Artificial Intelligence Bootcamp

Installation

• Introduction to the Python programming language and its applications
• Setting up the Python environment: installation of Python and necessary libraries

Python Basics I

• 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

 Python Basics II

• Recap of Python basics
• 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

Python Modules: NumPy,Pandas and Matplotlib

• Introduction to the NumPy module: features and applications
• Working with multidimensional arrays: creation, indexing, slicing, and reshaping
• Performing element-wise operations: arithmetic, logical, and statistical
• Overview of the Matplotlib module: data visualization and plotting
• Customizing plots: line properties, markers, colors, labels, and legends

Advanced Topics

• Introduction to Kaggle platform: features and benefits
• Leveraging Kaggle for real-life datasets: data exploration, analysis, and visualization

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 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

Hyperparameter Tuning, PCA, and SVD

• Hyperparameter tuning techniques: grid search, random search, and Bayesian optimization
• Principal Component Analysis (PCA): dimensionality reduction and feature extraction
• Singular Value Decomposition (SVD): applications in matrix factorization and data compression

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 Time Series and Time Series Forecasting 

• Concepts and characteristics of time series data
• Time series components: trend, seasonality, and noise
• Popular time series forecasting models: ARIMA, SARIMA, exponential smoothing • Implementing time series forecasting models

Models and Hyperparameter Tuning

• Evaluation metrics for time series forecasting: mean absolute error, mean absolute percentage error, etc.
• Cross-validation techniques for time series data
• Hyperparameter tuning for time series models

• Introduction to NLP and Text Normalization
• Overview of Natural Language Processing (NLP)
• Techniques for text normalization: lowercasing, punctuation removal, etc.
  
  
• 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

•  Markov Models and Language Model Evaluation

• • Basics of Markov models in NLP
  • Techniques for evaluating language models: probability smoothing and performance metrics

• Text Classification Fundamentals

• • Overview of Text Classification
  • Introduction to Naive Bayes and Sentiment Classification

• Advanced Classifiers and Vector Semantics

• • Generative vs. discriminative Classifiers
  • Understanding vector semantics and embeddings: TF-IDF theory and vector similarity

• Neural Word Embeddings and Sequence Models

• • • Introduction to neural word embeddings: Word2Vec and GloVe
    • Exploring sequence of words in NLP tasks

• Transformers and Large Language Models

• • Overview of transformers and their impact on NLP
  • Introduction to large language models (LLMs) and their applications

Computer Vision

• Cascade and HOG classifiers to detect faces
• Face detection using OpenCV and Dlib library
• Detect other objects using OpenCV, such as cars, clocks, eyes, and full body of people
• KCF and CSRT algorithms to perform object tracking
• convolutional neural networks and implement them using Python and TensorFlow
• Detect objects in images in videos using YOLO, one of the most powerful algorithms today
• Recognize gestures and actions in videos using OpenCV
• Create hallucinogenic images with Deep Dream
• Create images that don't exist in the real world with GANs (Generative Adversarial Networks)

Machine Learning Operations(MLOps)

•  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

•  Introduction to Docker for AI Applications
  • Basics of Docker and containerization
  • Building Docker images for AI/ML applications
  • Hands-on: Containerizing your FastAPI application

• Leveraging Lang Chain and LangSmith for Enhanced NLP Applications

• • • Introduction to Lang Chain and its Ecosystem
    • Overview of LangSmith for debugging, testing, evaluating, and monitoring LLM applications
    • Hands-on: Integrating Lang Chain with your NLP models and using LangSmith for enhanced capabilities

• Advanced Model Deployment with Hugging Face and Lang Chain

• • Integrating Hugging Face models for advanced NLP capabilities
  • Exploring Lang Chain for building complex NLP applications
  • Hands-on: Deploying a Hugging Face model via FastAPI with LangSmith integration

• 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