CP365 Artificial Intelligence
|
|
- Kelley McLaughlin
- 6 years ago
- Views:
Transcription
1 CP365 Artificial Intelligence
2 Tech News! Apple news conference tomorrow?
3 Tech News! Apple news conference tomorrow? Google cancels Project Ara modular phone
4 Weather-Based Stock Market Predictions?
5 Dataset Preparation Clean remove bogus data/fill in missing data Normalize data adjust features to be similar magnitudes
6 Deal with Missing Data Option 1: remove datapoints with any missing feature values
7 Deal with Missing Data Option 1: remove datapoints with any missing feature values Option 2: fill in missing data with <data_missing> tags for categorical data
8 Deal with Missing Data Option 1: remove datapoints with any missing feature values Option 2: fill in missing data with <data_missing> tags for categorical data Option 3: fill in missing data with global means for numeric data
9 Deal with Missing Data Option 1: remove datapoints with any missing feature values Option 2: fill in missing data with <data_missing> tags for categorical data Option 3: fill in missing data with global means for numeric data Option 4: fill in missing data with values from similar data points
10 Remove Outliers Some datapoints may have ridiculous feature values. We can remove outliers from our dataset to increase performance. What is an outlier?
11 Outliers Patient Height (cm) Patient Weight (kg)... Prognosis Good Good Poor Poor
12 Outliers Patient Height (cm) PatientObvious Weight (kgs) outlier... How can we define what makes an outlier? We 82.9could use 3σ... as the threshold. Prognosis Good Good Poor Poor
13 Outliers Patient Height (cm) This column has x = and Patient Weight... Prognosis σ = 23.1 (without the possible (kgs) outlier) The 3σ thresholds would be ( * 23.1, * 23.1) Good or (87, 225.6) Good Poor Poor
14 A Bad Dataset Patient Height (nm) Patient Weight (tons)... Prognosis 1.31 x Good 1.76 x Good 1.23 x Poor 1.61 x Poor
15 A Bad Dataset How will these large differences affect learning? Patient Height (nm) Patient Weight (tons)... Prognosis 1.31 x Good 1.76 x Good 1.23 x Poor 1.61 x Poor
16 Data Normalization Procedure Patient Height (nm) 1.31 x 109 Range of Extreme Values 1.76 x x x x x 109
17 Data Normalization Procedure Patient Height (nm) 1.31 x 109 Range of Extreme Values 1.76 x x x x x 109 Normalized Range Mapping (-1.0)
18 Data Normalization Formula Patient Height (nm) 1.31 x x x x 109 Say we want the normalized value, newpt, for the first height, 1.31 x 109, called pt. oldmax = 1.76 x 109 oldmin = 1.23 x 109 newmax = 1.0 newmin = 0.0
19 Data Normalization Formula Patient Height (nm) 1.31 x x x x 10 9 Say we want the normalized value, newpt, for the first height, 1.31 x 109, called pt. oldmax = 1.76 x 109 oldmin = 1.23 x 109 newmax = 1.0 newmin = 0.0 ( newpt= pt oldmin ( newmax newmin ) +newmin oldmax oldmin newpt=0.15 )
20 How do we know if an ML model is any good?
21 Overfitting
22 Testing Error Training Epoch
23 A Biological Neuron
24 Human Brain
25 How many neurons? Animal Number Neurons (cerebral cortex) Rat 20,000,000 Dog 160,000,000 Cat 300,000,000 Pig 450,000,000 Horse 1,200,000,000 Dolphin 5,800,000,000 African Elephant 11,000,000,000 Human 20,000,000,000
26 How many connections? Human 100,000,000,000,000
27 How many connections? Human Google (2012) 100,000,000,000,000 1,700,000,000 Google/Stanford (2013) 11,200,000,000 Digital Reasoning (2015) 160,000,000,000
28 Artificial Neuron Output connections Threshold Function w1 w2 w3 Input connections and weights
29 Hard Threshold S = Sum up all inputi * weighti if S > THRESHOLD: output = 1 else: output = 0 Threshold Function w1 w2 w3
30 Hard Threshold: Step Function
31 Write down artificial neurons with weights and thresholds that model the following functions: Identity Logical AND Logical OR Logical XOR Constant function
32 Sigmoid Threshold S = Sum up all inputi * weighti Threshold Function output = w1 w2 w3 1 S 1 e
33 Sigmoid Threshold: 'S' Function
34 sigmoid w1 = 0.1 w3 = 0.42 w2 = 0.2
35 sigmoid w1 = 0.1 w3 = 0.42 w2 = 0.2 Features x1 = 0.66 x2 = 0.11 x3 = 0.20
36 Output Calculations s = w1 * x1 + w2 * x2 + w3 * x3 s = 0.1 * * * 0.2 s = = e
37 y1 = 0.52 sigmoid w1 = 0.1 w3 = 0.42 w2 = 0.2 Features x1 = 0.66 x2 = 0.11 x3 = 0.20
38 Perceptron Network Output Layer Input Layer
39 Perceptron: Linear Boundary
40 Linear Boundary?
41 Multilayer Network Output Layer Hidden Layer(s) Input Layer
42 ANN Learning How to get the weights?
43 ANN Learning How to get the weights? error weight1 weight2
44 ANN Learning How do we get the right weights? Perceptron: Gradient descent Multilayer Network: Back propagation
45 Node Activation Function Activation (output) of node j. n a j =g(input j )=g( w ij ai ) i=0
46 Node Activation Function Activation (output) of node j. n a j =g(input j )=g( w ij ai ) i=0 g is the threshold activation function.
