Neural Network and Deep Learning 王强昌 2015-11-24 MLA lab.

Slides:



Advertisements
Similar presentations
A Brief Overview of Neural Networks By Rohit Dua, Samuel A. Mulder, Steve E. Watkins, and Donald C. Wunsch.
Advertisements

Slides from: Doug Gray, David Poole
NEURAL NETWORKS Backpropagation Algorithm
Machine Learning Neural Networks
Lecture 14 – Neural Networks
Artificial Neural Networks ECE 398BD Instructor: Shobha Vasudevan.
S. Mandayam/ ANN/ECE Dept./Rowan University Artificial Neural Networks / Fall 2004 Shreekanth Mandayam ECE Department Rowan University.
Prénom Nom Document Analysis: Artificial Neural Networks Prof. Rolf Ingold, University of Fribourg Master course, spring semester 2008.
1 Chapter 11 Neural Networks. 2 Chapter 11 Contents (1) l Biological Neurons l Artificial Neurons l Perceptrons l Multilayer Neural Networks l Backpropagation.
Prénom Nom Document Analysis: Artificial Neural Networks Prof. Rolf Ingold, University of Fribourg Master course, spring semester 2008.
Machine Learning Motivation for machine learning How to set up a problem How to design a learner Introduce one class of learners (ANN) –Perceptrons –Feed-forward.
Data Mining with Neural Networks (HK: Chapter 7.5)
-Artificial Neural Network- Chapter 5 Back Propagation Network
CS 484 – Artificial Intelligence
Image Compression Using Neural Networks Vishal Agrawal (Y6541) Nandan Dubey (Y6279)
Neural Networks. Background - Neural Networks can be : Biological - Biological models Artificial - Artificial models - Desire to produce artificial systems.
Radial-Basis Function Networks
Traffic Sign Recognition Using Artificial Neural Network Radi Bekker
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.
Multiple-Layer Networks and Backpropagation Algorithms
Artificial Neural Networks
Artificial Neural Nets and AI Connectionism Sub symbolic reasoning.
Neural Networks AI – Week 23 Sub-symbolic AI Multi-Layer Neural Networks Lee McCluskey, room 3/10
Introduction to Artificial Neural Network Models Angshuman Saha Image Source: ww.physiol.ucl.ac.uk/fedwards/ ca1%20neuron.jpg.
Machine Learning Dr. Shazzad Hosain Department of EECS North South Universtiy
NEURAL NETWORKS FOR DATA MINING
Classification / Regression Neural Networks 2
LINEAR CLASSIFICATION. Biological inspirations  Some numbers…  The human brain contains about 10 billion nerve cells ( neurons )  Each neuron is connected.
Artificial Intelligence Techniques Multilayer Perceptrons.
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.
Akram Bitar and Larry Manevitz Department of Computer Science
Back-Propagation Algorithm AN INTRODUCTION TO LEARNING INTERNAL REPRESENTATIONS BY ERROR PROPAGATION Presented by: Kunal Parmar UHID:
CS621 : Artificial Intelligence
Neural Networks Presented by M. Abbasi Course lecturer: Dr.Tohidkhah.
Neural Networks Teacher: Elena Marchiori R4.47 Assistant: Kees Jong S2.22
Image Source: ww.physiol.ucl.ac.uk/fedwards/ ca1%20neuron.jpg
EEE502 Pattern Recognition
Chapter 8: Adaptive Networks
Hazırlayan NEURAL NETWORKS Backpropagation Network PROF. DR. YUSUF OYSAL.
Neural Networks Vladimir Pleskonjić 3188/ /20 Vladimir Pleskonjić General Feedforward neural networks Inputs are numeric features Outputs are in.
Neural Networks 2nd Edition Simon Haykin
Artificial Intelligence CIS 342 The College of Saint Rose David Goldschmidt, Ph.D.
Bab 5 Classification: Alternative Techniques Part 4 Artificial Neural Networks Based Classifer.
Neural Networks Lecture 11: Learning in recurrent networks Geoffrey Hinton.
Kim HS Introduction considering that the amount of MRI data to analyze in present-day clinical trials is often on the order of hundreds or.
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
Deep Learning Overview Sources: workshop-tutorial-final.pdf
Machine Learning Artificial Neural Networks MPλ ∀ Stergiou Theodoros 1.
Chapter 11 – Neural Nets © Galit Shmueli and Peter Bruce 2010 Data Mining for Business Intelligence Shmueli, Patel & Bruce.
Learning: Neural Networks Artificial Intelligence CMSC February 3, 2005.
Learning with Neural Networks Artificial Intelligence CMSC February 19, 2002.
CSE343/543 Machine Learning Mayank Vatsa Lecture slides are prepared using several teaching resources and no authorship is claimed for any slides.
Multiple-Layer Networks and Backpropagation Algorithms
Deep Learning Amin Sobhani.
with Daniel L. Silver, Ph.D. Christian Frey, BBA April 11-12, 2017
CSE P573 Applications of Artificial Intelligence Neural Networks
Prof. Carolina Ruiz Department of Computer Science
Example: Voice Recognition
Artificial Neural Network & Backpropagation Algorithm
Artificial Neural Networks
CSE 573 Introduction to Artificial Intelligence Neural Networks
network of simple neuron-like computing elements
Artificial Neural Networks
Neural Network - 2 Mayank Vatsa
Neural Networks Geoff Hulten.
Artificial Neural Networks
PYTHON Deep Learning Prof. Muhammad Saeed.
Prof. Carolina Ruiz Department of Computer Science
Presentation transcript:

