An AI-driven Malfunction Detection Concept
|
|
|
- Clarence Shepherd
- 5 years ago
- Views:
Transcription
1 Deutsches Forschungszentrum für Künstliche Intelligenz German Research Centre for Artificial An AI-driven Malfunction Detection Concept fornfvinstancesin5g Julian Ahrens Mathias Strufe Lia Ahrens Hans D. Schotten May17,2018 ThisworkwassupportedbytheEuropeanUnion shorizon2020programme under the 5G-PPP project: Framework for Self-Organized Network Management in Virtualized and Software Defined Networks(SELF- NET) with Grant no. H2020-ICT /
2 Main Problem Example Setup Intelligent Networks AI-driven Malfunction Detection 2/ 16
3 Main Problem Main Problem Example Setup Intelligent Networks AI-driven Malfunction Detection 3/ 16
4 Main Problem Main Problem Example Setup Challenge: detect previously unencountered problems in VNFs using network and performance metrics Intelligent Networks AI-driven Malfunction Detection 3/ 16
5 Example Setup Main Problem Example Setup Intelligent Networks AI-driven Malfunction Detection 4/ 16
6 Example Setup Main Problem Example Setup Intelligent Networks AI-driven Malfunction Detection 4/ 16
7 Example Setup Intelligent Networks AI-driven Malfunction Detection 5/ 16
8 Example Setup Main Problem Example Setup Intelligent Networks AI-driven Malfunction Detection 6/ 16
9 Example Setup Main Problem Example Setup Example VNF: virtualized firewall Intelligent Networks AI-driven Malfunction Detection 6/ 16
10 Example Setup Main Problem Example Setup Example VNF: virtualized firewall Data flowing from the sources to the destinations Intelligent Networks AI-driven Malfunction Detection 6/ 16
11 Example Setup Main Problem Example Setup Example VNF: virtualized firewall Data flowing from the sources to the destinations Additional traffic between internet and destinations Intelligent Networks AI-driven Malfunction Detection 6/ 16
12 Example Setup Main Problem Example Setup Example VNF: virtualized firewall Data flowing from the sources to the destinations Additional traffic between internet and destinations Firewalls filtering traffic from source to one of the destinations Intelligent Networks AI-driven Malfunction Detection 6/ 16
13 Example Setup Main Problem Example Setup Intelligent Networks AI-driven Malfunction Detection 7/ 16
14 Example Setup Main Problem Example Setup Features: CPU utilization, memory utilization, HDD utilization, network traffic in and out, each on two interfaces Intelligent Networks AI-driven Malfunction Detection 7/ 16
15 Example Setup Main Problem Example Setup Features: CPU utilization, memory utilization, HDD utilization, network traffic in and out, each on two interfaces Ñ seven features Intelligent Networks AI-driven Malfunction Detection 7/ 16
16 Example Setup Main Problem Example Setup Features: CPU utilization, memory utilization, HDD utilization, network traffic in and out, each on two interfaces Ñ seven features Anomaly used for testing: memory leak Intelligent Networks AI-driven Malfunction Detection 7/ 16
17 Intelligent Networks AI-driven Malfunction Detection 8/ 16
18 Intelligent Networks AI-driven Malfunction Detection 9/ 16
19 Dataset of known good operation Intelligent Networks AI-driven Malfunction Detection 9/ 16
20 Dataset of known good operation No actual anomalies are used during the training process Intelligent Networks AI-driven Malfunction Detection 9/ 16
21 Dataset of known good operation No actual anomalies are used during the training process Available methods: clustering, dimensionality reduction/ sparsity constraints Intelligent Networks AI-driven Malfunction Detection 9/ 16
22 Dataset of known good operation No actual anomalies are used during the training process Available methods: clustering, dimensionality reduction/ sparsity constraints Ñ Measure of similarity required Intelligent Networks AI-driven Malfunction Detection 9/ 16
23 Dataset of known good operation No actual anomalies are used during the training process Available methods: clustering, dimensionality reduction/ sparsity constraints Ñ Measure of similarity required Problem: Heterogeneity of data, multiple scales Intelligent Networks AI-driven Malfunction Detection 9/ 16
24 Dataset of known good operation No actual anomalies are used during the training process Available methods: clustering, dimensionality reduction/ sparsity constraints Ñ Measure of similarity required Problem: Heterogeneity of data, multiple scales Ñ Normalization required Intelligent Networks AI-driven Malfunction Detection 9/ 16
25 Dataset of known good operation No actual anomalies are used during the training process Available methods: clustering, dimensionality reduction/ sparsity constraints Ñ Measure of similarity required Problem: Heterogeneity of data, multiple scales Ñ Normalization required Normalization via parametric and nonparametric statistical approaches Intelligent Networks AI-driven Malfunction Detection 9/ 16
26 Intelligent Networks AI-driven Malfunction Detection 10/ 16