47 Node Activation Function Sum of all weights and input values. Activation (output) of node j. n a j =g(input j )=g( w ij ai ) i=0 g is the threshold activation function.
48 Minimize Global Error Function For every output node, j, sum up... error = (t j a j ) 2 j
49 Minimize Global Error Function...the difference in target value vs. generated output value and square it. For every output node, j, sum up... 2 error= (t j a j ) j
50 Perceptron Learning Δ w ij =η(t j a j )ai Update the weight on connection i j
51 Perceptron Learning The learning rate (0.3ish) Δ w ij =η(t j a j )ai Update the weight on connection i j
52 Perceptron Learning The learning rate (0.3ish) Δ w ij =η(t j a j )ai Update the weight on connection i j Difference in target and generated output.
53 Perceptron Learning The learning rate (0.3ish) Input activation Δ w ij =η(t j a j )ai Update the weight on connection i j Difference in target and generated output.
54 Let's learn NAND! Starting weight values: W1 = 0.81, W2 = 0.55, W3 = 0.16 n a j=g (input j )=g ( w ji ai ) i=0 η = 0.3 Δ wij =η(t j a j ) ai Use sigmoid threshold Dataset: NAND Input1 Input2 Label Out W1 In1 W2 In2 W3 1.0
55 ANN Learning - Backpropagation Output Layer Hidden Layer Input Layer Put in input values and feed the activation forward to produce the output.
56 ANN Learning - Backpropagation Output Layer Hidden Layer Input Layer Calculate the error in the output layer and then backpropagate it to update lower weights.
57 ANN Learning - Backpropagation Update the weight on connection i j Δ w ij =ηδ j ai
58 ANN Learning - Backpropagation Update the weight on connection i j Δ w ij =ηδ j ai Think of this as the error measure for node j. Different for output and hidden weights.
59 ANN Learning - Backpropagation Update the weight on connection i j Input activation Δ w ij =ηδ j ai Think of this as the error measure for node j. Different for output and hidden weights.
60 ANN Learning Backpropagation for Output Nodes δ j =a j (1 a j )(t j a j ) Error measure for output node, j.
61 ANN Learning Backpropagation for Output Nodes Derivative of sigmoid function. δ j =a j (1 a j )(t j a j ) Error measure for output node, j.
62 ANN Learning Backpropagation for Output Nodes Derivative of sigmoid function. Difference in target vs. generated output. δ j =a j (1 a j )(t j a j ) Error measure for output node, j.
63 ANN Learning Backpropagation for Hidden Nodes δ j =a j (1 a j ) δk w jk k Error measure for hidden node, j.
64 ANN Learning Backpropagation for Hidden Nodes Derivative of sigmoid function. δ j =a j (1 a j ) δk w jk k Error measure for hidden node, j.
65 ANN Learning Backpropagation for Hidden Nodes Derivative of sigmoid function. Error measure a combination of output errors that this weight contributes to. δ j =a j (1 a j ) δk w jk k Error measure for hidden node, j.
66 ANN Learning Initialize random network weights for epoch in range NUMBER_EPOCHS: Train network on random presentation of instances Update weights with backpropagation Report global error function value
67 Choosing the Learning Rate, η What happened when our learning rate was too high for linear regression? How do we choose an appropriate learning rate for ANNs?
68 Bold Driver After each epoch... sodahead.com if error went down: η = η * 1.05 else: η = η * 0.50
69 Choosing the Network Structure Output Layer How many nodes? What are their connections? Hidden Layer Input Layer
70 Choosing the Network Structure # of output nodes determined by the number of function Output outputs. Layer Hidden Layer Input Layer
71 Choosing the Network Structure # of input nodes Output determined by the Layer number of function inputs. Hidden Layer Input Layer
72 Choosing the Network Too Structure few hidden nodes: unable to get a detailed enough approximation of the target function Output Layer Hidden Layer Input Layer
73 Choosing the Network Structure Output Layer Too many hidden nodes: slower to train and easier to overfit training data Hidden Layer Input Layer
74 ANN Representational Power With one hidden layer: Model all continuous functions With two hidden layers: Model all functions
75 Rules of Thumb Use 1 or 2 hidden layers
76 Rules of Thumb Use 1 or 2 hidden layers Use about (2/3)n hidden nodes for reasonably complex functions
77 Rules of Thumb Use 1 or 2 hidden layers Use about (2/3)n hidden nodes for reasonably complex functions Don't train for too many epochs
78 Splitting up datasets Training data use to train your ML model Validation data use to improve your ML model while training Testing data use to test performance of your ML model
79 K-Fold Cross Validation Full Dataset Dataset split into k chunks
80 K-Fold Cross Validation: Pass 1 Training Dataset Validation Dataset
81 K-Fold Cross Validation: Pass 2 Training Dataset Validation Dataset
82 K-Fold Cross Validation Perform K training/validation passes Each pass counts as a classification accuracy sample Extreme case: K = datasetsize Leave-one-out testing
