Tracking my progress toward a Master's in AI and Machine Learning. Follow along as I complete foundational courses and build practical projects.
Real-time tracking of course completion and skill development
Complete roadmap of Coursera and edX courses (with certificates) to become a strong candidate for the MFF UK Computer Science – AI Master's programme.
Phase 1 · Math Foundations
University of Sydney — Coursera
Key Topics: Limits, derivatives, integrals, single-variable calculus basics.
Phase 1 · Math Foundations
University of Sydney — Coursera
Key Topics: Series, multivariable ideas, deeper calculus intuition.
Phase 1 · Math Foundations
Imperial College London — Coursera
Key Topics: Linear algebra, multivariate calculus, PCA for ML.
Phase 1 · Math Foundations
Key Topics: Linear algebra, calculus, probability & statistics for ML.
Phase 1 · Math Foundations
Key Topics: Probability theory, random variables, expectation, inference.
Phase 2 · Discrete Math & Logic
Key Topics: Logic, proofs, combinatorics, graph theory, discrete probability.
Phase 2 · CS Foundations
Key Topics: C, Python, data structures, algorithms, web basics.
Phase 2 · CS Foundations
University of Michigan — Coursera
Key Topics: Python basics, files, APIs, databases.
Phase 2 · CS Foundations
Key Topics: Search, optimization, ML, neural networks, AI applications.
Phase 3 · Algorithms
Key Topics: Data structures, greedy, dynamic programming, graph algorithms.
Phase 3 · Algorithms
Key Topics: Algorithm analysis, advanced data structures, performance.
Phase 4 · Computer Systems
Hebrew University of Jerusalem — Coursera
Key Topics: Logic gates, CPU, memory, low-level computer architecture.
Phase 4 · Computer Systems
Key Topics: CPU microarchitecture, pipelines, memory hierarchy.
Phase 4 · Computer Systems
Key Topics: Processes, scheduling, memory management, synchronization.
Phase 5 · Theory of Computation
Key Topics: Automata, formal languages, Turing machines, computability.
Phase 5 · Theory of Computation
Key Topics: Regular languages, CFGs, Turing machines, decidability, complexity.
Phase 6 · Core AI / ML
Andrew Ng / DeepLearning.AI — Coursera
Key Topics: Supervised & unsupervised learning, model evaluation, ML practice.
Phase 6 · Core AI / ML
Key Topics: Neural networks, CNNs, RNNs, optimization & regularization.
Phase 7 · Advanced AI
University of Alberta — Coursera
Key Topics: MDPs, value iteration, policy gradients, Q-learning.
Phase 7 · Advanced AI
Key Topics: Classic NLP, word embeddings, seq2seq, transformers.
Focused subset of courses chosen specifically to prepare for the MFF UK Computer Science take-home entrance exam (proofs, algorithms, discrete math, and automata).
Introduction to Discrete Mathematics for Computer Science · UCSD & HSE (Coursera)
Primary source for proofs, induction, combinatorics, graphs, and logic — the backbone of most take-home exam questions.
Status: Planned · Exam-critical
Data Structures and Algorithms · UCSD & HSE (Coursera)
Directly trains algorithm design, complexity analysis, and correctness proofs that appear in entrance exam tasks.
Status: Planned · Exam-critical
Automata and Computability · Coursera
Covers finite automata, regular languages, CFLs, grammars, Turing machines, and decidability — all central to theory questions.
Status: Planned · Exam-critical
Automata Theory · StanfordOnline (edX)
Deepens understanding of automata, grammars, and complexity theory; perfect for tackling harder theoretical questions.
Status: Planned · Exam reinforcement
Mathematics for Machine Learning: Linear Algebra · Imperial (Coursera)
Ensures comfort with vectors, matrices, and linear transformations, which support some algebra-heavy proof questions.
Status: Planned · Exam support
Probability: The Science of Uncertainty and Data · MITx (edX)
Strengthens probability and counting skills; useful for exam problems involving random variables and combinatorial reasoning.
Status: Planned · Exam support
Practical applications of concepts learned through coursework
Implementing a basic neural network using only NumPy to understand the mathematical foundations of deep learning. This project involves building forward propagation, backpropagation, and gradient descent algorithms.
Interactive web application that visualizes various sorting algorithms (bubble sort, merge sort, quick sort, heap sort) to better understand their time complexity and behavior.
Comprehensive Python toolkit for statistical analysis including hypothesis testing, regression analysis, and data visualization. Designed to reinforce concepts from statistics coursework.
Curated collection of books, papers, and online resources for AI/ML mastery
I'm documenting my entire learning process from foundational mathematics to advanced AI concepts. Follow along as I work toward my goal of entering a Master's program in AI and Machine Learning.