Notes

Neural architectures, backpropagation, attention, and representation learning · 213 pages total

• DL Fundamentals & Optimization Algorithms 42 pages

  October 13, 2026

  Handwritten notes on deep learning fundamentals: neural network architectures, activation functions, backpropagation, and optimization algorithms (SGD, Adam, RMSProp).

• Model Performance Measurements 21 pages

  October 12, 2026

  Handwritten notes on evaluating deep learning models: loss functions, accuracy metrics, confusion matrices, ROC curves, and regularization techniques.

• Convolutional Neural Networks 71 pages

  October 11, 2026

  Handwritten notes on CNNs: convolution operations, pooling layers, feature maps, architectures (LeNet, AlexNet, VGG, ResNet), and transfer learning.

• Sequence Modelling: RNNs, GRUs & LSTMs 64 pages

  October 10, 2026

  Handwritten notes on sequence modelling: recurrent neural networks, vanishing gradients, GRU and LSTM gating mechanisms, and bidirectional architectures.

• Transformer & Sampling 15 pages

  October 9, 2026

  Handwritten notes on the Transformer architecture: self-attention, multi-head attention, positional encoding, and sampling strategies for text generation.

Pre-training, scaling laws, architectures, fine-tuning, and alignment · 4 pages total

• LLM Pre-training and Scaling Laws 4 pages

  October 27, 2026

  Notes on LLM pre-training pipelines, multi-GPU distributed training with DDP vs. FSDP, Chinchilla scaling laws, and pre-training for domain adaptation.

Classical ML, optimization algorithms, probabilistic models, and loss functions · 147 pages total

• Supervised Learning 32 pages

  October 7, 2026

  Handwritten notes on supervised learning: regression, classification, decision boundaries, loss functions, and model evaluation.

• Advanced Algorithms & Evaluation Metrics 59 pages

  October 6, 2026

  Handwritten notes on advanced ML algorithms and evaluation: ensemble methods, SVMs, tree-based models, ROC curves, and performance metrics.

• Unsupervised Learning 38 pages

  October 5, 2026

  Handwritten notes on unsupervised learning: clustering algorithms, dimensionality reduction, anomaly detection, and density estimation.

• Reinforcement Learning 18 pages

  October 4, 2026

  Handwritten notes on reinforcement learning: Markov decision processes, Q-learning, policy gradients, reward shaping, and exploration vs exploitation.

Linear algebra, multivariable calculus, probability, and statistics for ML · 238 pages total

• Algebra for Machine Learning 49 pages

  October 5, 2026

  Comprehensive handwritten notes covering linear algebra foundations for machine learning: vectors, matrices, row echelon form, norms, projections, linear regression, and dimensionality reduction.

• Calculus for Machine Learning 47 pages

  October 4, 2026

  Handwritten notes on calculus essentials for ML: derivatives, partial derivatives, gradient descent, chain rule, and multivariate optimization.

• Probability for Machine Learning 74 pages

  October 3, 2026

  Handwritten notes covering probability theory for ML: random variables, Bayes' theorem, distributions, expectation, variance, and probabilistic reasoning.

• Statistics for Machine Learning 68 pages

  October 2, 2026

  Handwritten notes on statistics for ML: descriptive statistics, hypothesis testing, confidence intervals, regression analysis, and maximum likelihood estimation.

Inference serving, memory bandwidth, hardware accelerators, and GPU execution.

• Basics of Training Optimization

  October 13, 2026

  Training optimization fundamentals — efficient training pipelines, hardware utilization, and performance tuning.