Fabio Massimo Zanzotto and Danilo Croce University of Rome “Tor Vergata” Roma, Italy Reading what Machines ‘Think’

Slides:



Advertisements
Similar presentations
Pseudo-Relevance Feedback For Multimedia Retrieval By Rong Yan, Alexander G. and Rong Jin Mwangi S. Kariuki
Advertisements

Random Forest Predrag Radenković 3237/10
Change Detection C. Stauffer and W.E.L. Grimson, “Learning patterns of activity using real time tracking,” IEEE Trans. On PAMI, 22(8): , Aug 2000.
CPSC 502, Lecture 15Slide 1 Introduction to Artificial Intelligence (AI) Computer Science cpsc502, Lecture 15 Nov, 1, 2011 Slide credit: C. Conati, S.
Intelligent Environments1 Computer Science and Engineering University of Texas at Arlington.
Multiple People Detection and Tracking with Occlusion Presenter: Feifei Huo Supervisor: Dr. Emile A. Hendriks Dr. A. H. J. Stijn Oomes Information and.
Image Indexing and Retrieval using Moment Invariants Imran Ahmad School of Computer Science University of Windsor – Canada.
Fabio Massimo Zanzotto and Lorenzo Dell’Arciprete University of Rome “Tor Vergata” Roma, Italy Efficient kernels for sentence pair classification.
Decision Tree Rong Jin. Determine Milage Per Gallon.
CS292 Computational Vision and Language Pattern Recognition and Classification.
Introduction to Cognitive Science Lecture #1 : INTRODUCTION Joe Lau Philosophy HKU.
Detecting Image Region Duplication Using SIFT Features March 16, ICASSP 2010 Dallas, TX Xunyu Pan and Siwei Lyu Computer Science Department University.
A Self-Organizing Approach to Background Subtraction for Visual Surveillance Applications Lucia Maddalena and Alfredo Petrosino, Senior Member, IEEE.
CSSE463: Image Recognition Day 31 Due tomorrow night – Project plan Due tomorrow night – Project plan Evidence that you’ve tried something and what specifically.
CS292 Computational Vision and Language Visual Features - Colour and Texture.
Smart Traveller with Visual Translator. What is Smart Traveller? Mobile Device which is convenience for a traveller to carry Mobile Device which is convenience.
Pattern Recognition. Introduction. Definitions.. Recognition process. Recognition process relates input signal to the stored concepts about the object.
Face Processing System Presented by: Harvest Jang Group meeting Fall 2002.
Introduction to machine learning
Cognitive level of Analysis
Walter Hop Web-shop Order Prediction Using Machine Learning Master’s Thesis Computational Economics.
Identifying Computer Graphics Using HSV Model And Statistical Moments Of Characteristic Functions Xiao Cai, Yuewen Wang.
Machine Learning CUNY Graduate Center Lecture 1: Introduction.
Fabio Massimo Zanzotto
Machine Learning1 Machine Learning: Summary Greg Grudic CSCI-4830.
Chapter 1 What is Programming? Lecture Slides to Accompany An Introduction to Computer Science Using Java (2nd Edition) by S.N. Kamin, D. Mickunas, E.
2 2  Background  Vision in Human Brain  Efficient Coding Theory  Motivation  Natural Pictures  Methodology  Statistical Characteristics  Models.
November 13, 2014Computer Vision Lecture 17: Object Recognition I 1 Today we will move on to… Object Recognition.
1 Pattern Recognition Pattern recognition is: 1. A research area in which patterns in data are found, recognized, discovered, …whatever. 2. A catchall.
Visual Information Systems Recognition and Classification.
Learning from observations
CISC Machine Learning for Solving Systems Problems Presented by: Ashwani Rao Dept of Computer & Information Sciences University of Delaware Learning.