27 Dimensionality reduction via s Intelligent Networks AI-driven Malfunction Detection 10/ 16
28 Dimensionality reduction via s s are replicating artificial neural networks Intelligent Networks AI-driven Malfunction Detection 10/ 16
29 Dimensionality reduction via s s are replicating artificial neural networks Intelligent Networks AI-driven Malfunction Detection 10/ 16
30 Dimensionality reduction via s s are replicating artificial neural networks Both current value and difference to last value used as features Intelligent Networks AI-driven Malfunction Detection 10/ 16
31 Dimensionality reduction via s s are replicating artificial neural networks Both current value and difference to last value used as features Ñ 14 features in the example setup Intelligent Networks AI-driven Malfunction Detection 10/ 16
32 Dimensionality reduction via s s are replicating artificial neural networks Both current value and difference to last value used as features Ñ 14 features in the example setup Hyperparameters: number of layers/ layer sizes, activation function, rate during training Intelligent Networks AI-driven Malfunction Detection 10/ 16
33 Intelligent Networks AI-driven Malfunction Detection 11/ 16
34 Measure of similarity: Euclidean distance Intelligent Networks AI-driven Malfunction Detection 11/ 16
35 Measure of similarity: Euclidean distance is trained to best approximate its input by its output in the Euclidean distance over the training data Intelligent Networks AI-driven Malfunction Detection 11/ 16
36 Measure of similarity: Euclidean distance is trained to best approximate its input by its output in the Euclidean distance over the training data Measure of normality: Euclidean distance of output of autoencoder to its input Intelligent Networks AI-driven Malfunction Detection 11/ 16
37 Measure of similarity: Euclidean distance is trained to best approximate its input by its output in the Euclidean distance over the training data Measure of normality: Euclidean distance of output of autoencoder to its input If this distance is above a certain threshold, a datapoint is considered anomalous by the autoencoder Intelligent Networks AI-driven Malfunction Detection 11/ 16
38 Measure of similarity: Euclidean distance is trained to best approximate its input by its output in the Euclidean distance over the training data Measure of normality: Euclidean distance of output of autoencoder to its input If this distance is above a certain threshold, a datapoint is considered anomalous by the autoencoder Hyperparameter: anomaly threshold Intelligent Networks AI-driven Malfunction Detection 11/ 16
39 Measure of similarity: Euclidean distance is trained to best approximate its input by its output in the Euclidean distance over the training data Measure of normality: Euclidean distance of output of autoencoder to its input If this distance is above a certain threshold, a datapoint is considered anomalous by the autoencoder Hyperparameter: anomaly threshold Use an additional validation dataset to adjust the anomaly threshold until the number of false positives reaches a desirable level Intelligent Networks AI-driven Malfunction Detection 11/ 16
40 Intelligent Networks AI-driven Malfunction Detection 12/ 16
41 Use more than one autoencoder in order to capture different characteristics of the data Intelligent Networks AI-driven Malfunction Detection 12/ 16
42 Use more than one autoencoder in order to capture different characteristics of the data Different autoencoders governed by different hyperparameters Intelligent Networks AI-driven Malfunction Detection 12/ 16
43 Use more than one autoencoder in order to capture different characteristics of the data Different autoencoders governed by different hyperparameters Allows for diversity in sparsity, nonlinearity, etc. Intelligent Networks AI-driven Malfunction Detection 12/ 16
44 Use more than one autoencoder in order to capture different characteristics of the data Different autoencoders governed by different hyperparameters Allows for diversity in sparsity, nonlinearity, etc. In the test scenario: three to seven layers, central layer sizes from two to eight neurons, tanh and ReLU activation functions, total of 216 autoencoders Intelligent Networks AI-driven Malfunction Detection 12/ 16
45 Use more than one autoencoder in order to capture different characteristics of the data Different autoencoders governed by different hyperparameters Allows for diversity in sparsity, nonlinearity, etc. In the test scenario: three to seven layers, central layer sizes from two to eight neurons, tanh and ReLU activation functions, total of 216 autoencoders Vote among autoencoders: a datapoint is considered normal if enough of the autoencoders consider the datapoint normal; otherwise, it is considered anomalous Intelligent Networks AI-driven Malfunction Detection 12/ 16
46 Results Intelligent Networks AI-driven Malfunction Detection 13/ 16
47 Results Results Intelligent Networks AI-driven Malfunction Detection 14/ 16
