Teaching

Teaching Associate at the Hertie School of Governance’s MSc Data Science programme.

Deep Learning

Lab materials and exercises covering neural network architectures, problem applications and basic deployment.

Topics covered:

• Neural network fundamentals and backpropagation
• Convolutional Neural Networks (CNNs) for computer vision
• Recurrent Neural Networks (RNNs) and sequence modeling
• Transformers and attention mechanisms
• Generative models (VAEs, GANs)
• Practical implementation with PyTorch

GitHub Repository · Companion Notes (PDF) · ML Prerequisite Notes (PDF)

Data Structures & Algorithms

Lab materials and exercises covering fundamental data structures and algorithmic problem solving essential for efficient programming and technical interviews.

Topics covered:

• Arrays, linked lists, stacks, and queues
• Trees, graphs, and hash tables
• Sorting and searching algorithms
• Dynamic programming and greedy algorithms
• Algorithm complexity analysis (Big O notation)
• Problem-solving strategies and coding exercises

GitHub Repository · Companion Notes (PDF)

Mathematics for Data Science

Foundational mathematics for data science and machine learning.

Topics covered:

• Probability Theory - Random variables, distributions, Bayes’ theorem, expectation and variance
• Calculus - Differentiation, integration, multivariate calculus, optimisation
• Linear Algebra - Vectors, matrices, eigenvalues, singular value decomposition, matrix factorization
• Optimisation - Gradient descent, convex optimisation, constrained optimisation

Companion Notes (PDF)

Powered by Jekyll and Minimal Light theme.