Machine Learning with Large Datasets 10-605 in Spring 2012

From Cohen Courses
Jump to navigationJump to search

Instructor and Venue

Description

Large datasets are difficult to work with for several reasons. They are difficult to visualize, and it is difficult to understand what sort of errors and biases are present in them. They are computationally expensive to process, and often the cost of learning is hard to predict - for instance, and algorithm that runs quickly in a dataset that fits in memory may be exorbitantly expensive when the dataset is too large for memory. Large datasets may also display qualitatively different behavior in terms of which learning methods produce the most accurate predictions.

This course is intended to provide a student practical knowledge of, and experience with, the issues involving large datasets. Among the issues considered are: scalable learning techniques, such as streaming machine learning techniques; parallel infrastructures such as map-reduce; practical techniques for reducing the memory requirements for learning methods, such as feature hashing and Bloom filters; and techniques for analysis of programs in terms of memory, disk usage, and (for parallel methods) communication complexity.

The class will include frequent programming assignments, and a one-month short project chosen by the student. The project should be relevant to the course - e.g., to compare the scalability of variant learning algorithms on datasets.

Syllabus

Prerequisites

An introductory course in machine learning, like 10-601 or 10-701, is a prerequisite or a co-requisite. If you plan to take this course and 10-601 concurrently please tell the instructor.

The course will include several substantial programming assignments, so an additional prerequisite is 15-210, or 15-214, or comparable familiarity with Java and good programming skills.

Undergraduates need permission of the instructor to enroll.

Datasets

Some datasets will be provided by the instructors to use in the course.

  • RCV2 - text classification dataset.
  • Wikipedia links - page-page links for Wikipedia.
  • Geographical names and places - data on places from GeoNames, Wikipedia, and Geo-tagged Flikr images.
  • NELL all-pairs data - NPs and the contexts they appear in on the web.
  • Google n-grams.
  • ?Million Song Database - audio signatures of songs with tags and meta-data.
  • ?KDD search-engine queries.

Projects

Schedule of Presentations

  • We first put all projects into two groups based on their topics, and then assign each group to a presentation day.

May 1 --- NELL, tencent, and Twitter

  • 1 NELL KB classification with SV- -VO features by Guo Chen
  • 2 SVO relation classification with LogReg/SVM by Malcolm Greaves
  • 3 pic co-clustering for verb-noun pairs by Philip Gianfortoni , Mahesh Joshi
  • 4 clickthru rate prediction by Lingjuan Peng, Yijia Zhang
  • 5 tencent weibo link prediction by Rui Du, Tianle Huang
  • 6 tencent weibo social recommendation by Yifu Diao
  • 7 TwitLDA by Supreeth Selvaraj
  • 8 run pagerank on twitter hashtags - GraphLab and MR by Yogesh Dalal, Dongzhen Piao
  • 9 twitter Spam by Elmer Garduno Hernandez

May 3 --- other stuff

  • 1 SVO relation classification by Mridul Gupta, Anuroop Sriram, Mahaveer
  • 2 WSD trained on WP sense-page links by Andrew Rodriguez
  • 3 GPS smoothing for bus data by Eliot Knudsen
  • 4 memory-caching HDFS by Philip Brown
  • 5 stacked LSH-based predictors by Benjamin Eckart
  • 6 Netflix - ensemble of matrix factorization and kNN by Peng Zhang
  • 7 hybrid parallel SGD coordinate descent by Chong Tat Chua, Dongyeop Kang
  • 8 RCV1 heirarchical classification by Tarun Sharma
  • 9 brains and nouns by Seshadri Sridharan
Retrieved from "http://curtis.ml.cmu.edu/w/courses/index.php?title=Machine_Learning_with_Large_Datasets_10-605_in_Spring_2012&oldid=11192"