83 ANN Implementation?
84 Break!
CMPT 882 Week 3 Summary
CMPT 882 Week 3 Summary! Artificial Neural Networks (ANNs) are networks of interconnected simple units that are based on a greatly simplified model of the brain. ANNs are useful learning tools by being
More informationPerceptrons and Backpropagation. Fabio Zachert Cognitive Modelling WiSe 2014/15
Perceptrons and Backpropagation Fabio Zachert Cognitive Modelling WiSe 2014/15 Content History Mathematical View of Perceptrons Network Structures Gradient Descent Backpropagation (Single-Layer-, Multilayer-Networks)
More informationNeural Network Neurons
Neural Networks Neural Network Neurons 1 Receives n inputs (plus a bias term) Multiplies each input by its weight Applies activation function to the sum of results Outputs result Activation Functions Given
More informationLECTURE NOTES Professor Anita Wasilewska NEURAL NETWORKS
LECTURE NOTES Professor Anita Wasilewska NEURAL NETWORKS Neural Networks Classifier Introduction INPUT: classification data, i.e. it contains an classification (class) attribute. WE also say that the class
More informationSupervised Learning in Neural Networks (Part 2)
Supervised Learning in Neural Networks (Part 2) Multilayer neural networks (back-propagation training algorithm) The input signals are propagated in a forward direction on a layer-bylayer basis. Learning
More informationLearning. Learning agents Inductive learning. Neural Networks. Different Learning Scenarios Evaluation
Learning Learning agents Inductive learning Different Learning Scenarios Evaluation Slides based on Slides by Russell/Norvig, Ronald Williams, and Torsten Reil Material from Russell & Norvig, chapters
More informationCS6220: DATA MINING TECHNIQUES
CS6220: DATA MINING TECHNIQUES Image Data: Classification via Neural Networks Instructor: Yizhou Sun yzsun@ccs.neu.edu November 19, 2015 Methods to Learn Classification Clustering Frequent Pattern Mining
More informationNeural Networks. CE-725: Statistical Pattern Recognition Sharif University of Technology Spring Soleymani
Neural Networks CE-725: Statistical Pattern Recognition Sharif University of Technology Spring 2013 Soleymani Outline Biological and artificial neural networks Feed-forward neural networks Single layer
More informationSupervised Learning (contd) Linear Separation. Mausam (based on slides by UW-AI faculty)
Supervised Learning (contd) Linear Separation Mausam (based on slides by UW-AI faculty) Images as Vectors Binary handwritten characters Treat an image as a highdimensional vector (e.g., by reading pixel
More informationData Mining. Neural Networks
Data Mining Neural Networks Goals for this Unit Basic understanding of Neural Networks and how they work Ability to use Neural Networks to solve real problems Understand when neural networks may be most
More informationAssignment # 5. Farrukh Jabeen Due Date: November 2, Neural Networks: Backpropation
Farrukh Jabeen Due Date: November 2, 2009. Neural Networks: Backpropation Assignment # 5 The "Backpropagation" method is one of the most popular methods of "learning" by a neural network. Read the class
More informationWeek 3: Perceptron and Multi-layer Perceptron
Week 3: Perceptron and Multi-layer Perceptron Phong Le, Willem Zuidema November 12, 2013 Last week we studied two famous biological neuron models, Fitzhugh-Nagumo model and Izhikevich model. This week,
More informationOpening the Black Box Data Driven Visualizaion of Neural N
Opening the Black Box Data Driven Visualizaion of Neural Networks September 20, 2006 Aritificial Neural Networks Limitations of ANNs Use of Visualization (ANNs) mimic the processes found in biological
More informationLecture 17: Neural Networks and Deep Learning. Instructor: Saravanan Thirumuruganathan
Lecture 17: Neural Networks and Deep Learning Instructor: Saravanan Thirumuruganathan Outline Perceptron Neural Networks Deep Learning Convolutional Neural Networks Recurrent Neural Networks Auto Encoders
More informationNotes on Multilayer, Feedforward Neural Networks
Notes on Multilayer, Feedforward Neural Networks CS425/528: Machine Learning Fall 2012 Prepared by: Lynne E. Parker [Material in these notes was gleaned from various sources, including E. Alpaydin s book
More informationCode Mania Artificial Intelligence: a. Module - 1: Introduction to Artificial intelligence and Python:
Code Mania 2019 Artificial Intelligence: a. Module - 1: Introduction to Artificial intelligence and Python: 1. Introduction to Artificial Intelligence 2. Introduction to python programming and Environment
More informationA Systematic Overview of Data Mining Algorithms