48 Results Significant generalization performance Results Intelligent Networks AI-driven Malfunction Detection 14/ 16
49 Results Significant generalization performance Most of the autoencoders converge very well on the validation dataset Results Intelligent Networks AI-driven Malfunction Detection 14/ 16
50 Results Significant generalization performance Most of the autoencoders converge very well on the validation dataset Results Intelligent Networks AI-driven Malfunction Detection 14/ 16
51 Results Significant generalization performance Most of the autoencoders converge very well on the validation dataset Results % detection rate vs. 0.7% false positives Intelligent Networks AI-driven Malfunction Detection 14/ 16
52 Questions? Intelligent Networks AI-driven Malfunction Detection 15/ 16
53 Thank you! Intelligent Networks AI-driven Malfunction Detection 16/ 16
Outlier detection using autoencoders
Outlier detection using autoencoders August 19, 2016 Author: Olga Lyudchik Supervisors: Dr. Jean-Roch Vlimant Dr. Maurizio Pierini CERN Non Member State Summer Student Report 2016 Abstract Outlier detection
COMP 551 Applied Machine Learning Lecture 13: Unsupervised learning
COMP 551 Applied Machine Learning Lecture 13: Unsupervised learning Associate Instructor: Herke van Hoof (herke.vanhoof@mail.mcgill.ca) Slides mostly by: (jpineau@cs.mcgill.ca) Class web page: www.cs.mcgill.ca/~jpineau/comp551
Intrusion Detection by Combining and Clustering Diverse Monitor Data
Intrusion Detection by Combining and Clustering Diverse Monitor Data TSS/ACC Seminar April 5, 26 Atul Bohara and Uttam Thakore PI: Bill Sanders Outline Motivation Overview of the approach Feature extraction
Analyzing Flow-based Anomaly Intrusion Detection using Replicator Neural Networks. Carlos García Cordero Sascha Hauke Max Mühlhäuser Mathias Fischer
Analyzing Flow-based Anomaly Intrusion Detection using Replicator Neural Networks Carlos García Cordero Sascha Hauke Max Mühlhäuser Mathias Fischer The Beautiful World of IoT 06.03.2018 garcia@tk.tu-darmstadt.de
Lecture #17: Autoencoders and Random Forests with R. Mat Kallada Introduction to Data Mining with R
Lecture #17: Autoencoders and Random Forests with R Mat Kallada Introduction to Data Mining with R Assignment 4 Posted last Sunday Due next Monday! Autoencoders in R Firstly, what is an autoencoder? Autoencoders
Brainchip OCTOBER
Brainchip OCTOBER 2017 1 Agenda Neuromorphic computing background Akida Neuromorphic System-on-Chip (NSoC) Brainchip OCTOBER 2017 2 Neuromorphic Computing Background Brainchip OCTOBER 2017 3 A Brief History
Unsupervised learning in Vision
Chapter 7 Unsupervised learning in Vision The fields of Computer Vision and Machine Learning complement each other in a very natural way: the aim of the former is to extract useful information from visual
Data Mining Course Overview
Data Mining Course Overview 1 Data Mining Overview Understanding Data Classification: Decision Trees and Bayesian classifiers, ANN, SVM Association Rules Mining: APriori, FP-growth Clustering: Hierarchical
Network Traffic Measurements and Analysis
DEIB - Politecnico di Milano Fall, 2017 Introduction Often, we have only a set of features x = x 1, x 2,, x n, but no associated response y. Therefore we are not interested in prediction nor classification,
On Classification: An Empirical Study of Existing Algorithms Based on Two Kaggle Competitions
On Classification: An Empirical Study of Existing Algorithms Based on Two Kaggle Competitions CAMCOS Report Day December 9th, 2015 San Jose State University Project Theme: Classification The Kaggle Competition
Correlative Analytic Methods in Large Scale Network Infrastructure Hariharan Krishnaswamy Senior Principal Engineer Dell EMC
Correlative Analytic Methods in Large Scale Network Infrastructure Hariharan Krishnaswamy Senior Principal Engineer Dell EMC 2018 Storage Developer Conference. Dell EMC. All Rights Reserved. 1 Data Center
Intrusion Detection Systems
Intrusion Detection Systems Dr. Ahmad Almulhem Computer Engineering Department, KFUPM Spring 2008 Ahmad Almulhem - Network Security Engineering - 2008 1 / 15 Outline 1 Introduction Overview History 2 Types
International Journal of Scientific Research & Engineering Trends Volume 4, Issue 6, Nov-Dec-2018, ISSN (Online): X
Analysis about Classification Techniques on Categorical Data in Data Mining Assistant Professor P. Meena Department of Computer Science Adhiyaman Arts and Science College for Women Uthangarai, Krishnagiri,
CLUSTERING. CSE 634 Data Mining Prof. Anita Wasilewska TEAM 16
CLUSTERING CSE 634 Data Mining Prof. Anita Wasilewska TEAM 16 1. K-medoids: REFERENCES https://www.coursera.org/learn/cluster-analysis/lecture/nj0sb/3-4-the-k-medoids-clustering-method https://anuradhasrinivas.files.wordpress.com/2013/04/lesson8-clustering.pdf
MATLAB representation of neural network Outline Neural network with single-layer of neurons. Neural network with multiple-layer of neurons.
