Graduate Seminar In Machine Learning

Slides:



Advertisements
Similar presentations
The Seminar Seminar Every Talk is a Job Talk. Two Types of Seminar Conference Presentation Short time (15-20 min) Narrow Audience (usually) No Audience.
Advertisements

Welcome to the seminar course
CSEE W4140 Networking Laboratory Opening Lecture Jong Yul Kim
MAT 3749 Introduction to Analysis Fall 2013
CSE 5522: Survey of Artificial Intelligence II: Advanced Techniques Instructor: Alan Ritter TA: Fan Yang.
Science Student Success Centre Find the resources you need on campus Improve the way you prepare for your semester. Find summer research opportunities.
CAS CS 330 Algorithms Administrativia 6/15/2015Gene Itkis, CS330 Algorithms3 General info Instructor: Gene Itkis
Machine Learning (Extended) Dr. Ata Kaban
introduction to MSc projects
Independent Work Fall 2007 David Walker. Welcome Junior ABs (both semesters) Junior ABs (both semesters) Senior ABs (thesis) Senior ABs (thesis) BSEs.
 Getting started  Syllabus  Objectives and Evaluation  Teams and Mentors  Topics Covered  Learning Outcomes  Exams Regulations  Presentations.
Medical Law and Bioethics
Cpt S 471/571: Computational Genomics Spring 2015, 3 cr. Where: Sloan 9 When: M WF 11:10-12:00 Instructor weekly office hour for Spring 2015: Tuesdays.
COMP Introduction to Programming Yi Hong May 13, 2015.
CS598CXZ (CS510) Advanced Topics in Information Retrieval (Fall 2014) Instructor: ChengXiang (“Cheng”) Zhai 1 Teaching Assistants: Xueqing Liu, Yinan Zhang.
Lecture 1 Page 1 CS 239, Fall 2010 Introduction CS 239 Advanced Topics in Computer Security Peter Reiher September 23, 2010.
CSCD 434 Network Security Spring 2014 Lecture 1 Course Overview.
1 HEINZ NIXDORF INSTITUT University of Paderborn Algorithms und Complexity Seminar Designing Peer-to-Peer- Networks Christian Schindelhauer
CSCI 51 Introduction to Computer Science Dr. Joshua Stough January 20, 2009.
Overviews of ITCS 6161/8161: Advanced Topics on Database Systems Dr. Jianping Fan Department of Computer Science UNC-Charlotte
CS 6961: Structured Prediction Fall 2014 Course Information.
1 Machine Learning (Extended) Dr. Ata Kaban Algorithms to enable computers to learn –Learning = ability to improve performance automatically through experience.
2014 ML Project2: Goal: Do some real machine learning; learn you to use machine learning to make sense out of data. Group Project—4 (3) students per group.
 Making the transition from high school to college requires extra effort:  You must start studying and preparing from the first day of class.  Attend.
1 CS1100 Fall Instructor: David Gries CS100M: Matlab No prior programming experience One semester of calculus Math & engineering type problems CS100J:
Research Experience Program (REP) Spring 2008 Psychology 100 Ψ.
CMPT 308 — Computability and Complexity Fall 2004 Instructor: Andrei Bulatov, TA: Ramsay Dyer, Learning.
EE5393: Course Information Instructor Prof. Marc Riedel office: EE/CSi tel: Credits: 3 Meeting time:
Advances in Cloud Computing CIS6930/CIS4930
1 CS100J Spring Instructor: David Gries CS100M: Matlab No prior programming experience One semester of calculus Math & engineering type problems.
ECE 6504: Deep Learning for Perception Dhruv Batra Virginia Tech Topics: –Deconvolution.
Wilmer Arellano  Getting started  Syllabus  Objectives and Evaluation  Teams and Mentors  Topics Covered  Learning Outcomes  Exams Regulations.
Structural Bioinformatics Seminar Prof. Haim J. Wolfson1 How to present a lecture in Bioinformatics (an informal guide) Haim J. Wolfson School of Computer.
By: Wilmer Arellano.  1. Form a team  2. Find a Team Leader  3. Find Three Potential Topics  4. Find a Mentor  5. Select a Topic.
Welcome to MT140 Introduction to Management Unit 1 Seminar – Introduction to Management.
Medical Law and Bioethics Unit 1. WELCOME Kaplan School Week  Kaplan’s school week runs from Wednesday to Tuesday  You will begin a new unit on Wednesday.
Beyond the Basics: How Can Librarians Teach What We Truly Care About? Beyond the Basics: How Can Librarians Teach What We Truly Care About? Information.
Introduction to CSCI 1311 Dr. Mark C. Lewis
CS6501 Advanced Topics in Information Retrieval Course Policy
Lab Introduction Installing Python
Objectives of the Course and Preliminaries
How to write an empirical research project in (labor) economics
CS598CXZ (CS510) Advanced Topics in Information Retrieval (Fall 2016)
CS410: Text Information Systems (Spring 2018)
AP computer science PRINCIPLES
Good talks – some hints Henning Schulzrinne
Field Experience in Family Social Sciences
CAS CS112 Intro to CS II w/ C++
Cpt S 471/571: Computational Genomics
Intro to Theory of Computation
Course Overview Juan Carlos Niebles and Ranjay Krishna
CS7280: Special Topics in Data Mining Information/Social Networks
Continued Professional Development
CSCD 434 Network Security Spring 2012 Lecture 1 Course Overview.
An Efficient method to recommend research papers and highly influential authors. VIRAJITHA KARNATAPU.
CAS CS 538 Cryptography.
Cpt S 471/571: Computational Genomics
Introduction to Comparative Effectiveness Course (HAP 823)
COMP61011 : Machine Learning Decision Trees
CS4501: Information Retrieval Course Policy
Lecture on High Performance Processor Architecture (CS05162)
Field Experience in Family Social Sciences
Technologies of Google Seminar Week 1
Title of your project Team members
Welcome to the First-Year Experience!
Title of your project Team members
Term Project Description
Welcome to the First-Year Experience!
Course overview Lecture : Juan Carlos Niebles and Ranjay Krishna
COMP108 Algorithmic Foundations Mathematical Induction
Presentation transcript:

