• Python environment setup
  • Installing Python
  • PATH configuration
  • Using the terminal efficiently
• Virtual environment basics
  • venv vs conda
  • Creating environments
  • Activating & deactivating
• Python syntax refresher
  • Indentation rules
  • Variable naming best practices
• Data types (Deep Coverage)
  • Numbers (int, float)
  • Strings and Unicode handling
  • Lists, tuples, sets, dictionaries
  • Mutable vs immutable types
  • Interning and memory model
• Control structures
  • Loops
  • Conditional statements
  • Ternary operators
  • List comprehensions
  • Generator expressions
• Functions (Deep AI-focused view)
  • Defining functions
  • *args and **kwargs
  • Pure vs impure functions
  • Lambda functions
  • Higher-order functions
• Object-oriented Python
  • Classes, objects
  • Constructors
  • Magic methods
  • Encapsulation
  • Inheritance
  • Polymorphism
  • Composition vs inheritance (important for deep learning model design)
• Exception handling
  • try/except/else/finally
  • Custom exceptions
  • Common exceptions in ML pipelines
• Modular Programming 
  • Import system
  • init.py
  • Creating Python packages
• Python for numerical computing
  • Integers vs floats
  • Float precision
  • Overflow/underflow
• Time & space complexity
  • Big-O notation basics
  • Optimizing loops
  • List operations complexity
• File handling
  • Reading/writing text files
  • JSON
  • Pickle
  • CSV
• Python’s memory model
  • Stack vs heap
  • Object references
  • Garbage collection
• Writing clean Python
  • PEP8
  • Docstrings
  • Function annotations
• Using Jupyter Notebook
  • Cells
  • Magic commands
  • Visualizations basics
• Virtual environment troubleshooting
  • Broken dependencies
  • Path issues
  • Python version conflicts
• Installing libraries
  • pip install
  • Upgrading pip
  • Handling dependency conflicts
• Python packaging basics
  • requirements.txt
  • pip freeze
  • Using setup.py
• Basic debugging
  • print debugging
  • pdb
  • VS Code debugger
• Type hints
  • Optional, Union, List, Dict
  • Typing in ML projects
• Functional programming concepts
  • map, filter, reduce
  • Immutability
• Essential coding skills for AI
  • Vectorized thinking
  • Efficient loops
  • Code structuring for ML experiments

 Download Detailed Syllabus

• Numpy Arrays Deep Dive
  • ndarray structure
  • Shape, size, strides
  • Memory layout: C vs Fortran order
  • Data types: float16, float32, float64 (important for GPUs)
• Array creation
  • arange
  • linspace
  • zeros, ones, full
  • identity, eye
• Indexing & slicing
  • Basic slicing
  • Boolean indexing
  • Fancy indexing
  • Negative indexing
  • Multidimensional slicing
• Array reshaping
  • reshape
  • ravel vs flatten
  • expand_dims
  • squeeze
  • Broadcasting rules
• Mathematical operations
  • Element-wise operations
  • dot vs matmul
  • Norms
  • Log, exp, sqrt
  • Softmax implementation
  • Stable softmax (important in attention layers for Transformers)
• Linear algebra module
  • matrix inverse
  • eigenvalues and eigenvectors
  • determinants
  • solve linear equations
• Random number generation
  • rng = np.random.default_rng()
  • Normal distribution
  • Uniform distribution
  • Multivariate Gaussian
• Aggregations
  • sum, mean, var, std
  • axis operations
  • min/max
  • argmax
• Vectorization
  • Avoiding loops
  • Vectorizing Python functions
  • Speed comparisons
• Broadcasting
  • Rules
  • Examples
  • Practical usage in attention scoring
• Memory efficiency
  • Avoiding unnecessary copies
  • Using views
  • In-place operations
• Numerically stable operations
  • softmax
  • log-sum-exp
  • small epsilon tricks
• Practical Numpy for AI
  • Implementing dot products
  • Cosine similarity
  • Euclidean distance
  • Vector norms
• Working with images
  • Loading
  • Reshaping
  • Normalizing
• GPU-compatible concepts
  • float16 vs float32
  • Batch operations

 Download Detailed Syllabus

• DataFrames
  • Creating
  • Inspecting
  • dtypes
• Importing data
  • CSV
  • JSON
  • SQL
  • Excel
• Data cleaning
  • Removing NA
  • Imputing
  • Detecting duplicates
• Data preprocessing
  • Encoding categorical variables
  • Label encoding
  • One-hot encoding
• Feature scaling
  • MinMaxScaler
  • StandardScaler
• Aggregations
  • groupby
  • pivot tables
  • multi-index
• Merging & joining
  • inner, left, right, outer joins
• Text columns
  • string operations
  • regex filtering
• Time series
  • converting to datetime
  • resampling
• Data exporting
  • Save to CSV
  • Save to JSON

 Download Detailed Syllabus

• Matplotlib deep usage
• Subplots
• Styling
• Histograms
• Scatter plots
• Pairplots
• Density plots
• Heatmaps
• Boxplots
• Trend lines
• Correlation matrix
• Visualizing distributions
• Understanding skewness
• Plotting confusion matrices
• Plotting learning curves
• Visualizing embeddings (PCA, t-SNE)

 Download Detailed Syllabus

• ML pipeline
• Bias/variance
• Overfitting
• Regularization
• Loss functions
• Convex vs non-convex optimization
• Gradient descent
• Stochastic GD
• Mini-batch GD
• Hyperparameters
• Choosing metrics
• Cross-validation
• Train/test split
• Model selection
• Feature engineering
• Normalization
• Standardization
• Outlier handling
• ML evaluation workflow
• Pitfalls in ML experiments

 Download Detailed Syllabus