Logical operators: and, or, and not
• Exploring advanced data types: sets and strings manipulation.

Expressions, Conditional Statements & For Loop

• Evaluating expressions: operator precedence and associativity
• Introduction to conditional statements: if, elif, and else
• Executing code based on conditionals.
• Understanding the flow of control in conditional statements
• Iteration using the for loop: range(), iteration over lists, and strings.

While loop, Break and Continue Statements, and Nested Loops

• Working with while loop: syntax, conditions, and examples
• Combining loops and conditionals
• Using the break statement to exit loops prematurely.
• Utilizing the continue statement to skip iterations.
• Implementing nested loops for complex iterations

Functions

• Introduction to functions: purpose, advantages, and best practices
• Defining and calling user-defined functions
• Parameters and arguments: positional, keyword, and default values
• Return statement and function output.
• Variable scope and lifetime
• Function documentation and code readability

Exception Handling and File Handling

• Understanding exceptions: errors, exceptions, and exception hierarchy
• Handling exceptions using try-except blocks: handling specific exceptions, multiple exceptions, and else and finally clauses.
• Raising exceptions and creating custom exception classes
• File handling in Python: opening, reading, writing, and closing files.
• Working with different file modes and file objects

Mathematical Concepts

Linear Algebra:

• • • Vectors, matrices, operations, and their applications in data science.
    • Introduction to numpy for matrix operations.
      
      Introduction to numpy:
      
      

• • Why numpy is the preferred library for numerical operations in Python.
  • Basic numpy operations: creating arrays, array indexing, array slicing.
  • Matrix operations using numpy: matrix multiplication, finding determinants, solving linear equations.

Probability and Statistics

Probability Theory:

• • • Basic probability, rules, and distributions (normal, binomial, Poisson).
    • Random variables, expectations, and variance.

       

      Descriptive Statistics:

       

• • • Measures of central tendency (mean, median, mode).
    • Measures of variability (range, variance, standard deviation)

       

      Introduction to pandas and scipy

       

• • Using pandas for data manipulation and summary statistics.
  • scipy for performing hypothesis tests and building confidence intervals.
  • Visualization with seaborn and matplotlib to understand data distributions and relationships.

     

Probability and Statistics II

Inferential Statistics:

• • Sampling distributions and the Central Limit Theorem.
  • Confidence intervals and hypothesis testing.
    
    

    Correlation and Regression:

    • Scatter plots, correlation coefficients.
    • Simple linear regression analysis.

       

      Introduction to Seaborn and Matplotlib
      
      
      • Visualization of correlation matrices and scatter plots to identify relationships between variables.
      • Advanced plotting techniques such as pair plots, heatmaps, and regression plots to extract deeper insights from data.

Introduction and Missing Value Analysis

• Introduction to Exploratory Data Analysis (EDA)
• Importance of EDA in data analysis
• Steps involved in EDA
• Handling missing values: identification, analysis, and treatment strategies • Imputation techniques for missing values
  
  

Data Consistency, Binning, and Outlier Analysis

• Data consistency checks using fuzzy logic
• Binning and discretization techniques for continuous variables
• Outlier detection and analysis methods
• Handling outliers: techniques for treatment or removal
  
  

Feature Selection and Data Wrangling

• Importance of feature selection in EDA
• Feature selection techniques: filter methods, wrapper methods, and embedded methods
• Data wrangling: cleaning and transforming data for analysis
• Handling categorical variables: encoding techniques
   

Inference, Hypothesis Testing, and Visualization

• Inference and hypothesis testing in EDA
• Common statistical tests: t-test, chi-square test, ANOVA, etc.
• Visualization techniques for EDA: histograms, box plots, scatter plots, etc. 
• Hands-on  practical session for complete EDA using a dataset
  
  

Machine Learning and Deep Learning

Overview of Machine Learning

• Supervised, unsupervised, and reinforcement learning.
• Machine learning workflow from data collection to model deployment.
• Introduction to Python libraries essential for ML (Scikit-learn, TensorFlow, PyTorch)
  
  