MATLAB representation of neural network Outline Neural network with single-layer of neurons. Neural network with multiple-layer of neurons. Introduction: Neural Network topologies (Typical Architectures)
Functional Safety beyond ISO26262 for Neural Networks in Highly Automated Driving
Functional Safety beyond ISO26262 for Neural Networks in Highly Automated Driving Autonomous Driving Meetup #5 MAN Track Forum, Munich 27 th of March 2018 André Roßbach, Tim Heinemann, Florian Bogenberger
Statistical Learning Part 2 Nonparametric Learning: The Main Ideas. R. Moeller Hamburg University of Technology
Statistical Learning Part 2 Nonparametric Learning: The Main Ideas R. Moeller Hamburg University of Technology Instance-Based Learning So far we saw statistical learning as parameter learning, i.e., given
Deep Learning with Tensorflow AlexNet
Machine Learning and Computer Vision Group Deep Learning with Tensorflow http://cvml.ist.ac.at/courses/dlwt_w17/ AlexNet Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton, "Imagenet classification
NVIDIA FOR DEEP LEARNING. Bill Veenhuis
NVIDIA FOR DEEP LEARNING Bill Veenhuis bveenhuis@nvidia.com Nvidia is the world s leading ai platform ONE ARCHITECTURE CUDA 2 GPU: Perfect Companion for Accelerating Apps & A.I. CPU GPU 3 Intro to AI AGENDA
MoonRiver: Deep Neural Network in C++
MoonRiver: Deep Neural Network in C++ Chung-Yi Weng Computer Science & Engineering University of Washington chungyi@cs.washington.edu Abstract Artificial intelligence resurges with its dramatic improvement
The exam is closed book, closed notes except your one-page (two-sided) cheat sheet.
CS 189 Spring 2015 Introduction to Machine Learning Final You have 2 hours 50 minutes for the exam. The exam is closed book, closed notes except your one-page (two-sided) cheat sheet. No calculators or
Supervised 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
Knowledge-Defined Networking: Towards Self-Driving Networks
Knowledge-Defined Networking: Towards Self-Driving Networks Albert Cabellos (UPC/BarcelonaTech, Spain) albert.cabellos@gmail.com 2nd IFIP/IEEE International Workshop on Analytics for Network and Service
Motivation. 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:
CSC 411: Lecture 14: Principal Components Analysis & Autoencoders
CSC 411: Lecture 14: Principal Components Analysis & Autoencoders Raquel Urtasun & Rich Zemel University of Toronto Nov 4, 2015 Urtasun & Zemel (UofT) CSC 411: 14-PCA & Autoencoders Nov 4, 2015 1 / 18
MTTTS17 Dimensionality Reduction and Visualization. Spring 2018 Jaakko Peltonen. Lecture 11: Neighbor Embedding Methods continued
MTTTS17 Dimensionality Reduction and Visualization Spring 2018 Jaakko Peltonen Lecture 11: Neighbor Embedding Methods continued This Lecture Neighbor embedding by generative modeling Some supervised neighbor
CHAPTER 6 MODIFIED FUZZY TECHNIQUES BASED IMAGE SEGMENTATION
CHAPTER 6 MODIFIED FUZZY TECHNIQUES BASED IMAGE SEGMENTATION 6.1 INTRODUCTION Fuzzy logic based computational techniques are becoming increasingly important in the medical image analysis arena. The significant
CSC 411: Lecture 14: Principal Components Analysis & Autoencoders
CSC 411: Lecture 14: Principal Components Analysis & Autoencoders Richard Zemel, Raquel Urtasun and Sanja Fidler University of Toronto Zemel, Urtasun, Fidler (UofT) CSC 411: 14-PCA & Autoencoders 1 / 18
DS504/CS586: Big Data Analytics Big Data Clustering Prof. Yanhua Li
Welcome to DS504/CS586: Big Data Analytics Big Data Clustering Prof. Yanhua Li Time: 6:00pm 8:50pm Thu Location: AK 232 Fall 2016 High Dimensional Data v Given a cloud of data points we want to understand
Neural Networks for Machine Learning. Lecture 15a From Principal Components Analysis to Autoencoders
Neural Networks for Machine Learning Lecture 15a From Principal Components Analysis to Autoencoders Geoffrey Hinton Nitish Srivastava, Kevin Swersky Tijmen Tieleman Abdel-rahman Mohamed Principal Components
Contents. Preface to the Second Edition
Preface to the Second Edition v 1 Introduction 1 1.1 What Is Data Mining?....................... 4 1.2 Motivating Challenges....................... 5 1.3 The Origins of Data Mining....................
