• Python Basics (Loops, Functions, etc.) 
• NumPy and Pandas for Data Handling 
• Matplotlib and Seaborn for Visualization 
• Scikit-learn for ML 
• PyTorch Basics 
• Tensor (Multi-dimensional Array) Manipulation 
• Training Models on CPU and GPU

• Linear Regression 
• Logistic Regression 
• L1 & L2 Regularization 
• K-Nearest Neighbors (K-NN) 
• Decision Trees 
• Model Ensembles (Gradient Boosting, Bagging,
• Random Forest)
• Support Vector Machines (SVM) 

• K-Means Clustering 
• Principal Component Analysis (PCA) 
• t-SNE, UMAP 
• DBSCAN, Hierarchical & Spectral Clustering

• Model Evaluation Metrics (Accuracy, Precision, Recall, F1-Score, etc.)
• Underfitting, Overfitting 
• Hyperparameter Tuning 
• Cross-Validation 
• Confusion Matrix and ROC Curves
• Feature Engineering  
• Data Processing 

• Text Classification 
• Pre-trained Text Encoders (e.g. BERT)
• Language Modeling 
• Pre-trained Language Models (open-source and API-based ones)

• Perceptron Basics 
• Gradient Descent 
• Backpropagation 
• Activation Functions (ReLU, Sigmoid, Tanh)
• Loss Functions (MSE, MAE, Cross Entropy, etc.) 

• Loss Functions (MSE, MAE, Cross Entropy, etc.) 
• Deep Learning Multi-Layer Perceptrons (MLP)
• Data Embeddings (text, image, audio) 
• Pooling Techniques (Max, Average) 
• Attention Mechanism
• Transformers (theory needed only for text and image)
• Autoencoders 
• SGD, Mini-Batch Gradient Descent
• Momentum Methods (Adam, AdamW) 
• Convergence and Learning Rates 
• Regularization: Dropout, Early Stopping, Weight Decay
• Weight Initialization 
• Batch Normalization 
• Model Finetuning (full and parameter-efficient)

• Convolutional Layers 
• Image Classification 
• Image Segmentation (U-Net) 
• Pre-trained Vision Encoders (e.g. ResNet) 
• Image Augmentation
• Vision-text encoders (e.g. CLIP)

• Classification Metrics
• Bias-Variance Tradeoff

https://ioai-official.org/wp-content/uploads/2025/10/Syllabus.pdf