Visit plans.ucsd.edu to find a personalized 4yearplan by college.
Lower Division Requirements
(11 courses, 44 units or 10 courses, 40 units)
Math
 MATH 10A, 10B, 10C, 18
 OR MATH 20A, 20B, 18 *
* Machine Learning students are strongly advised to take MATH 20ABCE and MATH 18 and 180A, as they are prerequisites for COGS 118ABCD, of which 2 are required for the Machine Learning Specialization.

Should student have completed Math 10A + B + C, then the next Math to take is Math 20B + C + E + 18 then 180A.

Should student have completed Math 10A + B, then the next Math to take is Math 20B + C + E + 18 then 180A.

Should student have completed Math 10A, then the next Math to take is Math 20A + B + C + E + 18 then 180A.
Cognitive Science
 Introduction: COGS 1
 Design: COGS 10 or DSGN 1
 Methods: COGS 13, 14A, 14B
 Neuroscience: COGS 17
 Programming: COGS 18 * or CSE 8A or 11
* Machine Learning students are strongly advised to take COGS 18, as it is a prerequisite for Cogs 118ABCD, of which 2 are required for the Machine Learning Specialization.
Upper Division Requirements
(12 courses, 48 units)
Core (6 courses)
 Distributed Cognition: COGS 100
 Fundamental Cognitive Phenomena (choose any 2): COGS 101A, 101B, 101C
 Cognitive Neuroscience (choose any 2): COGS 107A, 107B, 107C
 Computation: COGS 108
Electives (6 courses)
 A total of 6 electives are required, where at least 3 of the 6 electives must be taken within the Cognitive Science department. At least 4 of the 6 electives must be taken from the approved specialization elective list.
 Students specializing in Machine Learning and Neural Computation must choose 2 from this group of classes for their Specialization Electives: COGS 118A, 118B, 118C, and 118D.
 One course in the Cognitive Science 19X series may be used as an elective to satisfy the requirements for the B.S. degree, but only with the approval of both the instructor who supervised the course and the undergraduate advisor.
 COGS 160 may only be used once for an elective.
Approved Electives (PDF)
Approved Specialization Electives (PDF)
Alert
Courses for the major must be taken for a letter grade (with the exception of 195, 198, and 199 which are only offered on a P/NP basis). A minimum grade of C is required for all courses.
Virginia de Sa. Professor, CSB 164, 8588225095, vdesa@cogsci.ucsd.edu, website. Research: We use computational modeling, psychophysics studies, and machine learning to learn more about visual and multisensory perception.
Jason Fleischer. Assistant Teaching Professor, CSB 257, jfleischer@ucsd.edu, website. Research: Using machine learning to extract knowledge from complex biological datasets. Gene expression changes with aging. Circadian metabolism and human health. Computational neuroscience.
Marcelo Mattar. Assistant Professor, SSRB 232, mmattar@ucsd.edu, website. Research: Reinforcement learning, planning, memory, network neuroscience, computational neuroscience, probabilistic inference. How we learn predictive representations of the world and how we simulate the future when making a decision.
Eran Mukamel. Assistant Professor, SSRB 255, 8588223713, emukamel@ucsd.edu, website. Research: Computational analysis of largescale neural data, electrophysiology of sleep and general anesthesia, computational epigenomics in brain cells.
Zhuowen Tu. Associate Professor, SSRB 250, 8588220908, ztu@ucsd.edu, website. Research: Computer vision, machine learning, deep learning, neural computation, neuro imaging.
Bradley Voytek. Associate Professor, CSB 169, 8585340002, bvoytek@ucsd.edu, website. Oscillatory network communication, automated science, datamining, aging, attention, working memory, cognitive braincomputer interfaces, brain/cognition/society interactions.
Angela J. Yu. Associate Professor, CSB 157, 8588223317, ajyu@cogsci.ucsd.edu, website. Research: Decision making, attention, active vision, learning, neuromodulation, Bayesian modeling, control theory.
Faculty with Related Research
Philip Guo. Assistant Professor, CSB 129, pg@ucsd.edu, website. Research: Humancomputer interaction, design, online learning, computing education, programmer productivity.
Ayse P. Saygin. Associate Professor, SSRB 20220, 8588221994, saygin@cogsci.ucsd.edu, website. Research: Cognitive neuroscience, neuropsychology, neuroimaging, visual perception, attention, multisensory integration, biological motion, social neuroscience, language comprehension, humanmachine interaction, social robotics.
Terrence J. Sejnowski. Adjunct Professor, CNL/Salk, 8584534100 Ext. 1611, terry@salk.edu, website. Research: Computational neurobiology; the representation, transformation, and storage of information in the nervous system.
COGS 8. Handson Computing (4)
Introductorylevel course that will give students insight into the fundamental concepts of algorithmic thinking and design. The course will provide the students with firstperson, handson experience programming a web crawler and simple physical robots.
COGS 9. Introduction to Data Science (4)
Concepts of data and its role in science will be introduced, as well as the ideas behind datamining, textmining, machine learning, and graph theory, and how scientists and companies are leveraging those methods to uncover new insights into human cognition.
COGS 18. Introduction to Python (4)
This class will teach fundamental Python programming skills and practices, including the "Zen of Python." Students will focus on scientific computing and learn to write functions and tests, as well as how to debug code, using Jupyter notebook programming environment.
