Mark Goadrich Computer Science and Mathematics

Slides:



Advertisements
Similar presentations
Approaches, Tools, and Applications Islam A. El-Shaarawy Shoubra Faculty of Eng.
Advertisements

Autonomic Scaling of Cloud Computing Resources
Machine Learning: Intro and Supervised Classification
The multi-layered organization of information in living systems
An Introduction to Artificial Intelligence Presented by : M. Eftekhari.
Flocking Behaviors Presented by Jyh-Ming Lien. Flocking System What is flocking system? – A system that simulates behaviors of accumulative objects (e.g.
Evolving Cutting Horse and Sheepdog Behavior with a Simulated Flock Chris Beacham Computer Systems Research Lab 2009.
COMPUTER SIMULATION MODELS AND MULTILEVEL CANCER CONTROL INTERVENTIONS Joseph Morrissey, Kristen Hassmiller Lich, Rebecca Anhang Price, Jeanne Mandelblatt.
Ant Colony Optimization. Brief introduction to ACO Ant colony optimization = ACO. Ants are capable of remarkably efficient discovery of short paths during.
1 PharmID: A New Algorithm for Pharmacophore Identification Stan Young Jun Feng and Ashish Sanil NISSMPDM 3 June 2005.
Graph-Based Data Mining Diane J. Cook University of Texas at Arlington
Evolutionary Algorithms Simon M. Lucas. The basic idea Initialise a random population of individuals repeat { evaluate select vary (e.g. mutate or crossover)
Natural Computation: computational models inspired by nature Dr. Daniel Tauritz Department of Computer Science University of Missouri-Rolla CS347 Lecture.
Data Mining Presentation Learning Patterns in the Dynamics of Biological Networks Chang hun You, Lawrence B. Holder, Diane J. Cook.
Introduction to molecular networks Sushmita Roy BMI/CS 576 Nov 6 th, 2014.
Nawaf M Albadia Introduction. Components. Behavior & Characteristics. Classes & Rules. Grid Dimensions. Evolving Cellular Automata using Genetic.
Artificial Life Lawrence Goetz Brooklyn College. What is life?
L/O/G/O Ant Colony Optimization M1 : Cecile Chu.
Cookies, Spreadsheets, and Modeling: Dynamic, Interactive, Visual Science and Math Scott A. Sinex Prince George’s Community College Presented at Network.
SWARM INTELLIGENCE IN DATA MINING Written by Crina Grosan, Ajith Abraham & Monica Chis Presented by Megan Rose Bryant.
Bioinformatics and it’s methods Prepared by: Petro Rogutskyi
Artificial Intelligence Dr. Paul Wagner Department of Computer Science University of Wisconsin – Eau Claire.
Invitation to Computer Science 5th Edition
Chapter 14: Artificial Intelligence Invitation to Computer Science, C++ Version, Third Edition.
AI Overview Reference: "Artificial Intelligence, a Modern Approach, 3 rd ed."
Free Powerpoint Templates Page 1 Free Powerpoint Templates Influence and Correlation in Social Networks Azad University KurdistanSocial Network.
Exploring the dynamics of social networks Aleksandar Tomašević University of Novi Sad, Faculty of Philosophy, Department of Sociology
Biology: flocking, herding & schooling Day 5 COLQ 201 Multiagent modeling Harry Howard Tulane University.
Introduction to ILP ILP = Inductive Logic Programming = machine learning  logic programming = learning with logic Introduced by Muggleton in 1992.
Swarm Computing Applications in Software Engineering By Chaitanya.
Gene Regulatory Network Inference. Progress in Disease Treatment  Personalized medicine is becoming more prevalent for several kinds of cancer treatment.
Study on Genetic Network Programming (GNP) with Learning and Evolution Hirasawa laboratory, Artificial Intelligence section Information architecture field.
B-KUL-H02B1A Natural Language Processing Taught by: Marie-Francine Moens Vincent Vandeghinste Lectures and exercises 2nd semester 4 study points.
Predator/Prey Simulation for Investigating Emergent Behavior Jay Shaffstall.
Microarrays.
Controlling the Behavior of Swarm Systems Zachary Kurtz CMSC 601, 5/4/
Extracting the Common Structure of Compounds to Induce Plant Immunity Activation using ILP 20/08/2015 Department of Industrial Administration, Faculty.
Learning, page 1 CSI 4106, Winter 2005 Symbolic learning Points Definitions Representation in logic What is an arch? Version spaces Candidate elimination.
Interactive Learning of the Acoustic Properties of Objects by a Robot
Neural Networks and Machine Learning Applications CSC 563 Prof. Mohamed Batouche Computer Science Department CCIS – King Saud University Riyadh, Saudi.
Kansas State University Department of Computing and Information Sciences CIS 730: Introduction to Artificial Intelligence Lecture 9 of 42 Wednesday, 14.
By: Amira Djebbari and John Quackenbush BMC Systems Biology 2008, 2: 57 Presented by: Garron Wright April 20, 2009 CSCE 582.
Tetris Agent Optimization Using Harmony Search Algorithm
Introduction to biological molecular networks
Incorporating Artificial Intelligence into Mammography Prediction Louis Oliphant Computer Sciences Department University of Wisconsin-Madison.
Learning Comprehensible Relational Features to Distinguish Subfossil Decapod Crustacean Dactyls Mark Goadrich and Jeffrey Agnew Departments of Computer.
Feature Selction for SVMs J. Weston et al., NIPS 2000 오장민 (2000/01/04) Second reference : Mark A. Holl, Correlation-based Feature Selection for Machine.
 A family of optimization methods that search for an optimum minimum or maximum for a given problem (but never finds it ).  The methods are best suited.
Representation and Search The function of a representation is to capture the critical features of the problem domain –and make the information accessible.
AI Overview Reference: "Artificial Intelligence, a Modern Approach, 3 rd ed."
Agent-Based Modeling ANB 218a Jeff Schank.
Journal club Jun , Zhen.
Machine Learning overview Chapter 18, 21
The Matching Hypothesis
Your Poster’s Title Goes Here names go here institution names go here
Plant-Moose-Predator System Simulation
Your Poster’s Title Goes Here names go here institution names go here
Your Poster’s Title Goes Here Name of Presenter Name of institution
What shape am I? I am a plane shape. I have 4 sides.
Your Poster’s Title Goes Here names go here institution names go here
Computing Functions with Turing Machines
Overview of Machine Learning
Your Poster’s Title Goes Here names go here institution names go here
Your Poster’s Title Goes Here names go here institution names go here
Your Poster’s Title Goes Here names go here institution names go here
Your Poster’s Title Goes Here names go here institution names go here
Unsupervised Machine Learning in Agent-Based Modeling
Type Topic in here! Created by Educational Technology Network
Your Poster’s Title Goes Here names go here institution names go here
Your Poster’s Title Goes Here Name of Presenter Name of institution
Presentation transcript:

