archive-edu.com » EDU » C » COLUMBIA.EDU

Total: 442

Choose link from "Titles, links and description words view":

Or switch to "Titles and links view".

  • I warning learn topics num topics reducing to d dimensions instead of d small dim num topics else small dim num topics end W eigvecs diag 1 sqrt eigvals time eigs toc tic eigs weighted mean X z3 lambda inf num topics 1 theta zeros small dim num topics time topics zeros num topics 1 for topic 1 num topics tic topic tic for trial 1 num trials if init opt 1 current theta randn small dim 1 elseif init opt 2 current theta W gamrnd 1 1 num words 1 elseif init opt 3 current theta W X ceil rand num docs else error unknown initialization option end current theta current theta norm current theta current lambda inf for iter 1 max iters 1 eta W current theta dotprods X eta update W X z3 dotprods 2 2 eta 2 weighted mean 2 eta X z3 dotprods X z3 X eta 2 theta 1 topic 1 lambda 1 topic 1 1 theta 1 topic 1 current theta 2 objval dot update current theta converged objval current lambda lambda topic theta topic current theta lambda topic current lambda end end time topics topic toc tic topic end tic em tic

    Original URL path: http://www.cs.columbia.edu/~djhsu/code/learn_topics.m (2016-02-17)
    Open archived version from archive


  • size X doc lengths sum X 1 if any doc lengths 1e 5 small dim length I eigvecs eigvecs I eigvals eigvals I warning learn lda topics num topics reducing to d dimensions instead of d small dim num topics else small dim num topics end sqrteigvals sqrt eigvals W eigvecs diag 1 sqrteigvals time eigs toc tic eigs weighted mean1 X z1 weighted mean3 X z3 lambda inf num topics 1 theta zeros small dim num topics time topics zeros num topics 1 for topic 1 num topics tic topic tic for trial 1 num trials if init opt 1 current theta randn small dim 1 elseif init opt 2 current theta W gamrnd 1 1 num words 1 elseif init opt 3 current theta W X ceil rand num docs else error unknown initialization option end current theta current theta norm current theta current lambda inf for iter 1 max iters 1 eta W current theta dotprods X eta dotmean dot weighted mean1 eta sqrtP eta diag sqrteigvals eigvecs eta update W X z3 dotprods 2 2 eta 2 weighted mean3 2 eta X z3 dotprods X z3 X eta 2 alpha0 alpha0 2 2 dotmean eigvecs diag

    Original URL path: http://www.cs.columbia.edu/~djhsu/code/learn_lda_topics.m (2016-02-17)
    Open archived version from archive

  • Tony Jebara
    Jebara Computer Science Columbia University Mail 500 West 120 St Rm 450 Mail Code 0401 New York NY 10027 Office 530 West 120 St Rm 605 CEPSR The Columbia Machine Learning Lab pursues research in machine learning with applications in

    Original URL path: http://www.cs.columbia.edu/~jebara/ (2016-02-17)
    Open archived version from archive

  • Home Page of Gail Kaiser
    students interested in investigation and discussion and inappropriate for students who just want to listen to lectures and do homeworks More information is available here Prof Kaiser will teach COMS W4156 Advanced Software Engineering again in Fall 2016 This is a lecture and lab course that focuses on how to develop mobile web cloud applications leveraging open source software third party frameworks and industry standard project management tools and repositories The course will cover modern agile processeses object oriented analysis and design and rigorous software testing This course will teach you more of what employers in the software industry expect you to know than any other course offered at Columbia 4156 is required for the MS computer security and software systems tracks Undergraduate CS and CE juniors and seniors are strongly encouraged to take the course MS students from other tracks PhD students and non majors are also very welcome Prof Kaiser is seeking undergraduate and MS project students for Spring 2016 and beyond with preference for students who might be available for two or more consecutive semesters possibly but not necessarily including summer Contact her by email if interested Breaking News 11 12 15 Seek Funding Step Added To Scientific Method Slides from Prof Kaiser s Distinguished Lecture at the University of Southern California from April 18 2013 Alex Orso s advice on how to get your paper accepted at a top software engineering conference Prof Kaiser s advice on finding related work for conference papers Prem Devanbu s Review Anti Patterns Automatic Systems Research Topic or Paper Title Generator Current PSL Doctoral Students Nipun Arora Jonathan Bell see Jon s tool for choosing a project acronym Mike Fang Hsiang Su Riley Spahn co advised with Prof Geambasu Jeffrey Bender co advised with Prof Lee Teachers College Former PSL

    Original URL path: http://www.cs.columbia.edu/~kaiser/ (2016-02-17)
    Open archived version from archive