Clustering algorithms and autoencoders for anomaly detection
Clustering algorithms and autoencoders for anomaly detection Alessia Saggio Lunch Seminars and Journal Clubs Université catholique de Louvain, Belgium 3rd March 2017 a Outline Introduction Clustering algorithms
Machine Learning : Clustering, Self-Organizing Maps
Machine Learning Clustering, Self-Organizing Maps 12/12/2013 Machine Learning : Clustering, Self-Organizing Maps Clustering The task: partition a set of objects into meaningful subsets (clusters). The
Deep Learning with R. Francesca Lazzeri Data Scientist II - Microsoft, AI Research
with R Francesca Lazzeri - @frlazzeri Data Scientist II - Microsoft, AI Research Agenda with R What is Demo Better understanding of R DL tools Fundamental concepts in Forward Propagation Algorithm Activation
Machine Learning. The Breadth of ML Neural Networks & Deep Learning. Marc Toussaint. Duy Nguyen-Tuong. University of Stuttgart
Machine Learning The Breadth of ML Neural Networks & Deep Learning Marc Toussaint University of Stuttgart Duy Nguyen-Tuong Bosch Center for Artificial Intelligence Summer 2017 Neural Networks Consider
CS 343: Artificial Intelligence
CS 343: Artificial Intelligence Kernels and Clustering Prof. Scott Niekum The University of Texas at Austin [These slides based on those of Dan Klein and Pieter Abbeel for CS188 Intro to AI at UC Berkeley.
2. Neural network basics
2. Neural network basics Next commonalities among different neural networks are discussed in order to get started and show which structural parts or concepts appear in almost all networks. It is presented
Package SAENET. June 4, 2015
Type Package Package SAENET June 4, 2015 Title A Stacked Autoencoder Implementation with Interface to 'neuralnet' Version 1.1 Date 2015-06-04 An implementation of a stacked sparse autoencoder for dimension
Network Anomaly Detection Using Autonomous System Flow Aggregates
Network Anomaly Detection Using Autonomous System Flow Aggregates Thienne Johnson 1,2 and Loukas Lazos 1 1 Department of Electrical and Computer Engineering 2 Department of Computer Science University
Clustering and Dimensionality Reduction. Stony Brook University CSE545, Fall 2017
Clustering and Dimensionality Reduction Stony Brook University CSE545, Fall 2017 Goal: Generalize to new data Model New Data? Original Data Does the model accurately reflect new data? Supervised vs. Unsupervised
Performance Measures
1 Performance Measures Classification F-Measure: (careful: similar but not the same F-measure as the F-measure we saw for clustering!) Tradeoff between classifying correctly all datapoints of the same
For 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
Case-Based Reasoning. CS 188: Artificial Intelligence Fall Nearest-Neighbor Classification. Parametric / Non-parametric.