A Systematic Overview of Data Mining Algorithms 1 Data Mining Algorithm A well-defined procedure that takes data as input and produces output as models or patterns well-defined: precisely encoded as a
More informationArtificial Neural Networks MLP, RBF & GMDH
Artificial Neural Networks MLP, RBF & GMDH Jan Drchal drchajan@fel.cvut.cz Computational Intelligence Group Department of Computer Science and Engineering Faculty of Electrical Engineering Czech Technical
More informationNatural Language Processing CS 6320 Lecture 6 Neural Language Models. Instructor: Sanda Harabagiu
Natural Language Processing CS 6320 Lecture 6 Neural Language Models Instructor: Sanda Harabagiu In this lecture We shall cover: Deep Neural Models for Natural Language Processing Introduce Feed Forward
More informationFor Monday. Read chapter 18, sections Homework:
For Monday Read chapter 18, sections 10-12 The material in section 8 and 9 is interesting, but we won t take time to cover it this semester Homework: Chapter 18, exercise 25 a-b Program 4 Model Neuron
More informationLecture #11: The Perceptron
Lecture #11: The Perceptron Mat Kallada STAT2450 - Introduction to Data Mining Outline for Today Welcome back! Assignment 3 The Perceptron Learning Method Perceptron Learning Rule Assignment 3 Will be
More informationNeural Networks. Neural Network. Neural Network. Neural Network 2/21/2008. Andrew Kusiak. Intelligent Systems Laboratory Seamans Center
Neural Networks Neural Network Input Andrew Kusiak Intelligent t Systems Laboratory 2139 Seamans Center Iowa City, IA 52242-1527 andrew-kusiak@uiowa.edu http://www.icaen.uiowa.edu/~ankusiak Tel. 319-335
More informationNeural Network Learning. Today s Lecture. Continuation of Neural Networks. Artificial Neural Networks. Lecture 24: Learning 3. Victor R.
Lecture 24: Learning 3 Victor R. Lesser CMPSCI 683 Fall 2010 Today s Lecture Continuation of Neural Networks Artificial Neural Networks Compose of nodes/units connected by links Each link has a numeric
More informationA Systematic Overview of Data Mining Algorithms. Sargur Srihari University at Buffalo The State University of New York
A Systematic Overview of Data Mining Algorithms Sargur Srihari University at Buffalo The State University of New York 1 Topics Data Mining Algorithm Definition Example of CART Classification Iris, Wine
More informationMachine Learning 13. week
Machine Learning 13. week Deep Learning Convolutional Neural Network Recurrent Neural Network 1 Why Deep Learning is so Popular? 1. Increase in the amount of data Thanks to the Internet, huge amount of
More informationPattern Classification Algorithms for Face Recognition
Chapter 7 Pattern Classification Algorithms for Face Recognition 7.1 Introduction The best pattern recognizers in most instances are human beings. Yet we do not completely understand how the brain recognize
More informationMotivation. Problem: With our linear methods, we can train the weights but not the basis functions: Activator Trainable weight. Fixed basis function
Neural Networks Motivation Problem: With our linear methods, we can train the weights but not the basis functions: Activator Trainable weight Fixed basis function Flashback: Linear regression Flashback:
More informationCOMP 551 Applied Machine Learning Lecture 14: Neural Networks
COMP 551 Applied Machine Learning Lecture 14: Neural Networks Instructor: (jpineau@cs.mcgill.ca) Class web page: www.cs.mcgill.ca/~jpineau/comp551 Unless otherwise noted, all material posted for this course
More informationNeural Networks. Robot Image Credit: Viktoriya Sukhanova 123RF.com
Neural Networks These slides were assembled by Eric Eaton, with grateful acknowledgement of the many others who made their course materials freely available online. Feel free to reuse or adapt these slides
More informationMultilayer Feed-forward networks
Multi Feed-forward networks 1. Computational models of McCulloch and Pitts proposed a binary threshold unit as a computational model for artificial neuron. This first type of neuron has been generalized
More informationClassification Lecture Notes cse352. Neural Networks. Professor Anita Wasilewska
Classification Lecture Notes cse352 Neural Networks Professor Anita Wasilewska Neural Networks Classification Introduction INPUT: classification data, i.e. it contains an classification (class) attribute
More informationBack propagation Algorithm:
Network Neural: A neural network is a class of computing system. They are created from very simple processing nodes formed into a network. They are inspired by the way that biological systems such as the
More information5 Learning hypothesis classes (16 points)