Pleasing in appearance.
Powerpoint Templates Page 1 Powerpoint Templates Scalable Text Classification with Sparse Generative Modeling Antti PuurulaWaikato University.
Gang WangDerek HoiemDavid Forsyth. INTRODUCTION APROACH (implement detail) EXPERIMENTS CONCLUSION.
CISC Machine Learning for Solving Systems Problems Presented by: Satyajeet Dept of Computer & Information Sciences University of Delaware Automatic.
A NOVEL METHOD FOR COLOR FACE RECOGNITION USING KNN CLASSIFIER
Subject Name: Computer Graphics Subject Code: Textbook: “Computer Graphics”, C Version By Hearn and Baker Credits: 6 1.
GENDER AND AGE RECOGNITION FOR VIDEO ANALYTICS SOLUTION PRESENTED BY: SUBHASH REDDY JOLAPURAM.
Support Vector Machines and Kernel Methods for Co-Reference Resolution 2007 Summer Workshop on Human Language Technology Center for Language and Speech.
Graph Data Management Lab, School of Computer Science Branch Code: A Labeling Scheme for Efficient Query Answering on Tree
Change Blindness Images Li-Qian Ma 1, Kun Xu 1, Tien-Tsin Wong 2, Bi-Ye Jiang 1, Shi-Min Hu 1 1 Tsinghua University 2 The Chinese University of Hong Kong.
Goggle Gist on the Google Phone A Content-based image retrieval system for the Google phone Manu Viswanathan Chin-Kai Chang Ji Hyun Moon.
Onlinedeeneislam.blogspot.com1 Design and Analysis of Algorithms Slide # 1 Download From
Foundations What is Cognitive Psychology? How do we study cognition? What is an explanation? –Levels of explanation.
Machine Learning Lecture 1: Intro + Decision Trees Moshe Koppel Slides adapted from Tom Mitchell and from Dan Roth.
Pattern Recognition NTUEE 高奕豪 2005/4/14. Outline Introduction Definition, Examples, Related Fields, System, and Design Approaches Bayesian, Hidden Markov.
Pattern Recognition. What is Pattern Recognition? Pattern recognition is a sub-topic of machine learning. PR is the science that concerns the description.
SUPERVISED AND UNSUPERVISED LEARNING Presentation by Ege Saygıner CENG 784.
1 Kernel Machines A relatively new learning methodology (1992) derived from statistical learning theory. Became famous when it gave accuracy comparable.
Accelerating K-Means Clustering with Parallel Implementations and GPU Computing Janki Bhimani Miriam Leeser Ningfang Mi
Feature learning for multivariate time series classification Mustafa Gokce Baydogan * George Runger * Eugene Tuv † * Arizona State University † Intel Corporation.
Brief Intro to Machine Learning CS539
Combining Models Foundations of Algorithms and Machine Learning (CS60020), IIT KGP, 2017: Indrajit Bhattacharya.
Learning to Detect and Classify Malicious Executables in the Wild by J
Machine Learning with Spark MLlib
Comparison with other Models Exploring Predictive Architectures
Supervised Time Series Pattern Discovery through Local Importance
Implementing Boosting and Convolutional Neural Networks For Particle Identification (PID) Khalid Teli .
Basic machine learning background with Python scikit-learn
Machine Learning Basics
The Assistive System Progress Report 2 Shifali Kumar Bishwo Gurung
Object Recognition Today we will move on to… April 12, 2018
Estimation of Skin Color Range Using Achromatic Features
Midterm Exam Closed book, notes, computer Similar to test 1 in format:
Speech recognition, machine learning
Midterm Exam Closed book, notes, computer Similar to test 1 in format:
Attention for translation
Speech recognition, machine learning
Random Neural Network Texture Model
Presentation transcript:

