dlp driven, learning, optical neural networks
DESCRIPTION
DLP Driven, Learning, Optical Neural Networks. Emmett Redd & A. Steven Younger Associate Professor Missouri State University [email protected]. Neural Network Applications. Stock Prediction: Currency, Bonds, S&P 500, Natural Gas - PowerPoint PPT PresentationTRANSCRIPT
![Page 1: DLP Driven, Learning, Optical Neural Networks](https://reader036.vdocument.in/reader036/viewer/2022062308/56812eb0550346895d9455b5/html5/thumbnails/1.jpg)
01001000100001001000100000110000001000001100
DLP Driven, Learning, Optical Neural Networks
Emmett Redd &
A. Steven Younger
Associate Professor
Missouri State [email protected]
![Page 2: DLP Driven, Learning, Optical Neural Networks](https://reader036.vdocument.in/reader036/viewer/2022062308/56812eb0550346895d9455b5/html5/thumbnails/2.jpg)
2
Neural Network Applications
Stock Prediction: Currency, Bonds, S&P 500, Natural Gas
Business: Direct mail, Credit Scoring, Appraisal, Summoning Juries
Medical: Breast Cancer, Heart Attack Diagnosis, ER Test Ordering
Sports: Horse and Dog Racing
Science: Solar Flares, Protein Sequencing, Mosquito ID, Weather
Manufacturing: Welding Quality, Plastics or Concrete Testing
Pattern Recognition: Speech, Article Class., Chem. Drawings
No Optical Applications—We are starting with Boolean
most from www.calsci.com/Applications.html
![Page 3: DLP Driven, Learning, Optical Neural Networks](https://reader036.vdocument.in/reader036/viewer/2022062308/56812eb0550346895d9455b5/html5/thumbnails/3.jpg)
3
Optical Computing & Neural Networks
Optical Parallel Processing Gives SpeedLenslet’s Enlight 256—8 Giga Multiply and
Accumulate per secondOrder 1011 connections per second possible with
holographic attenuators
Neural NetworksParallel versus SerialLearn versus ProgramSolutions beyond ProgrammingDeal with Ambiguous InputsSolve Non-Linear problemsThinking versus Constrained Results
![Page 4: DLP Driven, Learning, Optical Neural Networks](https://reader036.vdocument.in/reader036/viewer/2022062308/56812eb0550346895d9455b5/html5/thumbnails/4.jpg)
4
Optical Neural Networks
Sources are modulated light beams (pulse or amplitude)
Synaptic Multiplications are due to attenuation of light passing through an optical medium
Geometric or Holographic Target neurons sum signals from many source
neurons. Squashing by operational-amps or nonlinear
optics
![Page 5: DLP Driven, Learning, Optical Neural Networks](https://reader036.vdocument.in/reader036/viewer/2022062308/56812eb0550346895d9455b5/html5/thumbnails/5.jpg)
5
Standard Neural Net Learning We use a Training or Learning algorithm to adjust
the weights, usually in an iterative manner.
… x1
xN
y1
…yM
…
Learning Algorithm
Target Output (T) Other Info
![Page 6: DLP Driven, Learning, Optical Neural Networks](https://reader036.vdocument.in/reader036/viewer/2022062308/56812eb0550346895d9455b5/html5/thumbnails/6.jpg)
6
FWL-NN is equivalent to a standard Neural Network + Learning Algorithm
FWL-NN
+Learning Algorithm
![Page 7: DLP Driven, Learning, Optical Neural Networks](https://reader036.vdocument.in/reader036/viewer/2022062308/56812eb0550346895d9455b5/html5/thumbnails/7.jpg)
7
Optical Recurrent Neural Network
Squashing Functions
Synaptic Medium(35mm Slide)
Target Neuron Summation
Signal Source (Layer Input)
Layer OutputA Single Layer of an Optical Recurrent Neural Network. Only four synapses are shown. Actual networks will have a large number of synapses. A multi-layer network has several consecutive layers.