Neural Network and Deep Learning 王强昌 MLA lab

Neural Network and Deep Learning  Artificial Neural Network  Why we go deep?  Amazing achievement  Deep learning-getting started

Artificial Neural Network  How do ANNs work?  Feed-forward process  About Weights Gradient Descent Back-propagation process  Summaries

 Artificial Neural Network (ANN) is a technique for solving problems by constructing software that works like our brains.

 Our brains are a huge network of processing elements. A typical brain contains a network of 10 billion neurons.

An artificial neuron is an imitation of a human neuron

 Now, let us have a look at the model of an artificial neuron.

Transfer Function (Activation Function) Output x1x1 x2x2 xmxm ∑ y Neuron Input w1w1 w2w2 wmwm Weights f(v k ).....

 An example Sum : (1  0.25) + (0.5  (-1.5)) = (-0.75) = Transfer function : if we get then

 Transfer (Activation, Squash) function: Limits node output; enhances Non-linearity. For the function below, we limit the output in the range [0,1]. An example:

Artificial Neural Network  How do ANNs work?  Feed-forward process  About Weights Gradient Descent Back-propagation process  Summaries

Feed-forward process  Information flow is unidirectional Data is presented to input layer  Data example Pixel intensity (for image classification). Share prices (for stock market prediction ). Passed on to hidden Layer Passed on to output layer Hidden layer: internal representation (interpretation) of data. Layer

Picture below illustrates how data is propagated through the network.  w (xm)n represent weights of connections between network input x m and neuron n in next layer.  y n represents output of neuron n. Input layerHidden layer Output layer

Input layerHidden layer Output layer

Propagation of data through the hidden layer. w mn represent weights of connections between neuron m and neuron n in the next layer. Output layer Hidden layer Input layer

Propagation of data through the output layer. Input layerHidden layer Output layer

Artificial Neural Network  How do ANNs work?  Feed-forward process  About Weights Gradient Descent Back-propagation process  Summaries

About Weights  Weights w settings determine the behaviour of a network  How can we find the right weights ?