5 Learning hypothesis classes (16 points) Consider a classification problem with two real valued inputs. For each of the following algorithms, specify all of the separators below that it could have generated
More informationDept. of Computing Science & Math
Lecture 4: Multi-Laer Perceptrons 1 Revie of Gradient Descent Learning 1. The purpose of neural netor training is to minimize the output errors on a particular set of training data b adusting the netor
More informationMachine Learning in Biology
Università degli studi di Padova Machine Learning in Biology Luca Silvestrin (Dottorando, XXIII ciclo) Supervised learning Contents Class-conditional probability density Linear and quadratic discriminant
More informationPattern Recognition. Kjell Elenius. Speech, Music and Hearing KTH. March 29, 2007 Speech recognition
Pattern Recognition Kjell Elenius Speech, Music and Hearing KTH March 29, 2007 Speech recognition 2007 1 Ch 4. Pattern Recognition 1(3) Bayes Decision Theory Minimum-Error-Rate Decision Rules Discriminant
More informationINTRODUCTION TO DEEP LEARNING
INTRODUCTION TO DEEP LEARNING CONTENTS Introduction to deep learning Contents 1. Examples 2. Machine learning 3. Neural networks 4. Deep learning 5. Convolutional neural networks 6. Conclusion 7. Additional
More informationTechnical University of Munich. Exercise 7: Neural Network Basics
Technical University of Munich Chair for Bioinformatics and Computational Biology Protein Prediction I for Computer Scientists SoSe 2018 Prof. B. Rost M. Bernhofer, M. Heinzinger, D. Nechaev, L. Richter
More informationCharacter Recognition Using Convolutional Neural Networks
Character Recognition Using Convolutional Neural Networks David Bouchain Seminar Statistical Learning Theory University of Ulm, Germany Institute for Neural Information Processing Winter 2006/2007 Abstract
More informationNeural Networks. By Laurence Squires
Neural Networks By Laurence Squires Machine learning What is it? Type of A.I. (possibly the ultimate A.I.?!?!?!) Algorithms that learn how to classify data The algorithms slowly change their own variables
More informationArtificial neural networks are the paradigm of connectionist systems (connectionism vs. symbolism)
Artificial Neural Networks Analogy to biological neural systems, the most robust learning systems we know. Attempt to: Understand natural biological systems through computational modeling. Model intelligent
More informationCS 4510/9010 Applied Machine Learning. Neural Nets. Paula Matuszek Fall copyright Paula Matuszek 2016
CS 4510/9010 Applied Machine Learning 1 Neural Nets Paula Matuszek Fall 2016 Neural Nets, the very short version 2 A neural net consists of layers of nodes, or neurons, each of which has an activation
More informationLecture 20: Neural Networks for NLP. Zubin Pahuja
Lecture 20: Neural Networks for NLP Zubin Pahuja zpahuja2@illinois.edu courses.engr.illinois.edu/cs447 CS447: Natural Language Processing 1 Today s Lecture Feed-forward neural networks as classifiers simple
More informationCS 6501: Deep Learning for Computer Graphics. Training Neural Networks II. Connelly Barnes
CS 6501: Deep Learning for Computer Graphics Training Neural Networks II Connelly Barnes Overview Preprocessing Initialization Vanishing/exploding gradients problem Batch normalization Dropout Additional
More informationNeuron Selectivity as a Biologically Plausible Alternative to Backpropagation
Neuron Selectivity as a Biologically Plausible Alternative to Backpropagation C.J. Norsigian Department of Bioengineering cnorsigi@eng.ucsd.edu Vishwajith Ramesh Department of Bioengineering vramesh@eng.ucsd.edu
More informationMachine Learning Classifiers and Boosting
Machine Learning Classifiers and Boosting Reading Ch 18.6-18.12, 20.1-20.3.2 Outline Different types of learning problems Different types of learning algorithms Supervised learning Decision trees Naïve
More informationNeural Networks. Single-layer neural network. CSE 446: Machine Learning Emily Fox University of Washington March 10, /10/2017
3/0/207 Neural Networks Emily Fox University of Washington March 0, 207 Slides adapted from Ali Farhadi (via Carlos Guestrin and Luke Zettlemoyer) Single-layer neural network 3/0/207 Perceptron as a neural
More informationThe Mathematics Behind Neural Networks
The Mathematics Behind Neural Networks Pattern Recognition and Machine Learning by Christopher M. Bishop Student: Shivam Agrawal Mentor: Nathaniel Monson Courtesy of xkcd.com The Black Box Training the
More informationNeural Networks (pp )
Notation: Means pencil-and-paper QUIZ Means coding QUIZ Neural Networks (pp. 106-121) The first artificial neural network (ANN) was the (single-layer) perceptron, a simplified model of a biological neuron.