Supervised learning and Linear Regression

• Linear Regression: Concept, loss function, evaluation metrics (MSE, R²)
• Building a Linear Regression model in scikit-learn
• Visualizing predictions vs actuals
  
  

Machine Learning Performance Metrics and Naive Bayes

• Evaluation metrics for classification problems: accuracy, precision, recall, F1 score, etc.
• Introduction to Naive Bayes algorithm and its applications
• Implementing Naive Bayes for classification tasks

Logistic Regression, SVM, Decision Trees, and Random Forests

• Logistic Regression: theory, interpretation, and applications
• Support Vector Machines (SVM): concepts, kernels, and use cases
• Decision Trees: construction, pruning, and interpretability
• Random Forests: ensemble learning and feature importance
• Bagging and Boosting: techniques for improving model performance
  
  

Clustering Introduction, Partitioning Algorithms, and Cluster Evaluation

• Introduction to clustering: unsupervised learning technique
• Partitioning algorithms: K-means, K-medoids
• Hierarchical clustering: agglomerative and divisive approaches
• Density-based clustering: DBSCAN, OPTICS
• Cluster evaluation metrics: silhouette coefficient, Davies-Bouldin index  
  
  

Regression and Evaluation of Regression Methods

• Introduction to regression analysis
• Linear regression: assumptions, interpretation, and model evaluation • Evaluation metrics for regression: mean squared error, R-squared, etc.
• Other regression methods: polynomial regression, ridge regression, lasso regression
  
  

Introduction to Deep Learning

• Overview of deep learning, its importance in computer vision, key concepts, and architectures.
• Code along session for building Deep Neural Network from scratch
  
  

Deep Learning Hyperparameter Tuning

• Strategies for optimizing hyperparameters like learning rate, batch size, and regularization to improve model performance.

Conceptual Overview 

• Understand the distinct roles and responsibilities of data scientists and data engineers within projects. 
  
  

Data Sourcing with Python 

• Extracting data from sources like PostgreSQL, MongoDB, APIs, web scraping, and IoT devices.
  
  

Databricks Tour 

• Get introduced to Databricks as a platform for big data processing and machine learning.
  
  

Big Data Handling for Data Science 

• Process large-scale datasets using Apache Spark within a distributed environment. 
  
  

MLflow 

• Learn to track experiments and ensure reproducibility in machine learning workflows

Introduction to Convolutional Neural Networks (CNNs)

• Explanation of CNNs, their architecture, and their role in image processing.
• Codel along session on Convolutional Neural Networks.
  
  

Building Custom Image Classification Models

• Step-by-step guide to creating and training a custom image classifier using a CNN.
  
  

Transfer Learning and Introduction to Object Detection

• Introduction to transfer learning, its applications, and an overview of object detection techniques.
• Hands on with YOLO Object Detection
• Practical session on using the YOLO (You Only Look Once) algorithm for object detection.
  
  

Custom Training YOLO model

• Detailed guidance on training a YOLO model with a custom dataset for specific object detection tasks.
  
  

Using State-of-the-Art Models for Real-World Applications

• Exploring and implementing advanced models in computer vision for practical use cases.
  
  

Introduction to OpenCV

• Introduction to OpenCV, its libraries, and its importance in computer vision tasks.
  
  

Image Pre-processing and Pre-build Algorithms in OpenCV

• Hands-on session on image pre-processing techniques and using built-in algorithms in OpenCV.
  
  

Advance guided project with OpenCV

• Capstone project where Students apply learned techniques in a guided project using OpenCV.