COGS 108. Data Science in Practice (4)
Data science is multidisciplinary, covering computer science, statistics, cognitive science and psychology, data visualization, artificial intelligence, and machine learning, among others. This course teaches critical skills needed to pursue a data science career using handson programming and experimental challenges. Prerequisites: Cognitive Science 18 or MAE 8 or CSE 8A or CSE 11.
COGS 109. Modeling and Data Analysis (4)
Exposure to the basic computational methods useful throughout cognitive science. Computing basic statistics, modeling learning individuals, evolving populations, communicating agents, and corpusbased linguistics will be considered. Prerequisites: COGS 14B, MATH 18 or MATH 31AH, and COGS 18 or CSE 7 or CSE 8A or CSE 11.
COGS 118A. Supervised Machine Learning Algorithms (4)
This course introduces the mathematical formulations and algorithmic implementations of the core supervised machine learning methods. Topics in 118A include regression, nearest neighborhood, decision tree, support vector machine, and ensemble classifiers. COGS 118AB may be taken in either order. Prerequisites: (COGS 18 or CSE 8B or CSE 11) and (MATH 18 or MATH 31AH) and MATH 20E and MATH 180A and (COGS 108 or COGS 109 or COGS 118B or CSE 150 or CSE 151 or CSE 158 or ECE 174 or ECE 175A) or consent of instructor.
COGS 118B. Intro to Machine Learning II (4)
This course, with Cognitive Science 118A, forms a rigorous introduction to machine learning. Cognitive Science 118AB may be taken in either order. Topics in 118B include: maximum likelihood estimation, Bayesian parameter estimation, clustering, principal component analysis, and some application areas. Prerequisites: CSE 8B or CSE 11 and Math 18 or Math 31AH and Math 20E and Math 180A or consent of instructor.
COGS 118C. Neural Signal Processing (4)
This course will cover theoretical foundations and practical applications of signal processing to neural data. Topics include EEG/field potential methods (filtering, Fourier (spectral) analysis, coherence) and spike train analysis (reverse correlation, spike sorting, multielectrode recordings). Some applications to neural imaging (optical microscopy, fMRI) data will also be discussed. Prerequisites: Math 18 or Math 31AH, Cognitive Science 14B or Psychology 60, and Cognitive Science 108 or Cognitive Science 109.
COGS 118D. Mathematical Statistics for Behavioral Data Analysis (4)
Statistical methods for analyzing behavioral data. A mathematically sophisticated course covering both classical and Bayesian statistical methods for estimation, hypothesis testing, regression, and model comparison. Emphasis on both mathematical understanding of statistical methods as well as common applications. Prerequisites: Math 18 or Math 31AH and Math 180A or consent of instructor.
COGS 180. Decision Making in the Brain (4)
This course covers recent advances in the understanding of neural mechanisms and computational principles underlying the brain’s ability to make decisions. The role of various factors, as well as their neural encoding, will be considered, e.g., observation noise, reward, risk, internal uncertainty, emotional state, external incentives. Prerequisites: (BILD12 or COGS17) and (COGS108 or COGS109 or CSE150A) and (MATH18 or MATH20B or MATH31AH)
COGS 181. Neural Networks and Deep Learning (4)
This course will cover the basics about neural networks, as well as recent developments in deep learning including deep belief nets, convolutional neural networks, recurrent neural networks, longshort term memory, and reinforcement learning. We will study details of the deep learning architectures with a focus on learning endtoend models for these tasks, particularly image classification. Prerequisites: (COGS18 or CSE11 or CSE8B) and (MATH18 or MATH31AH) and (MATH20E) and (MATH180A) and (COGS118A or COGS118B or CSE150 or CSE151 or CSE158 or ECE174 or ECE175A)
COGS 182. Introduction to Reinforcement Learning (4)
This course is an introduction to Reinforcement Learning, the subfield of Machine Learning concerned with how artificial agents learn to act in the world in order to maximize reward. Topics include MDPs, Policy iteration, TD learning, Qlearning, function approximation, deep RL. Prerequisites (COGS18 or CSE11 or CSE8B) and (MATH18 or MATH31AH) and (MATH180A) and (COGS108 or COGS109 or COGS118B or CSE150A or CSE150B or CSE151A or CSE151B or CSE158 or ECE174 or ECE175A)
COGS 185. Advanced Machine Learning Methods (4)
This course is an advanced seminar and project course that follows the Introduction to Machine Learning courses. Advanced and new machine learning methods will be discussed and used. Prerequisites: Cognitive Science 118B or Cognitive Science 118A.
COGS 188. Artificial Intelligence Algorithms (4)
This class will cover a broad spectrum of machine learning algorithms. It builds on students' previous exposure to machine learning. It covers new artificial intelligence algorithms ranging from topic models as used in the text data analysis to genetic algorithms. Prerequisites: Cognitive Science 109 or Cognitive Science 118A or Cognitive Science 118B.
COGS 189. Brain Computer Interfaces (4)
This course will discuss signal processing, pattern recognition algorithms, and humancomputer interaction issues in EEGbased braincomputer interfaces. Other types of braincomputer interfaces will also be discussed. Prerequisites: Cognitive Science 108 or Cognitive Science 109 or Cognitive Science 118A or Cognitive Science 118B.