More informationOptimizing Number of Hidden Nodes for Artificial Neural Network using Competitive Learning Approach
Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology IJCSMC, Vol. 4, Issue. 5, May 2015, pg.358
More informationWeiguang Guan Code & data: guanw.sharcnet.ca/ss2017-deeplearning.tar.gz
Weiguang Guan guanw@sharcnet.ca Code & data: guanw.sharcnet.ca/ss2017-deeplearning.tar.gz Outline Part I: Introduction Overview of machine learning and AI Introduction to neural network and deep learning
More informationModel learning for robot control: a survey
Model learning for robot control: a survey Duy Nguyen-Tuong, Jan Peters 2011 Presented by Evan Beachly 1 Motivation Robots that can learn how their motors move their body Complexity Unanticipated Environments
More informationShip Energy Systems Modelling: a Gray-Box approach
MOSES Workshop: Modelling and Optimization of Ship Energy Systems Ship Energy Systems Modelling: a Gray-Box approach 25 October 2017 Dr Andrea Coraddu andrea.coraddu@strath.ac.uk 30/10/2017 Modelling &
More informationCP365 Artificial Intelligence
CP365 Artificial Intelligence Example Problem Problem: Does a given image contain cats? Input vector: RGB/BW pixels of the image. Output: Yes or No. Example Problem Problem: What category is a news story?
More informationLogical Rhythm - Class 3. August 27, 2018
Logical Rhythm - Class 3 August 27, 2018 In this Class Neural Networks (Intro To Deep Learning) Decision Trees Ensemble Methods(Random Forest) Hyperparameter Optimisation and Bias Variance Tradeoff Biological
More informationIntroduction to Neural Networks
Introduction to Neural Networks What are connectionist neural networks? Connectionism refers to a computer modeling approach to computation that is loosely based upon the architecture of the brain Many
More informationCS 2750: Machine Learning. Neural Networks. Prof. Adriana Kovashka University of Pittsburgh April 13, 2016
CS 2750: Machine Learning Neural Networks Prof. Adriana Kovashka University of Pittsburgh April 13, 2016 Plan for today Neural network definition and examples Training neural networks (backprop) Convolutional
More informationCOMPUTATIONAL INTELLIGENCE SEW (INTRODUCTION TO MACHINE LEARNING) SS18. Lecture 6: k-nn Cross-validation Regularization
COMPUTATIONAL INTELLIGENCE SEW (INTRODUCTION TO MACHINE LEARNING) SS18 Lecture 6: k-nn Cross-validation Regularization LEARNING METHODS Lazy vs eager learning Eager learning generalizes training data before
More informationNeural Networks CMSC475/675
Introduction to Neural Networks CMSC475/675 Chapter 1 Introduction Why ANN Introduction Some tasks can be done easily (effortlessly) by humans but are hard by conventional paradigms on Von Neumann machine
More informationCS 8520: Artificial Intelligence. Machine Learning 2. Paula Matuszek Fall, CSC 8520 Fall Paula Matuszek
CS 8520: Artificial Intelligence Machine Learning 2 Paula Matuszek Fall, 2015!1 Regression Classifiers We said earlier that the task of a supervised learning system can be viewed as learning a function
More informationAn Algorithm For Training Multilayer Perceptron (MLP) For Image Reconstruction Using Neural Network Without Overfitting.
An Algorithm For Training Multilayer Perceptron (MLP) For Image Reconstruction Using Neural Network Without Overfitting. Mohammad Mahmudul Alam Mia, Shovasis Kumar Biswas, Monalisa Chowdhury Urmi, Abubakar
More informationMore on Neural Networks. Read Chapter 5 in the text by Bishop, except omit Sections 5.3.3, 5.3.4, 5.4, 5.5.4, 5.5.5, 5.5.6, 5.5.7, and 5.
More on Neural Networks Read Chapter 5 in the text by Bishop, except omit Sections 5.3.3, 5.3.4, 5.4, 5.5.4, 5.5.5, 5.5.6, 5.5.7, and 5.6 Recall the MLP Training Example From Last Lecture log likelihood
More informationCS 8520: Artificial Intelligence
CS 8520: Artificial Intelligence Machine Learning 2 Paula Matuszek Spring, 2013 1 Regression Classifiers We said earlier that the task of a supervised learning system can be viewed as learning a function
More informationNeural Nets. CSCI 5582, Fall 2007
Neural Nets CSCI 5582, Fall 2007 Assignments For this week: Chapter 20, section 5 Problem Set 3 is due a week from today Neural Networks: Some First Concepts Each neural element is loosely based on the
More informationDeep Learning. Practical introduction with Keras JORDI TORRES 27/05/2018. Chapter 3 JORDI TORRES
Deep Learning Practical introduction with Keras Chapter 3 27/05/2018 Neuron A neural network is formed by neurons connected to each other; in turn, each connection of one neural network is associated
More informationAMOL MUKUND LONDHE, DR.CHELPA LINGAM
International Journal of Advances in Applied Science and Engineering (IJAEAS) ISSN (P): 2348-1811; ISSN (E): 2348-182X Vol. 2, Issue 4, Dec 2015, 53-58 IIST COMPARATIVE ANALYSIS OF ANN WITH TRADITIONAL
More informationEECS 496 Statistical Language Models. Winter 2018
EECS 496 Statistical Language Models Winter 2018 Introductions Professor: Doug Downey Course web site: www.cs.northwestern.edu/~ddowney/courses/496_winter2018 (linked off prof. home page) Logistics Grading
More informationReservoir Computing with Emphasis on Liquid State Machines
Reservoir Computing with Emphasis on Liquid State Machines Alex Klibisz University of Tennessee aklibisz@gmail.com November 28, 2016 Context and Motivation Traditional ANNs are useful for non-linear problems,
More informationCS 354R: Computer Game Technology
CS 354R: Computer Game Technology AI Fuzzy Logic and Neural Nets Fall 2018 Fuzzy Logic Philosophical approach Decisions based on degree of truth Is not a method for reasoning under uncertainty that s probability
More informationSimple Model Selection Cross Validation Regularization Neural Networks
Neural Nets: Many possible refs e.g., Mitchell Chapter 4 Simple Model Selection Cross Validation Regularization Neural Networks Machine Learning 10701/15781 Carlos Guestrin Carnegie Mellon University February
More informationA Quick Guide on Training a neural network using Keras.
