khal

Artificial Intelligence

Johns Hopkins University

Situates the study of Artificial Intelligence within the broader context of Cognitive Science, then covers principles and methods for reasoning, planning, and learning, including both conventional and deep learning approaches.

CSE Multivariable Calculus and Vector Analysis

University of Minnesota

Covers the derivative as a linear map, differential and integral calculus of functions of several variables including change of coordinates using Jacobians, line and surface integrals, and the theorems of Gauss, Green, and Stokes.

Classical Mechanics I

Johns Hopkins University

An in-depth introduction to classical mechanics for physics majors/minors and other students with a strong interest in physics, treating fewer topics than the general physics sequence but with greater mathematical sophistication.

Computational Linear Algebra

University of Minnesota

Covers matrices and linear transformations, linear vector spaces and inner product spaces, systems of linear equations, eigenvalues and singular values, and computational matrix methods using software such as MATLAB.

Computer System Fundamentals

Johns Hopkins University

Covers modern computer systems from a software perspective: binary data representation, machine arithmetic, assembly language, computer architecture, performance optimization, memory hierarchy, virtual memory, Unix systems programming, networking, and concurrency.

Databases

Johns Hopkins University

Introduces database management systems and database design: the relational and object-oriented data models, query languages and query optimization, transaction processing, parallel and distributed databases, recovery and security, and data mining.

Discrete Structures of Computer Science

University of Minnesota

Covers the foundations of discrete mathematics for computer science: sets, sequences, functions, big-O notation, propositional and predicate logic, proof methods, counting methods, recursion and recurrences, relations, and graph fundamentals.

Electricity and Magnetism Laboratory

Johns Hopkins University

Laboratory experiments chosen to complement the Electricity and Magnetism lecture course, introducing students to experimental techniques and statistical analysis.

General Physics II

Johns Hopkins University

The second semester of a calculus-based general physics sequence, covering wave motion, electricity and magnetism, optics, and modern physics.

Information Extraction

Johns Hopkins University

A graduate-level course covering techniques for automatically extracting structured information from unstructured text and other data sources, including named entity recognition, relation extraction, and template filling, with emphasis on statistical and machine learning approaches.

Information Retrieval and Web Agents

Johns Hopkins University

An in-depth, hands-on study of current information retrieval techniques and their application to intelligent web agents: document retrieval models, clustering, automatic indexing, query expansion, relevance feedback, and search-engine-scale IR issues.

Intermediate Programming

Johns Hopkins University

Teaches intermediate to advanced programming using C and C++: low-level programming techniques alongside object-oriented class design, pointers, dynamic memory allocation, polymorphism, inheritance, templates, collections, and exceptions.

Intro Algorithm

Johns Hopkins University

Concentrates on the design of algorithms and rigorous analysis of their efficiency: worst-case and average-case complexity, dynamic programming, sorting, searching, selection, and advanced data structures.

Introduction to Algorithms and Data Structures

University of Minnesota

Covers advanced object-oriented programming to implement abstract data types (stacks, queues, linked lists, hash tables, binary trees) in Java, including inheritance, searching/sorting algorithms, and basic algorithmic analysis.

Introduction to Computing and Programming Concepts

University of Minnesota

Introduces fundamental principles of computer science and programming, emphasizing problem solving and computing with data, using Python to implement solutions to a broad range of computational problems.

Introduction to Data Science

Johns Hopkins University

A thorough survey of data science methods balancing theory and application: supervised methods for regression and classification (regression, kNN, SVM, decision trees, random forests) and unsupervised methods (PCA, K-means, Gaussian mixtures), using Python and SQL.

Introduction to Probability and Statistics

University of Minnesota

An introductory statistics course covering elementary probability theory and an introduction to statistical inference, including testing, estimation, and confidence statements.

Machine Learning for Medical Applications

Johns Hopkins University

Covers basic principles of AI and machine learning applied to medicine, including biosignals (EEG, ECG) and medical imaging, culminating in a final project applying these techniques to a real-world medical problem.

Machine Learning: Deep Learning

Johns Hopkins University

Covers deep learning as a tool for data-intensive learning problems (supervised learning, dimensionality reduction, and control), with applications in speech, text, computer vision, medical imaging, and robotics.

Machine Learning: Reinforcement Learning

Johns Hopkins University

Covers both classical reinforcement learning and its modern counterparts behind results from AlphaGo to LLMs: Markov decision processes, dynamic programming, model-based and model-free RL, temporal difference learning, and Monte Carlo methods.

Machine Translation

Johns Hopkins University

Explores how systems like Google Translate convert text between languages, why translation systems make certain kinds of errors, and how modern translation systems learn from millions of words of already-translated text.

Mathematical Foundations for Computer Science

Johns Hopkins University

Introduces mathematical reasoning and discrete structures relevant to computer science: logic, proof techniques, sets, relations, functions, recurrences, counting, asymptotic analysis, discrete probability, graphs, and trees.

Natural Language Processing

Johns Hopkins University

An in-depth introduction to core techniques for analyzing, transforming, and generating human language, spanning linguistics, modeling, algorithms, and applications.

Natural Language Processing for Computational Social Science

Johns Hopkins University

Explores how NLP can be used to understand social phenomena that manifest in text, such as toxicity, discrimination, and propaganda, combining text-analysis methodology with statistical methods like time series analysis and causal inference.

Natural Language Processing: Self-Supervised Models

Johns Hopkins University

A thorough introduction to the self-supervised (pre-trained) learning techniques that have transformed NLP, with students designing, implementing, and understanding their own self-supervised neural network models in PyTorch.

Parallel Computing & Performance Engineering

Johns Hopkins University

Studies parallelism in data science, from instruction-level parallelism and shared-memory multicore computing to distributed computing and data-parallel frameworks like Dask, Spark, and Ray, drawing examples from data analytics and machine learning.

Regression and Statistical Computing

University of Minnesota

A second statistics course teaching students to analyze data using multiple linear regression (inference, diagnostics, validation, transformations, and model selection) and to design Monte Carlo simulation studies.

Research and Design in Applied Mathematics: Data Mining

Johns Hopkins University

A project-oriented course focused on practical applications of machine learning and data mining, in which teams of students work throughout the semester on topics chosen jointly with the instructor.

Probability & Statistics for Machine Learning & Data Science

DeepLearning.AI · Issued May 2026

Covers probability theory, common distributions, hypothesis testing, and statistical inference, the foundations used to reason about uncertainty in ML models.

Credential ID: P0XVJJRBCHM2

Calculus for Machine Learning and Data Science

DeepLearning.AI · Issued Nov 2025

Covers derivatives, gradients, and multivariable calculus, building the optimization intuition behind gradient descent and how ML models actually learn.

Credential ID: VLFXILPABP1Y

Linear Algebra for Machine Learning and Data Science

DeepLearning.AI · Issued Sep 2025

Covers vectors, matrices, eigenvalues, and linear transformations, the math underneath how data and model weights are actually represented and manipulated.

Credential ID: 7WFA7H8PGYR4