CS 188: Artificial Intelligence Fall 2008 Lecture 25: Kernels and Clustering 12/2/2008 Dan Klein UC Berkeley Case-Based Reasoning Similarity for classification Case-based reasoning Predict an instance
CS 188: Artificial Intelligence Fall 2008
CS 188: Artificial Intelligence Fall 2008 Lecture 25: Kernels and Clustering 12/2/2008 Dan Klein UC Berkeley 1 1 Case-Based Reasoning Similarity for classification Case-based reasoning Predict an instance
Classification of Face Images for Gender, Age, Facial Expression, and Identity 1
Proc. Int. Conf. on Artificial Neural Networks (ICANN 05), Warsaw, LNCS 3696, vol. I, pp. 569-574, Springer Verlag 2005 Classification of Face Images for Gender, Age, Facial Expression, and Identity 1
CS 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
3D Convolutional Neural Networks for Landing Zone Detection from LiDAR
3D Convolutional Neural Networks for Landing Zone Detection from LiDAR Daniel Mataruna and Sebastian Scherer Presented by: Sabin Kafle Outline Introduction Preliminaries Approach Volumetric Density Mapping
Introduction to ANSYS DesignXplorer
Lecture 4 14. 5 Release Introduction to ANSYS DesignXplorer 1 2013 ANSYS, Inc. September 27, 2013 s are functions of different nature where the output parameters are described in terms of the input parameters
Deep 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
Deep Predictive Coverage Collection
Deep Predictive Coverage Collection Rajarshi Roy Chinmay Duvedi Saad Godil Mark Williams rajarshir@nvidia.com cduvedi@nvidia.com sgodil@nvidia.com mwilliams@nvidia.com NVIDIA Corporation 2701 San Tomas
TRAFFIC SIGN CLASSIFICATION USING CONVOLUTIONAL NEURAL NETWORK
TRAFFIC SIGN CLASSIFICATION USING CONVOLUTIONAL NEURAL NETWORK Nemanja Veličković 1, Zeljko Stojković 2, Goran Dimić 2, Jelena Vasiljević 2 and Dhinaharan Nagamalai 3 1 University Union, School of Computing,
Advanced Introduction to Machine Learning, CMU-10715
Advanced Introduction to Machine Learning, CMU-10715 Deep Learning Barnabás Póczos, Sept 17 Credits Many of the pictures, results, and other materials are taken from: Ruslan Salakhutdinov Joshua Bengio
3D Computer Vision. Structured Light II. Prof. Didier Stricker. Kaiserlautern University.
3D Computer Vision Structured Light II Prof. Didier Stricker Kaiserlautern University http://ags.cs.uni-kl.de/ DFKI Deutsches Forschungszentrum für Künstliche Intelligenz http://av.dfki.de 1 Introduction
CSC 411 Lecture 18: Matrix Factorizations
CSC 411 Lecture 18: Matrix Factorizations Roger Grosse, Amir-massoud Farahmand, and Juan Carrasquilla University of Toronto UofT CSC 411: 18-Matrix Factorizations 1 / 27 Overview Recall PCA: project data
Lab 8 CSC 5930/ Computer Vision
Lab 8 CSC 5930/9010 - Computer Vision Description: One way to effectively train a neural network with multiple layers is by training one layer at a time. You can achieve this by training a special type
Applying Supervised Learning
Applying Supervised Learning When to Consider Supervised Learning A supervised learning algorithm takes a known set of input data (the training set) and known responses to the data (output), and trains
Neural 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
Event: PASS SQL Saturday - DC 2018 Presenter: Jon Tupitza, CTO Architect
Event: PASS SQL Saturday - DC 2018 Presenter: Jon Tupitza, CTO Architect BEOP.CTO.TP4 Owner: OCTO Revision: 0001 Approved by: JAT Effective: 08/30/2018 Buchanan & Edwards Proprietary: Printed copies of
Detecting Credential Spearphishing Attacks in Enterprise Settings
Detecting Credential Spearphishing Attacks in Enterprise Settings Grant Ho UC Berkeley Aashish Sharma, Mobin Javed, Vern Paxson, David Wagner 1 Spear Phishing Targeted email that tricks victim into giving
TGNet: Learning to Rank Nodes in Temporal Graphs. Qi Song 1 Bo Zong 2 Yinghui Wu 1,3 Lu-An Tang 2 Hui Zhang 2 Guofei Jiang 2 Haifeng Chen 2
TGNet: Learning to Rank Nodes in Temporal Graphs Qi Song 1 Bo Zong 2 Yinghui Wu 1,3 Lu-An Tang 2 Hui Zhang 2 Guofei Jiang 2 Haifeng Chen 2 1 2 3 Node Ranking in temporal graphs Temporal graphs have been
Machine Learning for User Behavior Anomaly Detection EUGENE NEYOLOV, HEAD OF R&D
Machine Learning for User Behavior Anomaly Detection EUGENE NEYOLOV, HEAD OF R&D 2 AUTHOR Eugene Neyolov HEAD OF R&D Security engineer and analyst leading applied research projects in security monitoring,
Deriving Network Traffic Signatures via Large Graphs
Deriving Network Traffic Signatures via Large Graphs hume@vt.edu www.hume.vt.edu Ahmed Abdelhadi (PI) Research Assistant Professor Outline Pattern of Life and IoT A Tractable Framework for POL Modeling
Machine Learning. Deep Learning. Eric Xing (and Pengtao Xie) , Fall Lecture 8, October 6, Eric CMU,