A Quick Guide on Training a neural network using Keras. TensorFlow and Keras Keras Open source High level, less flexible Easy to learn Perfect for quick implementations Starts by François Chollet from
More informationThe Problem of Overfitting with Maximum Likelihood
The Problem of Overfitting with Maximum Likelihood In the previous example, continuing training to find the absolute maximum of the likelihood produced overfitted results. The effect is much bigger if
More informationLecture 2 Notes. Outline. Neural Networks. The Big Idea. Architecture. Instructors: Parth Shah, Riju Pahwa
Instructors: Parth Shah, Riju Pahwa Lecture 2 Notes Outline 1. Neural Networks The Big Idea Architecture SGD and Backpropagation 2. Convolutional Neural Networks Intuition Architecture 3. Recurrent Neural
More informationFast Learning for Big Data Using Dynamic Function
IOP Conference Series: Materials Science and Engineering PAPER OPEN ACCESS Fast Learning for Big Data Using Dynamic Function To cite this article: T Alwajeeh et al 2017 IOP Conf. Ser.: Mater. Sci. Eng.
More informationNeural Nets & Deep Learning
Neural Nets & Deep Learning The Inspiration Inputs Outputs Our brains are pretty amazing, what if we could do something similar with computers? Image Source: http://ib.bioninja.com.au/_media/neuron _med.jpeg
More informationMulti-layer Perceptron Forward Pass Backpropagation. Lecture 11: Aykut Erdem November 2016 Hacettepe University
Multi-layer Perceptron Forward Pass Backpropagation Lecture 11: Aykut Erdem November 2016 Hacettepe University Administrative Assignment 2 due Nov. 10, 2016! Midterm exam on Monday, Nov. 14, 2016 You are
More informationMachine Learning in Telecommunications
Machine Learning in Telecommunications Paulos Charonyktakis & Maria Plakia Department of Computer Science, University of Crete Institute of Computer Science, FORTH Roadmap Motivation Supervised Learning
More informationMachine Learning. Chao Lan
Machine Learning Chao Lan Machine Learning Prediction Models Regression Model - linear regression (least square, ridge regression, Lasso) Classification Model - naive Bayes, logistic regression, Gaussian
More information11/14/2010 Intelligent Systems and Soft Computing 1
Lecture 7 Artificial neural networks: Supervised learning Introduction, or how the brain works The neuron as a simple computing element The perceptron Multilayer neural networks Accelerated learning in
More informationMore on Learning. Neural Nets Support Vectors Machines Unsupervised Learning (Clustering) K-Means Expectation-Maximization
More on Learning Neural Nets Support Vectors Machines Unsupervised Learning (Clustering) K-Means Expectation-Maximization Neural Net Learning Motivated by studies of the brain. A network of artificial
More informationArtificial Neural Networks. Introduction to Computational Neuroscience Ardi Tampuu
Artificial Neural Networks Introduction to Computational Neuroscience Ardi Tampuu 7.0.206 Artificial neural network NB! Inspired by biology, not based on biology! Applications Automatic speech recognition
More informationOptimum size of feed forward neural network for Iris data set.
Optimum size of feed forward neural network for Iris data set. Wojciech Masarczyk Faculty of Applied Mathematics Silesian University of Technology Gliwice, Poland Email: wojcmas0@polsl.pl Abstract This
More informationData Mining. Covering algorithms. Covering approach At each stage you identify a rule that covers some of instances. Fig. 4.