Introduction to NLP and Text Normalization

• Overview of Natural Language Processing (NLP)
• Techniques for text normalization: lowercasing, punctuation removal, etc.
• Basics of tokenization and stopword removal
  
  

Text Representation and Tokenization

• Introduction to vectors in NLP: Bag of Words and Count Vectorizer
• Basics of tokenization and stopword removal
  
  

Stemming, Lemmatization, and N-gram Language Models

• Understanding and applying stemming and lemmatization
• Introduction to N-gram language models
• Introduction to vectors in NLP: Bag of Words, Count Vectorizer, and TF-IDF
  
  

  Markov Models and Language Model Evaluation

• Basics of Markov models in NLP
• Overview of Text Classification
• Techniques for evaluating language models: probability smoothing and performance metrics
• Introduction to Naive Bayes and Sentiment Classification
  
  

Advanced Classifiers and Vector Semantics

• Generative vs. discriminative classifiers
• Understanding vector semantics and embeddings
• Introduction to neural word embeddings: Word2Vec and GloVe

Deep Learning for NLP and Sequence Models

• Overview of deep learning techniques for NLP
• Applying supervised and unsupervised learning methods to NLP tasks
• Exploring sequence of words in NLP tasks

Transformers and Large Language Models

• Understanding the architecture and mechanisms of transformers
• Overview of large language models (LLMs) and their capabilities
• Hands-on: Fine-tuning transformers and LLMs for NLP applications
  
  

Training and Fine-Tuning LLMs

• Techniques for training large language models
• Fine-tuning pre-trained LLMs for specific tasks
  
  

Multimodal Integration

• Exploring multimodal models and their integration
• Working with open-source models for diverse applications
• Utilizing cloud APIs for deploying and integrating multimodal solutions
  
  

LLM Agents

• Introduction to LLM agents
• Use cases and applications of LLM agents
• Techniques for designing and deploying LLM agents for various tasks

Introduction to Generative AI and Multimodal Models

• Overview of Generative AI and its impact on various industries.
• Understanding multimodal models and how they differ from single-modality models.
• Exploring the OpenAI API: Capabilities and applications for text, speech, and image-based AI.
  
  

Speech Synthesis and Conversational Agents

• Objective: Dive into text-to-speech (TTS) and speech-to-text (STT) models and explore conversational AI with agent frameworks.
• Overview of text and voice synthesis technologies.
• Introduction to Eleven Labs and Heygen: Creating high-quality audio and speech synthesis.
• Using OpenAI API for speech synthesis and understanding its capabilities
  
  

Advanced Agent Development with LangChain

• Basics of LangChain and its role in agent-based AI.
• Building, customizing, and deploying agents using LangChain.
• Exploring integration of LangChain with other APIs for multimodal interactions, including OpenAI API for image and text generation.
  
  

Building Complex Agent-Based Applications with CrewaI, Synthesia, and OpenAI

• Introduction to CrewaI: Building intelligent agents for various tasks.
• Synthesia for video and visual content generation in AI-driven applications.
• Using OpenAI API to generate multimodal content (text, images, and speech).
• Building a final project: Integrate multiple APIs to create a multimodal generative application.  

Introduction to MLOps and AI/NLP Fundamentals

• Overview of MLOps and its importance in the AI lifecycle
• Current trends in AI
• Setting up the development environment

Deep Dive into Machine Learning Models for NLP

• Understanding NLP models (llama2, GPT, Mistral, etc.)
• Introduction to Hugging Face Transformers and Datasets
• Hands-on: Building a simple NLP model with Hugging Face

Introduction to FastAPI for ML Model Deployment

• Basics of API development with FastAPI
• Deploying a simple ML model with FastAPI
• Hands-on: Creating your first ML API with FastAPI

 Advanced FastAPI Features for Production-Ready APIs

• Authentication and authorization in FastAPI
• Hands-on: Enhancing your ML API with advanced features

Docker Image Creation and Application Containerization

• Introduction to Docker and its role in application deployment
• Hands-on: Creating Docker images for NLP applications
• Converting existing applications into Docker containers for scalable deployment
  
  

 LangGraph and Advanced Model Integration

• Introduction to LangGraph for building graph-based NLP Applications
• Exploring advanced integration scenarios with LangGraph and LangChain
• Hands-on: Designing graph-based workflows for NLP tasks
  
  

Deploying ML Models on Google Cloud

• Overview of Google Cloud Platform (GCP) for ML
• Introduction to Google Cloud Run
• Hands-on: Deploying your Dockerized FastAPI application on GCP with LangSmith monitoring