Example: Voice Recognition  Task: Learn to discriminate between two different voices saying “Hello”  Data  Sources Steve David  Input data Frequency distribution (60 bins)

 Network architecture  Feed forward network (predefined) 60 input units (one for every frequency bin) 6 hidden units 2 output units (0-1 for “Steve”, 1-0 for “David”)

 Presenting the data Steve David

 Presenting the data (untrained network) Steve David

 Calculate error (suppose the error function is absolute value function) Steve:0-1 |0.43 – 0| = 0.43 |0.57 – 1| = 0.43 David:1-0 |0.7 – 1| = 0.3 |0.3 – 0| = 0.3

 Backprop error and adjust weights (just the last hidden layer) Steve |0.43 – 0| = 0.43 |0.57 – 1| = 0.43 David |0.7 – 1| = 0.3 |0.3 – 0| = 0.3 How do we adjust the weights ? weights

Artificial Neural Network  How do ANNs work?  Feed-forward process  About Weights Gradient Descent Back-propagation process  Summaries

Gradient Descent  Think of (w 0,w 1,…,w n-1 ) as a point in an n-dimensional space.  Suppose the error function is E(w 0,w 1,…,w n-1 ).  Try to minimize error E(w 0,w 1,…,w n-1 ) by changing the point position on the “error surface”.

 How do we change w i ? Change i-th weight by η w i = η*   : direction of going down.   η: length of going down, a constant. w i (new)=w i (old)+ w i

 Repeat the procedure above, we can finally get the minimum. But we need to compute derivative first ! Grad E =[,, …, ]

Artificial Neural Network  How do ANNs work?  Feed-forward process  About Weights Gradient Descent Back-propagation process  Summaries

Back-propagation process  the output of the network y is compared with the desired output z (the target), compute the error, suppose we get error function

 The idea is to propagate error back to all neurons.  The weights' coefficients w mn used to propagate errors back are equal to this used during feed-forward process.  The direction of data flow is changed (signals are propagated from output to inputs one after the other). depends on what function f(e) is. if f(e)=e, then 链式求导 w 56

 If propagated errors came from few neurons they are added. The illustration is below: w 46 链式求导 depends on what function f(e) is. if f(e)=e, then w 24 w 34

 Continue to propagate the error, we can modify the weights for the inputs nodes:

Artificial Neural Network  How do ANNs work?  Feed-forward process  About Weights Gradient Descent Back-propagation process  Summaries

Summaries  1. Initialize network with random weights.  2. For all training cases, repeat:  a. Feed-forward process: present training inputs to network and calculate output.  b.  b. Back-propagation process: for all layers (starting with output layer, back to input layer): Computes the error term for the output units using the observed error. From output layer, repeat - propagating the error term back to the previous layer - updating the weights between the two layers until the earliest hidden layer is reached.

Neural Network and Deep Learning  Artificial Neural Network  Why we go deep?  Amazing achievement  Deep learning-getting started

Why we go deep?  Learning multiple levels of representation

 Learning Non-Linear Features

 Learning features, not just handcrafting them. Most ML systems use very carefully hand-designed features and representations. So, many practitioners are very experienced – and good at such feature design (or kernel design). Hand-crafting features are brittle, incomplete.

 Highly varying functions can be efficiently represented with deep architectures.  Problems which can be represented with a polynomial number of nodes with k layers, may require an exponential number of nodes with k-1 layers.

Neural Network and Deep Learning  Artificial Neural Network  Why we go deep?  Amazing achievement  Deep learning-getting started

Amazing achievement on ImageNet classification  Database: part of ImageNet database, 1000 categories, 1.2 million training images, 150,000 testing images.  Task: classify testing image into one of 1000 categories.  Examples of two categories needed to be differentiated: Differentiate 波斯猫 布偶猫

Machine is as good as human !!! A New Era Begins: Deep Convolutional Neural Network (DCNN)

Neural Network and Deep Learning  Artificial Neural Network  Why we go deep?  Amazing achievement  Deep learning-getting started

Deep learning-getting started  了解一些 deep learning 基本方法的思想  教程 deep learning 大牛 Andrew Ng 所写 ,还 有 实验、 源代 码, 推 荐 细读

Thank You!