What I Did On My Summer Vacation: Undergraduate Research Internships, Neural Networks, - PowerPoint PPT Presentation

Loading...

PPT – What I Did On My Summer Vacation: Undergraduate Research Internships, Neural Networks, PowerPoint presentation | free to download - id: 7c4a0e-YzM0Y



Loading


The Adobe Flash plugin is needed to view this content

Get the plugin now

View by Category
About This Presentation
Title:

What I Did On My Summer Vacation: Undergraduate Research Internships, Neural Networks,

Description:

J. McLean Sloughter What I Did On My Summer Vacation: Undergraduate Research Internships, Neural Networks, & Airport Security Soon after the electrical current ... – PowerPoint PPT presentation

Number of Views:129
Avg rating:3.0/5.0
Slides: 27
Provided by: mcle99
Category:

less

Write a Comment
User Comments (0)
Transcript and Presenter's Notes

Title: What I Did On My Summer Vacation: Undergraduate Research Internships, Neural Networks,


1
What I Did On My Summer Vacation Undergraduate
Research Internships, Neural Networks, Airport
Security
  • J. McLean Sloughter

Soon after the electrical current became known
many attempts were made by the older
physiologists to explain nervous impulses in
terms of electricity. The analogy between the
nerves of the body and a system of telephone or
telegraph wires was too striking to be
overlooked. (from Studies in Advanced
Physiology, Louis J. Rettger, A.M., 1898, p. 443)
2
An Extremely Over-Simplified Explanation
  • The brain is made up of interconnected neurons
  • Neurons are binary either fire or dont fire
  • As a neuron receives signals from other neurons,
    it will start firing if the total signal reaches
    some threshhold

How the Brain Works
3
How the Brain Works
4
Just like that, except way more complicated
  • Actually a lot more neurons involved
  • Frequency of firing is also important
  • But lets ignore those details for now

How the Brain Works
5
Putting a philosophy degree to work
  • Warren McCulloch, a psychologist and philosopher,
    postulated that thought is discrete
  • Suggested a psychon the smallest unit of
    thought
  • Thought that an individual neuron firing or not
    firing might be a psychon
  • Recommended developing a calculus of ideas to
    describe neural activity

History 1940s
6
Philosophy Math Fame
  • McCulloch teamed up with Walter Pitts, a math
    prodigy
  • Together they published A Logical Calculus of
    the Ideas Immanent in Nervous Activity
  • This paper introduced the idea of a nervous
    network, the first artificial neural model of
    cognition

History 1940s
7
Enter von Neumann
  • Von Neumann became an early proponent of their
    work
  • However, he criticized it as being overly
    simplistic
  • Based on some of von Neumanns suggestions,
    McCulloch Pitts proposed a system using a large
    number of neurons
  • This allows for robustness an ability, for
    example, to recognize a slightly deformed square
    as still being essentially a square

History 1940s
8
Best Mathematician Name Ever
  • Norbert Weiner (The Father of Cybernetics)
    proposed a more involved system
  • Weighted inputs one neuron can be more
    influential than another
  • Memory learning weights
  • Did not propose how this learning takes place,
    dismissed that as a problem for engineers to deal
    with

History 1940s
9
In which not a whole lot happened
  • Marvin Minsky introduced a system based on
    behavioural conditioning
  • Neurons had probabilities of sending signals
  • When they produced the correct output,
    probabilities were increased
  • When the produced the wrong output, probabilities
    were decreased
  • And nobody really seemed to care (they were all
    busy becoming computer programmers)

History 1950s
10
Perceptrons
  • In 1960, Rosenblatt published a proof of the
    capabilities of what he named the perceptron
  • The perceptron acted much like the nervous
    network, but with weighted signals
  • The major advance was a learning algorithm
  • Rosenblatt was able to prove that, using his
    learning algorithm, any possible configuration of
    the perceptron could be learned, given the proper
    training data

History 1960s
11
Perceptron function
  • Consider a simple case where nodes A and B are
    each sending signals to node B
  • Node B has some threshold, T, which it needs to
    receive to be activated
  • A, B, and C are all binary 0 or 1
  • W1 and W2 are the weights between A and C and B
    and C
  • Then, if AW1 BW2 gt T, C 1
  • Otherwise, C 0