Fabio Massimo Zanzotto and Danilo Croce University of Rome “Tor Vergata” Roma, Italy Reading what Machines ‘Think’

F.M.Zanzotto University of Rome “Tor Vergata” Prelude Brain Activation Pattern Recognizer chair Tom Mitchell, Invited Talk at the Association for Computational Linguistics Conference 2007 Mitchell, T.M., Shinkareva, S.V., Carlson, A., Chang, K.M., Malave, V.L., Mason, R.A., Just, M.A.: Predicting human brain activity associated with the meanings of nouns. Science 320(5880) (May 2008) 1191–1195 Question This is a fascinating research problem. Can we find a more controlled setting where we can test if this is possible? Question This is a fascinating research problem. Can we find a more controlled setting where we can test if this is possible?

F.M.Zanzotto University of Rome “Tor Vergata” Idea Cognitive physical object Cognitive task Observed image Observing a chair Sorting a vector Brain Computational Machine

F.M.Zanzotto University of Rome “Tor Vergata” Why investigating the computer side is relevant? Foundational perspective –Computers are becoming extremely complex. They are fastly approaching the complexity of human brain –Computers are controlled machines: their behavior and thier internal organization is known –Then, computers offer a way to estimate if the claim on the brain side is reachable: if we can read what machines think, we can hope to read what brains think. Motivation

F.M.Zanzotto University of Rome “Tor Vergata” Why investigating the computer side is relevant? Applicative perspective Can we develop technologies that “read the computer mind”? This predictive model can have a wide variety of applications, e.g., detecting malicious software, detecting the intentions of hostile computers by looking at their activation patterns. Motivation

F.M.Zanzotto University of Rome “Tor Vergata” Investigating the computer side: Long term research program Sketching the overall observation activity Virtual Observation of Processes Experimental Investigation In the rest of the talk

F.M.Zanzotto University of Rome “Tor Vergata” Long-term research program … Physical Memory Chip Physical Memory Dump Virtual Memory Dump (organized in processes) Process Memory Dump Physical device activation image capturer Virtual activation image capturer

F.M.Zanzotto University of Rome “Tor Vergata” Sorting a vector Sketching the overall observation activity Brain Activation Pattern Recognizer chair Sorting a vector Process Activation Pattern Recognizer Building images from processes Defining feature spaces for images Observed Phenomena: Processes

F.M.Zanzotto University of Rome “Tor Vergata” Observed Phenomena: Processes

F.M.Zanzotto University of Rome “Tor Vergata” Given a cognitive activity, the procedure for extracting images from this activity is then the following: –running the process p representing the cognitive activity c –stopping the process at given states or at given time intervals –dumping the memory associated with the process M(p) –given a fixed height image and the memory dump, read incrementally bytes of the memory dump and fill the associated RGB pixel with the read values I(M(p)) Building activation images from processes

F.M.Zanzotto University of Rome “Tor Vergata” Process memory in a given time interval Activation image of the process in a given time interval where is the RGB pixel definition of the image Building activation images from processes

F.M.Zanzotto University of Rome “Tor Vergata” Process: Vector Sorter Initial State Process: Vector Sorter Final State Building activation images from processes Smoothing (more similar to real chip observation)

F.M.Zanzotto University of Rome “Tor Vergata” We used three major classes of features Chromatic feaures –Capture the color properties of the image determining, an n-dimensional vector representation of the 2D chromaticity histograms texture (OP - OGD) features –emphasize the background properties and their composition. transformation features (OGD) Defining feature spaces for images

F.M.Zanzotto University of Rome “Tor Vergata” Experimental Set-up –Collection of activation images –Used Machine Learning algorithms Experimental Results Experimental Evaluation

F.M.Zanzotto University of Rome “Tor Vergata” 3 different “cognitive tasks” (algorithms) –sorting, comparing two strings, visiting a binary tree 3 different programming languages –c, java, php for each pair algorithm-programming language –20 different randomly generated input data –3 snapshots (beginning, middle, end) Experimental Set-up

F.M.Zanzotto University of Rome “Tor Vergata” We randomly splited the final set (540 images) in: Training: 270 images Testing: 270 images Two classification tasks: Determining the programming language (3 classes) (lang) Determining the cognitive task (3 classes) (algo) Used Machine learning Models: Decision Tree Learners (DecTree) Naive Bayes Experimental Set-up

F.M.Zanzotto University of Rome “Tor Vergata” Results Classification accuracy

F.M.Zanzotto University of Rome “Tor Vergata” The parallelism between computer and brain/mind is not new in general –Cognitive psychology –Cognitive sciences We looked this parallelism from an other perspective Conclusion

F.M.Zanzotto University of Rome “Tor Vergata” Future Work … Physical Memory Chip Physical Memory Dump Virtual Memory Dump (organized in processes) Process Memory Dump Physical device activation image capturer Virtual activation image capturer

F.M.Zanzotto University of Rome “Tor Vergata” Thank you for the attention!