1 Andrew Ng, Associate Professor of Computer Science Robots and Brains.

Slides:



Advertisements
Similar presentations
COGNITIVE MEMORY HUMAN AND MACHINE
Advertisements

Evaluating which classifiers work best for decoding neural data.
Godfather to the Singularity
Object recognition and scene “understanding”
Rajat Raina Honglak Lee, Roger Grosse Alexis Battle, Chaitanya Ekanadham, Helen Kwong, Benjamin Packer, Narut Sereewattanawoot Andrew Y. Ng Stanford University.
Chapter 10 Artificial Intelligence © 2007 Pearson Addison-Wesley. All rights reserved.
Hybrid Pipeline Structure for Self-Organizing Learning Array Yinyin Liu 1, Ding Mingwei 2, Janusz A. Starzyk 1, 1 School of Electrical Engineering & Computer.
Visual Cognition II Object Perception. Theories of Object Recognition Template matching models Feature matching Models Recognition-by-components Configural.
MACHINE LEARNING AND ARTIFICIAL NEURAL NETWORKS FOR FACE VERIFICATION
Artificial Intelligence
CSC 4510 – Machine Learning Dr. Mary-Angela Papalaskari Department of Computing Sciences Villanova University Course website:
Andrew Ng CS228: Deep Learning & Unsupervised Feature Learning Andrew Ng TexPoint fonts used in EMF. Read the TexPoint manual before you delete this box.:
Traffic Sign Recognition Using Artificial Neural Network Radi Bekker
Information Technology Industry Report Brown University ADSP Lab 余 渊 善
(CMSC5720-1) MSC projects by Prof K.H. Wong (21 July 2015) (shb907) MSC projects supervised by Prof.
Pulsed Neural Networks Neil E. Cotter ECE Department University of Utah.
Artificial Intelligence: Prospects for the 21 st Century Henry Kautz Department of Computer Science University of Rochester.
(CMSC5720-1) MSC projects by Prof K.H. Wong (21 July2014) (shb907) MSC projects supervised by Prof.
 The most intelligent device - “Human Brain”.  The machine that revolutionized the whole world – “computer”.  Inefficiencies of the computer has lead.
End-to-End Text Recognition with Convolutional Neural Networks
ECE 6504: Deep Learning for Perception Dhruv Batra Virginia Tech Topics: –Neural Networks –Backprop –Modular Design.
Lecture 10: 8/6/1435 Machine Learning Lecturer/ Kawther Abas 363CS – Artificial Intelligence.
G52IVG, School of Computer Science, University of Nottingham 1 Administrivia Timetable Lectures, Friday 14:00 – 16:00 Labs, Friday 17:00 -18:00 Assessment.
Hierarchical Temporal Memory as a Means for Image Recognition by Wesley Bruning CHEM/CSE 597D Final Project Presentation December 10, 2008.
Andrew Ng Feature learning for image classification Kai Yu and Andrew Ng.
Copyright © 2008 Pearson Education, Inc. Publishing as Pearson Addison-Wesley Chapter 11: Artificial Intelligence Computer Science: An Overview Tenth Edition.
Representations for object class recognition David Lowe Department of Computer Science University of British Columbia Vancouver, Canada Sept. 21, 2006.
1 Machine Learning 1.Where does machine learning fit in computer science? 2.What is machine learning? 3.Where can machine learning be applied? 4.Should.
Autonomous Virtual Humans Tyler Streeter April 15, 2004.
I Robot.
Week 1 - An Introduction to Machine Learning & Soft Computing
Andrew Ng, Director, Stanford Artificial Intelligence Lab
Introduction Welcome Machine Learning.
PENGENALAN POLA DAN VISI KOMPUTER PENDAHULUAN. Vision Vision is the process of discovering what is present in the world and where it is by looking.
ARTIFICIAL INTELLIGENCE include people, procedures, hardware, software, data and knowledge needed to develop computer systems and machines that demonstrated.
1 Andrew Ng, Associate Professor of Computer Science Robots and Brains.
語音訊號處理之初步實驗 NTU Speech Lab 指導教授: 李琳山 助教: 熊信寬
Machine Learning Artificial Neural Networks MPλ ∀ Stergiou Theodoros 1.
Network Management Lecture 13. MACHINE LEARNING TECHNIQUES 2 Dr. Atiq Ahmed Université de Balouchistan.
Facial Smile Detection Based on Deep Learning Features Authors: Kaihao Zhang, Yongzhen Huang, Hong Wu and Liang Wang Center for Research on Intelligent.
1 Neural Networks MUMT 611 Philippe Zaborowski April 2005.
Fundamental ARTIFICIAL NEURAL NETWORK Session 1st
How being used at your company? What is Data Science?
Deep Learning: What is it good for? R. Burgmann
Classification of models
Artificial Intelligence, P.II
Chapter 11: Artificial Intelligence
ECE 5424: Introduction to Machine Learning
Deep Learning Insights and Open-ended Questions
R-CNN region By Ilia Iofedov 11/11/2018 BGU, DNN course 2016.
Ch 14. Active Vision for Goal-Oriented Humanoid Robot Walking (1/2) Creating Brain-Like Intelligence, Sendhoff et al. (eds), Robots Learning from.
Pearson Lanka (Pvt) Ltd.
Finding Clusters within a Class to Improve Classification Accuracy
Non-linear hypotheses
Walter J. Scheirer, Samuel E. Anthony, Ken Nakayama & David D. Cox
شبکه عصبی تنظیم: بهروز نصرالهی-فریده امدادی استاد محترم: سرکار خانم کریمی دانشگاه آزاد اسلامی واحد شهرری.
Institute of Neural Information Processing (Prof. Heiko Neumann •
Multiple Feature Learning for Action Classification
network of simple neuron-like computing elements
Machine Learning 101 Intro to AI, ML, Deep Learning
John H.L. Hansen & Taufiq Al Babba Hasan
Biologically Based Networks
Biologically Based Networks
Presentation By: Eryk Helenowski PURE Mentor: Vincent Bindschaedler
Lecture 21: Machine Learning Overview AP Computer Science Principles
Pose Estimation in hockey videos using convolutional neural networks
THE ASSISTIVE SYSTEM SHIFALI KUMAR BISHWO GURUNG JAMES CHOU
Lecture 9: Machine Learning Overview AP Computer Science Principles
Machine Learning.
Presentation transcript:

1 Andrew Ng, Associate Professor of Computer Science Robots and Brains

2 Who wants a robot to clean your house? [Photo Credit: iRobot]

3 Stanford STAIR Robot [Credit: Ken Salisbury]

4

5 What’s missing? Control Perception The software

6 Stanford autonomous helicopter

7 Computer GPS Accelerometers Compass

8

9 Computer program to fly helicopter [Courtesy of David Shim]

10 Option 1 BLACK

11 Machine learning Option 2

12 Machine learning

13 Machine learning to fly helicopter

14 What’s missing? The software Control Perception

15 “Robot, please find my coffee mug”

16 “Robot, please find my coffee mug” Mug

17 Why is computer vision hard? But the camera sees this:

18 Computer programs (features) for vision SIFT Spin image HoG Textons Shape context GIST

19 Why is speech recognition hard? What a microphone records: “Robot, please find my coffee mug.”

20 Computer programs (features) for audio ZCR Spectrogram MFCC Rolloff Flux

21 The idea: Most of perception in the brain may be one simple program

22 Auditory cortex learns to see Auditory Cortex The “one program” hypothesis [Roe et al., 1992]

23 Somatosensory cortex learns to see The “one program” hypothesis Somatosensory Cortex [Roe et al., 1992]

24 Neurons in the brain

25 Neural Network x1x1 x2x2 x3x3 Output Layer L 1 Layer L 2 Layer L 4 Layer L 3 x4x4

26 How does the brain process images? Neuron #1 of visual cortex (model) Neuron #2 of visual cortex (model) Primary visual cortex looks for “edges.”

27 Comparing to Biology Learning algorithm Visual cortex [PICTURE]

28 Comparing to Biology Learning algorithm Auditory cortex [PICTURE]

29 Computer vision results (NORB benchmark) Neural Network: accuracy Classical computer vision (SVM): accuracy

30 Missed Mugs True positivesFalse positives

31 Missed Mugs True positivesFalse positives

32 Missed Mugs True positivesFalse positives

33 Missed Mugs True positivesFalse positives

34 Missed Mugs True positivesFalse positives Results using non-embodied vision

35 Missed Mugs True positivesFalse positives

36 Missed Mugs True positivesFalse positives Results using non-embodied vision

37 Missed Mugs True positivesFalse positives Classifications using embodied agent

38 Missed Mugs True positivesFalse positives

39 Missed Mugs True positivesFalse positives Results using non-embodied vision

40 Missed Mugs True positivesFalse positives

41 Missed Mugs True positivesFalse positives

42 Hope of progress in Artificial Intelligence