Machine Learning 10-701, Fall 2015 Deep Learning Eric Xing (and Pengtao Xie) Lecture 8, October 6, 2015 Eric Xing @ CMU, 2015 1 A perennial challenge in computer vision: feature engineering SIFT Spin image
Research Article International Journals of Advanced Research in Computer Science and Software Engineering ISSN: X (Volume-7, Issue-6)
International Journals of Advanced Research in Computer Science and Software Engineering Research Article June 17 Artificial Neural Network in Classification A Comparison Dr. J. Jegathesh Amalraj * Assistant
Deep Learning for Robust Normal Estimation in Unstructured Point Clouds. Alexandre Boulch. Renaud Marlet
Deep Learning for Robust Normal Estimation in Unstructured Point Clouds Alexandre Boulch Renaud Marlet Normal estimation in point clouds Normal: 3D normalized vector At each point: local orientation of
Artificial 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
Machine 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
A Dendrogram. Bioinformatics (Lec 17)
A Dendrogram 3/15/05 1 Hierarchical Clustering [Johnson, SC, 1967] Given n points in R d, compute the distance between every pair of points While (not done) Pick closest pair of points s i and s j and
Clustering and Unsupervised Anomaly Detection with l 2 Normalized Deep Auto-Encoder Representations
Clustering and Unsupervised Anomaly Detection with l 2 Normalized Deep Auto-Encoder Representations Caglar Aytekin, Xingyang Ni, Francesco Cricri and Emre Aksu Nokia Technologies, Tampere, Finland Corresponding
Deep-Q: Traffic-driven QoS Inference using Deep Generative Network
Deep-Q: Traffic-driven QoS Inference using Deep Generative Network Shihan Xiao, Dongdong He, Zhibo Gong Network Technology Lab, Huawei Technologies Co., Ltd., Beijing, China 1 Background What is a QoS
Perceptron: This is convolution!
Perceptron: This is convolution! v v v Shared weights v Filter = local perceptron. Also called kernel. By pooling responses at different locations, we gain robustness to the exact spatial location of image
COMPUTATIONAL 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
CSC321: Neural Networks. Lecture 13: Learning without a teacher: Autoencoders and Principal Components Analysis. Geoffrey Hinton
CSC321: Neural Networks Lecture 13: Learning without a teacher: Autoencoders and Principal Components Analysis Geoffrey Hinton Three problems with backpropagation Where does the supervision come from?
A Survey And Comparative Analysis Of Data
A Survey And Comparative Analysis Of Data Mining Techniques For Network Intrusion Detection Systems In Information Security, intrusion detection is the act of detecting actions that attempt to In 11th
Contents III. 1 Introduction 1
III Contents 1 Introduction 1 2 The Parametric Distributional Clustering Model 5 2.1 The Data Acquisition Process.................... 5 2.2 The Generative Model........................ 8 2.3 The Likelihood
Is Bigger CNN Better? Samer Hijazi on behalf of IPG CTO Group Embedded Neural Networks Summit (enns2016) San Jose Feb. 9th
Is Bigger CNN Better? Samer Hijazi on behalf of IPG CTO Group Embedded Neural Networks Summit (enns2016) San Jose Feb. 9th Today s Story Why does CNN matter to the embedded world? How to enable CNN in
Intro to Artificial Intelligence
Intro to Artificial Intelligence Ahmed Sallam { Lecture 5: Machine Learning ://. } ://.. 2 Review Probabilistic inference Enumeration Approximate inference 3 Today What is machine learning? Supervised
Machine 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
Pouya Kousha Fall 2018 CSE 5194 Prof. DK Panda
Pouya Kousha Fall 2018 CSE 5194 Prof. DK Panda 1 Observe novel applicability of DL techniques in Big Data Analytics. Applications of DL techniques for common Big Data Analytics problems. Semantic indexing
Deep neural networks II
Deep neural networks II May 31 st, 2018 Yong Jae Lee UC Davis Many slides from Rob Fergus, Svetlana Lazebnik, Jia-Bin Huang, Derek Hoiem, Adriana Kovashka, Why (convolutional) neural networks? State of
Study of Machine Learning Based Intrusion Detection System
ISSN 2395-1621 Study of Machine Learning Based Intrusion Detection System #1 Prashant Wakhare, #2 Dr S.T.Singh 1 Prashant_mitr@rediffmail.com 2 stsingh47@gmail.com Computer Engineering, Savitribai Phule
Learning video saliency from human gaze using candidate selection
Learning video saliency from human gaze using candidate selection Rudoy, Goldman, Shechtman, Zelnik-Manor CVPR 2013 Paper presentation by Ashish Bora Outline What is saliency? Image vs video Candidates
CPSC 340: Machine Learning and Data Mining. Deep Learning Fall 2018
CPSC 340: Machine Learning and Data Mining Deep Learning Fall 2018 Last Time: Multi-Dimensional Scaling Multi-dimensional scaling (MDS): Non-parametric visualization: directly optimize the z i locations.