Using Relational Structure for Learning and Modeling in Biomedical and Social Domains Mark Goadrich Computer Science and Mathematics Centenary College of Louisiana Natural Science Colloquium November 6th, 2007

Overview First-Order Logic and Machine Learning The world is full of Objects Model these Objects to understand the world Inductive Logic Programming Objects and Relations/Properties Agent-Based Modeling Objects and Interactions/Behaviors ILP takes snapshots of the world ABM simulates a dynamic world

Bongard Problems 6 positive examples of a concept on left Bongard problems. From Mikhail Bongard, Soviet Computer Scientist. 1967 6 positive examples of a concept on left 6 negative examples on right How to learn this concept using a computer?

First-Order Logic using PROLOG Objects e3, t1, t2, c1 Types example(e3) triangle(t1) triangle(t2) circle(c1) Relations has_shape(e3, t1) has_shape(e3, t2) has_shape(e3, c1) inside(t2, c1) left(t2, t1) size(c1, 2.5) above(t2, t1) … We make lots of facts for each example. This is what is true about the world. Positive Example 3 Repeat this process for each example in dataset

Inductive Logic Programming (ILP) Search the space of possible rules “positive(E) :- …” Judge rule quality by positive - negative coverage positive(E):- has_shape(E, A) positive(E) positive(E):- has_shape(E, A), triangle(A) Animate sample rule at level 1 and 2 positive(E) :- has_shape(E, A), has_shape(E, B), triangle(A), circle(B), inside(A, B).

Research Issues in ILP Enormous space to search for rules Enormous number of examples Incorporation of continuous features Learning of probabilistic rules Evaluation of rule quality Survey of ILP domains and future interests

Mutagenesis Designing effective and selective drugs Represent chemicals as atoms and bonds between them atm(127, 127_1, c, 22, 0.191 ) bond(127, 127_1, 127_6, 7 ) Learned mutagenic rule: mutagenic(A) :- atm(A, B, c, 27, C), bond(A, D, E, 1), bond(A, B, E, 7). Bond(compound, atom1, atom2, bondtype) Atm(compound, atom, element, atomtype, charge) (A) 3,4,4'-tri-nitro-biphenyl (B) 2-nitro-1,3,7,8-tetrachlorodibenzo-1,4-dioxin (C) 1,6,-dinitro-9,10,11,12-tetrahydrobenzo[e]pyrene (D) nitrofurantoin

Breast Cancer Detection Large dataset of abnormalities found in mammograms Not enough radiologists Relational features More than one abnormality per mammogram More than one mammogram per person over time malignant(A) :- not asymmetric(A), in_same_mammorgram(A, A2), spiculated_margin(A2), not distorted(A2)

Robot Scientist Represent Metabolic Pathways as a Regulatory Network Graph Knock out genes, and then systematically deduce the unknown function Try to learn the network from time-series microarray data

Social Networks People are connected by friendships into networks Each person has likes/dislikes, possibly influenced by their network Can we learn your interests based on who you know and what they like? Targeted advertisements?

Netflix Prize What movies should Netflix recommend you watch next? Large relational dataset Movies Titles Ratings Friends Friend’s ratings Genre $1 million if you achieve 10% improvement over their algorithm Cinematch

Zendo Board game about inductive logic Master creates a rule which some 3-D pyramid structures fit and others do not Players build structures and try to guess the Master rule Easier to design computer Master to decide if a structure fits the rule Harder to design computer Player that must efficiently guess the rule

Crab Claws What physical characteristics distinguish between two species? Within the same species, what changes due to growth, diet and their relation to predation? Find the “shock graph” of each image Use ILP to learn differences based on these graphs

Agent-Based Modeling Objects have interactions with each other Flocks of Birds, Schools of Fish Separation Alignment Cohesion Objects interact with their environment Ant Foraging, Pheromones, Traffic Laws Agent-Based Modeling (ABM) Create discrete-time computational simulation Align models with known behavior Vary parameters to test new hypotheses

Social Science Cellular Process

Conclusions First-Order Logic combines with ILP and ABM to create a powerful representation of the world Research Opportunities Social Networks Zendo Player Claws and Shock Graphs Cellular Simulation Social Simulation [Insert your favorite dataset here]