Graduate Seminar In Machine Learning COMP 640, Fall 2017 Instructor: Anshumali Shrivastava anshumali@rice.edu

Information Location: DCH 1046 Timings: Mondays 3:00-4:30pm Office Hours: Mondays 4:30pm -5:30pm Website for Information: https://www.cs.rice.edu/~as143/COMP640_Fall17/index.html Discussions: Piazza Prerequisite: A rigorous course in ML (Ex. Comp 440 or equivalent)

What is This Class About? Keeping up with cutting edge research and advancements in Machine Learning (Like AI and Deep Learning). We will be discussing recent potentially sophisticated papers/topics in each class. This course is for future leaders in AI. Giving presentations, leading discussions, and writing summary on very advanced topics.

What we will cover Start with basic SVMs and Kernels. See some Basics of Large Scale SVMs via random features Then transition from Random Features to Learned features (aka deep learning) Look into tricks and trade of deep learning Go to Reinforcement learning and deep reinforcement learning. Understand self-driving cars and alpha go systems.

Requirements for 1 Credits Help presenting a part of topic in 1 class (2-3 students per class) Sign up to write a 2-3 page write-up discussion on 1 class (2-3 students per class). Cannot be same at the topic of presentation Important Need to collaborate and create a presentation. Dry run to instructor one week before the presentation data. (Start working early) Submit the write-up within a week of presentation.

You have to read the suggested reading materials before the class You have to read the suggested reading materials before the class. It is OK not to understand the math and proofs. It is OK to assume Oracles. There will be quiz at the start of the class. You should be able to answer the following in one line What is the aim of the paper? What is the conclusion? What were people doing before and how did this change? How is it different from the simplest way of achieving it given your knowledge.

Suggestions on Reading papers Understand the problem statement and difficulty. Read and understand the problem (the goal). Think how you will solve it. If you have no idea read ahead to see sub-goals. Keep reading until you arrive at a sub-goal, you have some idea of how to solve it. See what the paper has done differently. (What is really the technical difference or maybe there isn’t any) Asses why your own idea is superior/inferior Outcome Your idea is inferior: You learned something Your idea is superior: Write a new paper Cannot really see: Keep pondering.

Presentations Your team is responsible for running the show. No Restrictions. The suggested papers can be ignored if you have better materials to present to audience from internet of elsewhere. But should be related to the topic in the papers. The class should get to know about the topic from scratch. Do not assume any knowledge other than basic ML concepts. (cannot assume any sophisticated theorem) Should be interactive with open discussions and questions. (not too philosophical … must be technical)

Summary Discussions Ideally it should be like a technical blog on the discussion. Only basic knowledge can be assumed. Its ok to use sophisticated ideas with citations. Ex: http://neuro.cs.ut.ee/demystifying-deep-reinforcement-learning/

For 3 credits: A Full Research Project Talk to instructor. Some Examples: Take a well known algorithm and try to make it faster. Propose a novel fast approximate version. Identify bottlenecks and opportunities to parallelize in a novel way. Take an interesting dataset and try to find something interesting using custom ML models. Propose an alternative to well known models in some real environment. Propose a ML (like deep learning) algorithm/model for a novel application with real data. Theoretical analysis of some new properties of known or proposed algorithms. Ideally a good project should be publishable if the goals are met. Project can be totally unrelated to topics covered in class. START EARLY