Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

This page is outdated. For more recent MLDG, please go to http://wiki.cs.cornell.edu/index.php?title=Machine_Learning_Discussion_Group

 

 

  • Machine Learning Reading Group
  • Admins: Nikos, Ainur, Ruben

What is the MLDG?

It is an informal group for discussing the latest work in the field of Machine Learning. We usually discuss a paper from a recent conference(NIPS,ICML..) each meeting.

When and where do we meet?

This Fall Spring we will meet every Wednesday@4:30pm in 5126 Upson.

Who attends the MLDG?

The group is mainly attended by graduate students. The senior organizers are Nikos, Ainur and Ruben Sipos. Suggestions for topics or papers to discuss are always welcome.

Mailing List

Sign up to receive updates at our mailing list here.

Latest News

  • Anshumali, Hema and Abhishek all had papers accepted at NIPS.

Friday@4:00pm in 344 Gates Hall (Breakout room).

Papers Read

- Fall 2013

Date

Presenter

Topic(s)

Resources/Papers

Other activities/ comments

9/6/2013

Ruben

General ML

A Few Useful Things to Know about Machine Learning

 

9/20/2013

Karthik

Active Learning, Crowdsourcing

Tutorial style discussion.
Focus on Pairwise Ranking Aggregation in a Crowdsourced Setting

Paul Bennett (AI Seminar)

9/27/2013

Ashwin

Method of moments

A bit of background from
1) http://en.wikipedia.org/wiki/Method_of_moments_(statistics)
2) Chapter 7 of the following book.
Followed by freeform discussion on 
http://newport.eecs.uci.edu/anandkumar/pubs/AnandkumarEtal_mixtures12.pdf

 

10/4/2013

Adith

Distributed Representations

Freeform discussion. 
The Parallel Distributed Processing Approach to Semantic Cognition

 

10/18/2013

Hema

Vision

-

 

10/25/2013

Chenhao

Practice Talk

-

 

11/1/2013

Ashesh

Human-In-Loop Learning

Fine-Grained Crowd sourcing for Fine-Grained Recognition

 

11/15/2013

Stefano

 

 

 

11/22/2013

Yin

 

 

 

- Summer 2013

Date

Topic

Paper

Discussion Leader

7/18

Inverse Reinforcement Learning

Tutorial

Ashesh

7/11

Bayesian Nonparametrics

Dirichlet processes, its variants and applications

Yun

6/27

Deep Learning

Deep Learning (Examples, Thoughts and Ideas)

Moontae

6/13

Bioinformatics

Tutorial on Machine Learning problems in Bioinformatics and Genetics

Brad

6/6

Structured Learning

A Structural SVM Based Approach for Optimizing Partial AUC

Ruben

5/23

Deep Learning

Tutorial on Deep Learning

Ian

- Spring 2013

- Fall 2012

- Spring 2012

Date

Topic

Paper

Discussion Leader

4/6

Machine Learning and Game Theory

Machine Learning Markets

Karthik

...

- Fall 2011

Date

Topic

Paper

Discussion Leader

11/2

Deep Learning

Parsing Natural Scenes and Natural Language with Recursive Neural Networks

Abhishek & Ainur

 

10/19

Graphical Models

Spectral Algorithm for Latent Tree Graphical Models

Karthik

10/5

 

Trading Representability for Scalability: Adaptive Multi-Hyperplane Machine for Nonlinear Classification

Nikos

9/28

Submodularity

Submodularity tutorial

Ashwin

9/21

Graphical Models

Minimum Probability Flow Learning

Nikos

9/14

Submodularity

Submodular meets Spectral

Karthik

9/7

Deep-Learning, Graphical Models

Sum-Product Networks: A New Deep Architecture

TBD Karthik

- Spring 2011

Date

Topic

Paper

Discussion Leader

4/29, 5/6, 5/13

Variational Methods

Tutorial on Variational Approximation Methods

Nikos

4/22

Deep Learning

Deep Boltzman Machines

Ainur

4/15

Deep Learning

Multimodal Deep Learning

Akram

4/8

Deep Learning

Fast Learning Alg. for Deep Belief Nets

Akram

4/1

Semi-Supervised Learning

Optimal Reverse Prediction

Nikos

3/11

Game Theory and Learning

Game-Theoretic Approach to Apprenticeship Learning

Ruben

3/4

Game Theory and Learning

Game Theory, On-line Prediction and Boosting

Karthik

2/25

Multi-Task Learning

Tree-Guided Group Lasso for Multi-Task Regression with Structured Sparsity

Bishan

...

Date

Topic

Paper

Discussion Leader

11/12

Vision

A Neuromorphic Approach to Computer Vision

Jason

11/5

Metric Learning

Metric Learning to Rank

Karthik

10/29

Clustering

Mining Clustering Dimensions

Ruben

Who attends the MLDG?

The group is mainly attended by graduate students. The senior organizers are Ruben and Karthik. Suggestions for topics or papers to discuss are always welcome.

Mailing List

Sign up to receive updates at our mailing list here.

Latest News