  • each other Mom Now everything is fine Dad We just saw the PG 13 movie It was so good Mom There was a big sex Friend from work I am the loudest I am the loudest Everybody laughs Mom I had a lot of wine and now I m crazy Grandfather Hey do you guys know what God looks like All Yes Grandfather Don t tell the kids From www edge org What s your law Chalupa s Second Don t underestimate the importance of fashion in doing science Levy s The truth is always more interesting than your preconception of what it might be Warwick s First Art takes you out of town and gives you a destination Science builds the bus that takes you there Zangger s Second Truly great science is always ahead of its time Lucius Annaeus Seneca realized this already two thousand years ago when he said The time will come when our successors will be surprised that we did not know such obvious things Norretranders The difficulty in understanding new ideas originating from science or art is not intellectual but emotional Venter s Fifth Life is like sailing It is easy to run downwind but usually if you want to get somewhere worthwhile a long hard beat to weather is necessary Dawkins When two incompatible beliefs are advocated with equal intensity the truth does not lie halfway between them Blakemore s First People are never more honest than you think they are Maddox s Second Reviewers who are best placed to understand an author s work are the least likely to draw attention to its achievements but are prolific sources of minor criticism especially the identification of typos Schank s Any new idea will be treated as a variant of something the listener has

    Original URL path: http://www.cs.columbia.edu/~jrk/plan.txt (2016-02-17)
    Open archived version from archive

  • CSEE 3827, Spring 2016
    grade when calculating final grades Collaboration and Academic Integrity We take academic honesty extremely seriously and expect the same of you You may discuss homework problems with your classmates however each student is to write up his or her own solution and is expected to be able to explain and reproduce the work he or she submits Please note the names of your collaborators at the top of your homework submission Apart from these exceptions the Computer Science Department s Academic Honesty policy is in effect Grading Rubric Top Five Homeworks 40 In Class Tests 30 30 Textbooks There are no required texts If you want to use a text we recommend Logic and Computer Design Fundamentals 4th ed by M Morris Mano and Charles Kime ISBN 10 0 13 198926 X ISBN 13 978 0 13 198926 9 Computer Organization and Design The Hardware Software Interface 4th ed by David A Patterson and John L Hennessy ISBN 978 0 12 374493 7 Digital Design and Computer Architecture 2nd ed by D Harris and S Harris ISBN 978 0 12 394424 5 Syllabus Date Topic s Reading Slides Homework Due Tue 1 19 Representing Numbers Prof Edwards M K 1 4 3 4 4 10 7 H H 1 4 P H 3 5 binary pdf Thu 1 21 Admin Boolean Logic M K 2 1 2 5 2 8 2 9 H H 1 5 2 1 2 7 admin pdf boolean pdf Tue 1 26 Thu 1 28 Combinational Logic M K 3 1 3 3 3 3 6 3 9 4 1 4 2 4 5 9 4 H H 2 8 2 9 5 2 combinational pdf Tue 2 2 hw1 pdf hw1 solutions pdf Thu 2 4 Sequential Logic M K 5 1 5 3

    Original URL path: http://www.cs.columbia.edu/~martha/courses/3827/sp16/ (2016-02-17)
    Open archived version from archive

  • CSEE 3827, Fall 2015
    and expect the same of you You may discuss homework problems with your classmates however each student is to write up his or her own solution and is expected to be able to explain and reproduce the work she or she submits Please note the names of your collaborators at the top of your homework submission Apart from these exceptions the Computer Science Department s Academic Honesty policy is in effect Grading Rubric Top Five Homeworks 40 Exams 30 30 Textbooks There are no required texts Recommended texts are Logic and Computer Design Fundamentals 4th ed by M Morris Mano and Charles Kime ISBN 10 0 13 198926 X ISBN 13 978 0 13 198926 9 Computer Organization and Design The Hardware Software Interface 4th ed by David A Patterson and John L Hennessy ISBN 978 0 12 374493 7 Digital Design and Computer Architecture 2nd ed by D Harris and S Harris ISBN 978 0 12 394424 5 Syllabus Date Topic s Reading Slides Homework Due Tue 9 8 Representing Numbers M K 1 4 3 4 4 10 7 H H 1 4 P H 3 5 intro pdf Thu 9 10 Boolean Logic M K 2 1 2 5 2 8 2 9 H H 1 5 2 1 2 7 boolean pdf Tue 9 15 Thu 9 17 Combinational Logic M K 3 1 3 3 3 3 6 3 9 4 1 4 2 4 5 9 4 H H 2 8 2 9 5 2 combinational pdf Tue 9 22 Thu 9 24 Sequential Logic M K 5 1 5 3 5 6 H H 3 1 3 3 3 5 sequential pdf hw1 pdf hw1 solutions pdf Tue 9 29 Thu 10 1 Finite State Machines M K 5 4 5 5 H

    Original URL path: http://www.cs.columbia.edu/~martha/courses/3827/au15/ (2016-02-17)
    Open archived version from archive

  • Kim Course List
    and Practice of Parallel Programming Autumn 2013 Fundamentals of Computer Systems Autumn 2012 Fundamentals of Computer Systems Spring 2012 Principles and Practice of Parallel Programming Autumn 2012 Fundamentals of Computer Systems Spring 2011 Principles and Practice of Parallel Programming Autumn

    Original URL path: http://www.cs.columbia.edu/~martha/courses.html (2016-02-17)
    Open archived version from archive