Topic Hub
Machine Learning, AI & Information
From the mathematics of probability and information theory through deep learning, machine-learning for science, and the AI/ML applications transforming biology, chemistry, and physics.
7 courses
Machine Learning →
Supervised, unsupervised, and reinforcement learning: optimisation theory, kernel methods, deep architectures, and probabilistic models.
Information Theory →
Shannon entropy, channel capacity, source and channel coding, error-correcting codes, rate-distortion, and quantum information.
Probability & Statistics →
Probability spaces, random variables, limit theorems, statistical inference, Bayesian methods, and stochastic processes.
Computer Science →
Algorithms, data structures, complexity, programming languages, systems, networks, databases, and theoretical foundations.
Bioinformatics →
Sequence alignment, genome assembly, phylogenetics, transcriptomics, structural prediction, and statistical methods for biological big data.
Signal Theory →
Time–frequency analysis, Fourier and wavelet transforms, sampling, spectral estimation, filter design, and stochastic signals.
Electronics →
From RC and RLC circuits through diodes, BJTs, MOSFETs, op-amps, digital logic, and analog–digital interfacing for the working scientist.