Pattern 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
Compressive Parameter Estimation with Earth Mover s Distance via K-means Clustering. Dian Mo and Marco F. Duarte
Compressive Parameter Estimation with Earth Mover s Distance via K-means Clustering Dian Mo and Marco F. Duarte Compressive Sensing (CS) Integrates linear acquisition with dimensionality reduction linear
Data Compression. The Encoder and PCA
Data Compression The Encoder and PCA Neural network techniques have been shown useful in the area of data compression. In general, data compression can be lossless compression or lossy compression. In
INTRODUCTION 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
Convolutional Neural Networks
Lecturer: Barnabas Poczos Introduction to Machine Learning (Lecture Notes) Convolutional Neural Networks Disclaimer: These notes have not been subjected to the usual scrutiny reserved for formal publications.
ADVANCED MACHINE LEARNING MACHINE LEARNING. Kernel for Clustering kernel K-Means
1 MACHINE LEARNING Kernel for Clustering ernel K-Means Outline of Today s Lecture 1. Review principle and steps of K-Means algorithm. Derive ernel version of K-means 3. Exercise: Discuss the geometrical
Vulnerability of machine learning models to adversarial examples
Vulnerability of machine learning models to adversarial examples Petra Vidnerová Institute of Computer Science The Czech Academy of Sciences Hora Informaticae 1 Outline Introduction Works on adversarial
Neural 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
Clustering and Dimensionality Reduction
Clustering and Dimensionality Reduction Some material on these is slides borrowed from Andrew Moore's excellent machine learning tutorials located at: Data Mining Automatically extracting meaning from
AUTOMATIC PATTERN CLASSIFICATION BY UNSUPERVISED LEARNING USING DIMENSIONALITY REDUCTION OF DATA WITH MIRRORING NEURAL NETWORKS
AUTOMATIC PATTERN CLASSIFICATION BY UNSUPERVISED LEARNING USING DIMENSIONALITY REDUCTION OF DATA WITH MIRRORING NEURAL NETWORKS Name(s) Dasika Ratna Deepthi (1), G.R.Aditya Krishna (2) and K. Eswaran (3)
Machine Learning. Nonparametric methods for Classification. Eric Xing , Fall Lecture 2, September 12, 2016
Machine Learning 10-701, Fall 2016 Nonparametric methods for Classification Eric Xing Lecture 2, September 12, 2016 Reading: 1 Classification Representing data: Hypothesis (classifier) 2 Clustering 3 Supervised
Learning Social Graph Topologies using Generative Adversarial Neural Networks
Learning Social Graph Topologies using Generative Adversarial Neural Networks Sahar Tavakoli 1, Alireza Hajibagheri 1, and Gita Sukthankar 1 1 University of Central Florida, Orlando, Florida sahar@knights.ucf.edu,alireza@eecs.ucf.edu,gitars@eecs.ucf.edu
International Journal of Advance Engineering and Research Development SURVEY ON ARTIFICIAL INTELLIGENCE IN 5G
Scientific Journal of Impact Factor (SJIF): 5.71 e-issn (O): 2348-4470 p-issn (P): 2348-6406 International Journal of Advance Engineering and Research Development Volume 5, Issue 03, March -2018 SURVEY
Index. Springer Nature Switzerland AG 2019 B. Moons et al., Embedded Deep Learning,
Index A Algorithmic noise tolerance (ANT), 93 94 Application specific instruction set processors (ASIPs), 115 116 Approximate computing application level, 95 circuits-levels, 93 94 DAS and DVAS, 107 110
Dynamic load-balancing algorithm for a decentralized gpu-cpu cluster
Dynamic load-balancing algorithm for a decentralized gpu-cpu cluster Mert Değirmenci Department of Computer Engineering, Middle East Technical University Related work http://www2.computer.org/portal/web/csdl/doi/10.1109/icpads.2004.13161144
All You Want To Know About CNNs. Yukun Zhu
All You Want To Know About CNNs Yukun Zhu Deep Learning Deep Learning Image from http://imgur.com/ Deep Learning Image from http://imgur.com/ Deep Learning Image from http://imgur.com/ Deep Learning Image
Parallel Stochastic Gradient Descent
University of Montreal August 11th, 2007 CIAR Summer School - Toronto Stochastic Gradient Descent Cost to optimize: E z [C(θ, z)] with θ the parameters and z a training point. Stochastic gradient: θ t+1