Artificial Neural Networks By: Steve Kidos. Outline Artificial Neural Networks: An Introduction Frank Rosenblatt’s Perceptron Multi-layer Perceptron Dot.

Slides:



Advertisements
Similar presentations
1 Machine Learning: Lecture 4 Artificial Neural Networks (Based on Chapter 4 of Mitchell T.., Machine Learning, 1997)
Advertisements

1 Image Classification MSc Image Processing Assignment March 2003.
Artificial Neural Networks (1)
Perceptron Learning Rule
INTRODUCTION TO Machine Learning ETHEM ALPAYDIN © The MIT Press, Lecture Slides for.
Neural Network I Week 7 1. Team Homework Assignment #9 Read pp. 327 – 334 and the Week 7 slide. Design a neural network for XOR (Exclusive OR) Explore.
Machine Learning: Connectionist McCulloch-Pitts Neuron Perceptrons Multilayer Networks Support Vector Machines Feedback Networks Hopfield Networks.
Machine Learning Neural Networks
Brian Merrick CS498 Seminar.  Introduction to Neural Networks  Types of Neural Networks  Neural Networks with Pattern Recognition  Applications.
Artificial Intelligence (CS 461D)
Neural NetworksNN 11 Neural Networks Teacher: Elena Marchiori R4.47 Assistant: Kees Jong S2.22
Decision Support Systems
1 Chapter 11 Neural Networks. 2 Chapter 11 Contents (1) l Biological Neurons l Artificial Neurons l Perceptrons l Multilayer Neural Networks l Backpropagation.
Neural Networks Marco Loog.
Connectionist Modeling Some material taken from cspeech.ucd.ie/~connectionism and Rich & Knight, 1991.
An Illustrative Example
NEURAL NETWORKS Introduction
Artificial Neural Networks - Introduction -. Overview 1.Biological inspiration 2.Artificial neurons and neural networks 3.Application.
Artificial Neural Networks:
Soft Computing Colloquium 2 Selection of neural network, Hybrid neural networks.
MSE 2400 EaLiCaRA Spring 2015 Dr. Tom Way
Artificial Neural Networks (ANN). Output Y is 1 if at least two of the three inputs are equal to 1.
Artificial Neural Networks
Neural NetworksNN 11 Neural netwoks thanks to: Basics of neural network theory and practice for supervised and unsupervised.
1 Artificial Neural Networks Sanun Srisuk EECP0720 Expert Systems – Artificial Neural Networks.
 The most intelligent device - “Human Brain”.  The machine that revolutionized the whole world – “computer”.  Inefficiencies of the computer has lead.
Artificial Neural Networks An Overview and Analysis.
Introduction to Neural Networks Debrup Chakraborty Pattern Recognition and Machine Learning 2006.
Explorations in Neural Networks Tianhui Cai Period 3.
ANNs (Artificial Neural Networks). THE PERCEPTRON.
Waqas Haider Khan Bangyal. Multi-Layer Perceptron (MLP)
Chapter 3 Neural Network Xiu-jun GONG (Ph. D) School of Computer Science and Technology, Tianjin University
1 Machine Learning The Perceptron. 2 Heuristic Search Knowledge Based Systems (KBS) Genetic Algorithms (GAs)
NEURAL NETWORKS FOR DATA MINING
LINEAR CLASSIFICATION. Biological inspirations  Some numbers…  The human brain contains about 10 billion nerve cells ( neurons )  Each neuron is connected.
Presented by Scott Lichtor An Introduction to Neural Networks.
Artificial Neural Networks. The Brain How do brains work? How do human brains differ from that of other animals? Can we base models of artificial intelligence.
1 Chapter 11 Neural Networks. 2 Chapter 11 Contents (1) l Biological Neurons l Artificial Neurons l Perceptrons l Multilayer Neural Networks l Backpropagation.
Artificial Neural Networks An Introduction. What is a Neural Network? A human Brain A porpoise brain The brain in a living creature A computer program.
Feed-Forward Neural Networks 主講人 : 虞台文. Content Introduction Single-Layer Perceptron Networks Learning Rules for Single-Layer Perceptron Networks – Perceptron.
Artificial Neural Network Building Using WEKA Software
Back-Propagation Algorithm AN INTRODUCTION TO LEARNING INTERNAL REPRESENTATIONS BY ERROR PROPAGATION Presented by: Kunal Parmar UHID:
CITS7212: Computational Intelligence An Overview of Core CI Technologies Lyndon While.
Introduction to Neural Networks Introduction to Neural Networks Applied to OCR and Speech Recognition An actual neuron A crude model of a neuron Computational.
Lecture 5 Neural Control
Neural Networks Presented by M. Abbasi Course lecturer: Dr.Tohidkhah.
Neural Networks Teacher: Elena Marchiori R4.47 Assistant: Kees Jong S2.22
Dr.Abeer Mahmoud ARTIFICIAL INTELLIGENCE (CS 461D) Dr. Abeer Mahmoud Computer science Department Princess Nora University Faculty of Computer & Information.
Chapter 8: Adaptive Networks
Hazırlayan NEURAL NETWORKS Backpropagation Network PROF. DR. YUSUF OYSAL.
NEURAL NETWORKS LECTURE 1 dr Zoran Ševarac FON, 2015.
Artificial Neural Networks (ANN). Artificial Neural Networks First proposed in 1940s as an attempt to simulate the human brain’s cognitive learning processes.
Perceptrons Michael J. Watts
Artificial Intelligence CIS 342 The College of Saint Rose David Goldschmidt, Ph.D.
Chapter 6 Neural Network.
Lecture 12. Outline of Rule-Based Classification 1. Overview of ANN 2. Basic Feedforward ANN 3. Linear Perceptron Algorithm 4. Nonlinear and Multilayer.
1 Neural Networks MUMT 611 Philippe Zaborowski April 2005.
INTRODUCTION TO NEURAL NETWORKS 2 A new sort of computer What are (everyday) computer systems good at... and not so good at? Good at..Not so good at..
Business Intelligence and Decision Support Systems (9 th Ed., Prentice Hall) Chapter 6: Artificial Neural Networks for Data Mining.
Artificial neural networks
Learning in Neural Networks
Joost N. Kok Universiteit Leiden
What is an ANN ? The inventor of the first neuro computer, Dr. Robert defines a neural network as,A human brain like system consisting of a large number.
Artificial Neural Networks
Intelligent Leaning -- A Brief Introduction to Artificial Neural Networks Chiung-Yao Fang.
Intelligent Leaning -- A Brief Introduction to Artificial Neural Networks Chiung-Yao Fang.
Face Recognition with Neural Networks
network of simple neuron-like computing elements
Lecture Notes for Chapter 4 Artificial Neural Networks
Sanguthevar Rajasekaran University of Connecticut
Presentation transcript:

Artificial Neural Networks By: Steve Kidos

Outline Artificial Neural Networks: An Introduction Frank Rosenblatt’s Perceptron Multi-layer Perceptron Dot Example Learning and Cost Functions Learning Paradigms Implementations Applications Google Example

Artificial Neural Networks: An Introduction Artificial Neural Networks are modeled after the biological brain Consists of interconnected nodes, or “neurons” Uses parallel, nonlinear processing Neural networks are adaptive and experience-based Most importantly, a learning system

Frank Rosenblatt’s Perceptron In 1957 Frank Rosenblatt designed and implemented the first neural network, a single-layer perceptron Each input neuron is connected to every output neuron with each connection having a weight Learning is accomplished through modifying connection weights

Multi-layer Perceptrons Single-layer Perceptrons have limited functionality, a point Marvin Minsky drove home within the AI community Multi-layer Perceptrons are much more robust and are able to perform functions a single-layer perceptron cannot Allows for a much greater degree of complexity, allowing the network to deal with more complex problems

Dot Example 1 st Generation No training Essentially random behavior Sometimes they get lucky 100 th Generation Successful at finding white dot Very efficient

Learning and Cost Functions In the Dot example, there are a limited number of white dots per generation. This represents the cost. Each neural network has an associated cost, where the more white dots consumed, the less cost they have Dots with least cost survive to next generation “Mutated” dots are created from fit dots and have slightly different weights Learning is accomplished through mutations and cost (genetic algorithm)

Learning Paradigms Supervised learning, or “learning with a teacher”, uses pre-defined sets of input-output and corrects the network based on it’s output Reinforcement learning generates a cost associated with the network’s actions. The network learns by trying to minimize cost. Differs from supervised in that there is no explicit “expected” output. Dot example used this Unsupervised learning is generally self-organizing and only very specific networks use this method. It doesn’t have a teacher or reinforcement. It seeks to find structure in unlabeled data

Implementations of Neural Networks Multi-layer Feedforward Perceptron Self-Organizing Map Recurrent Networks Modular Neural Networks

Applications Function Approximation and Regression Pattern Recognition and Classification Robotics (controlling movement) NLP

Google’s Neural Network Used for visual classification Required 16,000 processors over 1,000 computers to process 10,000,000 images grabbed from YouTube Originally used to recognize cats, now being used to recognize speech, faces, and associate related text and images Visual classification outperforms humans in some instances

End

Sources l4/cs11/report.htmlhttp:// l4/cs11/report.html oogle-puts-its-virtual-brain-technology-to-work/ oogle-puts-its-virtual-brain-technology-to-work/