History 1960s
12
Perceptron learning
  • Initialize weights randomly
  • Set threshold to some arbitrary value (why does
    it not matter what value the threshold is set
    to?)
  • Randomly select one set of inputs
  • Find the result based on current weights
  • Subtract result from desired result error term
  • Look at each initial node individually
  • Multiply input value by error term by learning
    coefficient (between 0 and 1, controls amount of
    change youll allow at each iteration)
  • Add result to weight previously associated with
    that node to get a new weight
  • Pick a new set of inputs, repeat until convergence

History 1960s
13
Adaline
  • Widrow and Hoff created a system called Adaline
    Adaptive linear element
  • Very similar to perceptrons (though with a
    slightly different learning algorithm)
  • Major changes were the use of -1 instead of 0 for
    no signal, and a bias term a node that always
    fires
  • These were significant because they had no basis
    in neurophysiology, and were added purely because
    they could improve performance

History 1960s
14
The Wrath of Minksy
  • In 1969, Minsky again entered the world of neural
    networks, this time co-authoring the book
    Perceptrons with Seymour Papert

History 1960s
15
Xor
  • Minsky and Papert showed, among other critiques
    of perceptrons, that they werent capable of
    learning an exclusive OR (can you see why?)
  • An exclusive OR could be made by combining
    multiple other networks have A and B feed into
    both an OR and a NAND, and then AND the results
  • But learning rules only worked with a single
    layer network Minskey and Papert suggested
    researching whether learning rules could be
    developed for multi-layered networks

History 1960s
16
The Problem
  • Minsky Papert put their critique of perceptrons
    at the front of the book
  • They put their suggestions for research into
    multi-layered perceptrons at the back of the
    book, after a few hundred pages of rather dense
    math
  • People didnt seem to read that far
  • Research on perceptrons died

History 1960s
17
Nothing important happened
History 1970s
18
The Multi-Layer Perceptron
  • Rumelhart, Hinton, and Williams created a
    learning algorithm for multi-layer perceptrons
  • Requires differentiation of functions, and thus
    the hard threshold had to be replaced by a
    sigmoid function

History 1980s
19
MLP function
  • Net input to a node
  • Output from a node

History 1980s
20
MLP learning
  • Change weight as follows
  • Where b is the learning coefficient, and E is
    the error term
  • where

History 1980s
21
The Problem
  • Metal detectors only detect things that are,
    well, metal (and even then only sometimes)
  • Lots of bad things arent metal plastic
    explosives, ceramic guns, plastic flare guns
  • An x-ray could potentially see these objects, but
    submitting people to x-rays every time they fly
    isnt an especially good idea

Airport Security
22
The Solution
  • Scientists at Pacific Northwest National
    Laboratory developed a millimeter wave camera
  • Millimeter waves are not harmful like x-rays
  • They can penetrate clothing, but are reflected by
    skin
  • Plastics and ceramics show up with a distinctive
    speckled pattern, as they only partially reflect
    the waves

Airport Security
23
The New Problem Caused by the Solution
  • Scientists at a government lab just made a camera
    that can take pictures of you through your
    clothes
  • Implementing this in airports would have every
    passenger go through a virtual strip-search

Airport Security
24
The Solution to the Problem Caused by the
Solution to the Other Problem
  • Rather than have a human operator look at the
    pictures, we can have a computer look at them for
    us
  • The computer can identify suspicious areas and
    provide a non-naughty picture to the security
    officer

Airport Security
25
In Practice
  • This technology is now in use by SafeView, a
    company spun off from this project
  • It is being used in airports, government
    buildings, border crossings, and other locations
    around the world

Airport Security
26
Student Research Opportunities
  • I was involved in this project while a student
    intern at Pacific Northwest National Lab
  • Information about PNNLs student internship
    programs can be found online at
    http//science-ed.pnl.gov/students/
  • One of my summers on this project, I applied
    through the Department of Energys internship
    program, which includes opportunities at a number
    of other national labs
  • Information on DOE internship programs is
    available at http//www.scied.science.doe.gov/scie
    d/erulf/about.html

Research Internship
About PowerShow.com