Micromirror Array
PresynapticOptics
Postsynaptic Optics
Recurrent Connections
![Page 8: DLP Driven, Learning, Optical Neural Networks](https://reader036.vdocument.in/reader036/viewer/2022062308/56812eb0550346895d9455b5/html5/thumbnails/8.jpg)
8
Optical Fixed-Weight Learning Synapse
W(t-1)
x(t)
Σ
x(t-1)
T(t-1)
Planapse
Tranapse
y(t-1)
![Page 9: DLP Driven, Learning, Optical Neural Networks](https://reader036.vdocument.in/reader036/viewer/2022062308/56812eb0550346895d9455b5/html5/thumbnails/9.jpg)
9
Definitions
Fixed-Weight Learning Neural Network (FWL-NN) – A recurrent network that learns without changing synaptic weights
Potency – A weight signal Tranapse – A Potency modulated synapse Planapse – Supplies Potency error signal Recurron – A recurrent neuron Recurral Network – A network of Recurrons
![Page 10: DLP Driven, Learning, Optical Neural Networks](https://reader036.vdocument.in/reader036/viewer/2022062308/56812eb0550346895d9455b5/html5/thumbnails/10.jpg)
10
Page Representation of a Recurron
Tranapse
Planapse
Tranapse
Tranapse
U(t-1)
A(t)
B(t)
Bias
O(t-1)Σ
![Page 11: DLP Driven, Learning, Optical Neural Networks](https://reader036.vdocument.in/reader036/viewer/2022062308/56812eb0550346895d9455b5/html5/thumbnails/11.jpg)
11
Optical Neural Network Constraints
Finite Range Unipolar Signals [0,+1] Finite Range Bipolar Attenuation[-1,+1] Excitatory/Inhibitory handled separately Limited Resolution Signal Limited Resolution Synaptic Weights Alignment and Calibration Issues
![Page 12: DLP Driven, Learning, Optical Neural Networks](https://reader036.vdocument.in/reader036/viewer/2022062308/56812eb0550346895d9455b5/html5/thumbnails/12.jpg)
12
Proposed Design
Digital Micromirror Device 35 mm slide Synaptic Media CCD Camera Synaptic Weights - Positionally Encoded
- Digital Attenuation Planapse, Tranapse trained using Standard
Backpropagation Allows flexibility for evaluation.
![Page 13: DLP Driven, Learning, Optical Neural Networks](https://reader036.vdocument.in/reader036/viewer/2022062308/56812eb0550346895d9455b5/html5/thumbnails/13.jpg)
13
Generation, Acquisition, Processing
DemonstrationLeft Images (time order)
• Gray-scale Source Neuron Signal• Equivalent Pulse Modulated Source Neuron Signal• Gray-scale Source Neuron Signal – Reprise• Blank during Target Summation and Squashing
Middle Image – Fixed Weights on Attenuator Slide (static)
Right Images (time order)• Blank during First Source Gray-scale• Accumulating (Integrating Pulses) Target Neuron Input• Gray-scale during Summation and Squashing
Phases and Layers• Synapses Connect Two Layers (N and N+1)• Only Source Neurons (layer N) Illuminate• Only Target Neurons (layer N+1) Accumulate
![Page 14: DLP Driven, Learning, Optical Neural Networks](https://reader036.vdocument.in/reader036/viewer/2022062308/56812eb0550346895d9455b5/html5/thumbnails/14.jpg)
14
Hard and Soft Optical Alignment
Hardware AlignmentBest for Gross AlignmentPrecision Stages Required for Precise AlignmentHard to Correct for Distortions in Optics
Software AlignmentFine Image Displacements Image Rotation Integrating Regions of Arbitrary Shape and SizeDiffraction Effects Filtered and IgnoredCorrect for Optical Path Changes
![Page 15: DLP Driven, Learning, Optical Neural Networks](https://reader036.vdocument.in/reader036/viewer/2022062308/56812eb0550346895d9455b5/html5/thumbnails/15.jpg)
15
Photonic Circuit Elements
NEAROptical FiberFiber AmplifiersSplitters
MEDIUMCylindrical Lenses before and after Synaptic
Media (1-D systems, sparse media)Non-Linear Crystals for Squashing
FAR Integrated Emitters, Attenuator, Detectors/LimitersHolographic Attenuators (destructive interference)Stackable
![Page 16: DLP Driven, Learning, Optical Neural Networks](https://reader036.vdocument.in/reader036/viewer/2022062308/56812eb0550346895d9455b5/html5/thumbnails/16.jpg)
16
DLP Driven, Learning, Optical Neural Networks
Emmett Redd and A. Steven Younger
Associate ProfessorMissouri State [email protected]
This material is based upon work supported by the National Science Foundation under Grant No. 0446660.