Data Mining Chapter 4. Algorithms: The Basic Methods (Covering algorithm, Association rule, Linear models, Instance-based learning, Clustering) 1 Covering approach At each stage you identify a rule that
More informationDeep Neural Networks Optimization
Deep Neural Networks Optimization Creative Commons (cc) by Akritasa http://arxiv.org/pdf/1406.2572.pdf Slides from Geoffrey Hinton CSC411/2515: Machine Learning and Data Mining, Winter 2018 Michael Guerzhoy
More informationCse634 DATA MINING TEST REVIEW. Professor Anita Wasilewska Computer Science Department Stony Brook University
Cse634 DATA MINING TEST REVIEW Professor Anita Wasilewska Computer Science Department Stony Brook University Preprocessing stage Preprocessing: includes all the operations that have to be performed before
More informationPredict the box office of US movies
Predict the box office of US movies Group members: Hanqing Ma, Jin Sun, Zeyu Zhang 1. Introduction Our task is to predict the box office of the upcoming movies using the properties of the movies, such
More informationCOMPUTATIONAL INTELLIGENCE
COMPUTATIONAL INTELLIGENCE Fundamentals Adrian Horzyk Preface Before we can proceed to discuss specific complex methods we have to introduce basic concepts, principles, and models of computational intelligence
More informationIntroduction to Neural Networks
ECE 5775 (Fall 17) High-Level Digital Design Automation Introduction to Neural Networks Ritchie Zhao, Zhiru Zhang School of Electrical and Computer Engineering Rise of the Machines Neural networks have
More informationFAST NEURAL NETWORK ALGORITHM FOR SOLVING CLASSIFICATION TASKS
Virginia Commonwealth University VCU Scholars Compass Theses and Dissertations Graduate School 2012 FAST NEURAL NETWORK ALGORITHM FOR SOLVING CLASSIFICATION TASKS Noor Albarakati Virginia Commonwealth
More informationLinear Separability. Linear Separability. Capabilities of Threshold Neurons. Capabilities of Threshold Neurons. Capabilities of Threshold Neurons
Linear Separability Input space in the two-dimensional case (n = ): - - - - - - w =, w =, = - - - - - - w = -, w =, = - - - - - - w = -, w =, = Linear Separability So by varying the weights and the threshold,
More informationArtificial Neural Networks
The Perceptron Rodrigo Fernandes de Mello Invited Professor at Télécom ParisTech Associate Professor at Universidade de São Paulo, ICMC, Brazil http://www.icmc.usp.br/~mello mello@icmc.usp.br Conceptually
More informationCOMPUTATIONAL INTELLIGENCE
COMPUTATIONAL INTELLIGENCE Radial Basis Function Networks Adrian Horzyk Preface Radial Basis Function Networks (RBFN) are a kind of artificial neural networks that use radial basis functions (RBF) as activation
More informationCPSC 340: Machine Learning and Data Mining. Logistic Regression Fall 2016
CPSC 340: Machine Learning and Data Mining Logistic Regression Fall 2016 Admin Assignment 1: Marks visible on UBC Connect. Assignment 2: Solution posted after class. Assignment 3: Due Wednesday (at any
More informationArtificial Neural Networks Lecture Notes Part 5. Stephen Lucci, PhD. Part 5
Artificial Neural Networks Lecture Notes Part 5 About this file: If you have trouble reading the contents of this file, or in case of transcription errors, email gi0062@bcmail.brooklyn.cuny.edu Acknowledgments:
More informationPerceptron as a graph
Neural Networks Machine Learning 10701/15781 Carlos Guestrin Carnegie Mellon University October 10 th, 2007 2005-2007 Carlos Guestrin 1 Perceptron as a graph 1 0.9 0.8 0.7 0.6 0.5 0.4 0.3 0.2 0.1 0-6 -4-2
More informationNeural Networks (Overview) Prof. Richard Zanibbi
Neural Networks (Overview) Prof. Richard Zanibbi Inspired by Biology Introduction But as used in pattern recognition research, have little relation with real neural systems (studied in neurology and neuroscience)
More informationCS 1674: Intro to Computer Vision. Neural Networks. Prof. Adriana Kovashka University of Pittsburgh November 16, 2016
CS 1674: Intro to Computer Vision Neural Networks Prof. Adriana Kovashka University of Pittsburgh November 16, 2016 Announcements Please watch the videos I sent you, if you haven t yet (that s your reading)
More informationNeural Networks and Deep Learning
Neural Networks and Deep Learning Example Learning Problem Example Learning Problem Celebrity Faces in the Wild Machine Learning Pipeline Raw data Feature extract. Feature computation Inference: prediction,
More informationExercise: Training Simple MLP by Backpropagation. Using Netlab.
Exercise: Training Simple MLP by Backpropagation. Using Netlab. Petr Pošík December, 27 File list This document is an explanation text to the following script: demomlpklin.m script implementing the beckpropagation
More informationNeural Network Approach for Automatic Landuse Classification of Satellite Images: One-Against-Rest and Multi-Class Classifiers
Neural Network Approach for Automatic Landuse Classification of Satellite Images: One-Against-Rest and Multi-Class Classifiers Anil Kumar Goswami DTRL, DRDO Delhi, India Heena Joshi Banasthali Vidhyapith
More information