Print Settings
 

CS 21SI: AI for Social Good

Students will learn about and apply cutting-edge artificial intelligence techniques to real-world social good spaces (such as healthcare, government, education, and environment). Taught jointly by CS+Social Good and the Stanford AI Group, the aim of the class is to empower students to apply these techniques outside of the classroom. The class will focus on techniques from machine learning and deep learning, including regression, support vector machines (SVMs), neural networks, convolutional neural networks (CNNs), and recurrent neural networks (RNNs). The course alternates between lectures on machine learning theory and discussions with invited speakers, who will challenge students to apply techniques in their social good domains. Students complete weekly coding assignments reinforcing machine learning concepts and applications. Prerequisites: programming experience at the level of CS107, mathematical fluency at the level of CS103, comfort with probability at the level of CS109 (or equivalent). Application required for enrollment.
Terms: Spr | Units: 2 | Grading: Satisfactory/No Credit

CS 103: Mathematical Foundations of Computing

Mathematical foundations required for computer science, including propositional predicate logic, induction, sets, functions, and relations. Formal language theory, including regular expressions, grammars, finite automata, Turing machines, and NP-completeness. Mathematical rigor, proof techniques, and applications. Prerequisite: CS106B or equivalent. CS106B may be taken concurrently with CS103.
Terms: Aut, Win, Spr | Units: 3-5 | UG Reqs: GER:DB-Math, WAY-FR | Grading: Letter or Credit/No Credit

CS 103A: Mathematical Problem-solving Strategies

Problem solving strategies and techniques in discrete mathematics and computer science. Additional problem solving practice for CS103. In-class participation required. Prerequisite: consent of instructor. Co-requisite: CS103.
Terms: Aut, Win, Spr | Units: 1 | Grading: Satisfactory/No Credit
Instructors: ; Lee, C. (PI); Schwarz, K. (PI)

CS 124: From Languages to Information (LINGUIST 180, LINGUIST 280)

Extracting meaning, information, and structure from human language text, speech, web pages, social networks. Methods include: string algorithms, edit distance, language modeling, the noisy channel, naive Bayes, inverted indices, collaborative filtering, PageRank. Applications such as question answering, sentiment analysis, information retrieval, text classification, social network models, chatbots, sequence alignment, spell checking, speech processing, recommender systems. Prerequisites: CS103, CS107, CS109.
Terms: Win | Units: 3-4 | Grading: Letter or Credit/No Credit

LINGUIST 180: From Languages to Information (CS 124, LINGUIST 280)

Extracting meaning, information, and structure from human language text, speech, web pages, social networks. Methods include: string algorithms, edit distance, language modeling, the noisy channel, naive Bayes, inverted indices, collaborative filtering, PageRank. Applications such as question answering, sentiment analysis, information retrieval, text classification, social network models, chatbots, sequence alignment, spell checking, speech processing, recommender systems. Prerequisites: CS103, CS107, CS109.
Terms: Win | Units: 3-4 | Grading: Letter or Credit/No Credit

LINGUIST 280: From Languages to Information (CS 124, LINGUIST 180)

Extracting meaning, information, and structure from human language text, speech, web pages, social networks. Methods include: string algorithms, edit distance, language modeling, the noisy channel, naive Bayes, inverted indices, collaborative filtering, PageRank. Applications such as question answering, sentiment analysis, information retrieval, text classification, social network models, chatbots, sequence alignment, spell checking, speech processing, recommender systems. Prerequisites: CS103, CS107, CS109.
Terms: Win | Units: 3-4 | Grading: Letter or Credit/No Credit
© Stanford University | Terms of Use | Copyright Complaints