Computational Modeling of Neural Networks and Memory Simulation

18
Overview: Background Inspirations Biology and Neuroscience Computer Modeling Project Design and Coding Successes and Challenges Central Question: Can we model a human brain? Computational Modeling of Neural Networks and Memory Simulation NJ Governor’s School for the Sciences Team Project T7 Dr. Minjoon Kouh Aaron Loether Alex Sonal Carl Ashwin Rebecca Shreyas Madhu Seth Jeff James Jonatha n

description

Computational Modeling of Neural Networks and Memory Simulation. Alex Sonal Carl Ashwin Rebecca Shreyas Madhu Seth Jeff James Jonathan . Overview: Background Inspirations Biology and Neuroscience Computer Modeling Project Design and Coding Successes and Challenges - PowerPoint PPT Presentation

Transcript of Computational Modeling of Neural Networks and Memory Simulation

Page 1: Computational Modeling of Neural Networks and Memory Simulation

Overview:•Background• Inspirations• Biology and Neuroscience• Computer Modeling

•Project• Design and Coding• Successes and Challenges

•Central Question: Can we model a human brain?

Computational Modeling of Neural Networks and Memory Simulation

NJ Governor’s School for the SciencesTeam Project T7Dr. Minjoon KouhAaron Loether

AlexSonalCarlAshwinRebeccaShreyas

MadhuSethJeffJamesJonathan

Page 2: Computational Modeling of Neural Networks and Memory Simulation

Current State of Neuroscience

◦ Anatomy is well understood◦ Lack of a cohesive brain theory Emergent properties Prediction versus Behavior

Page 3: Computational Modeling of Neural Networks and Memory Simulation

The Brain

Page 4: Computational Modeling of Neural Networks and Memory Simulation

MemoryBiology

◦ Patterns of active and inactive neurons in neural networks

◦ Vividness is determined by interneuron connection strength

Psychology◦ Forgetting◦ “Networks of

knowledge” (associative memory)

Page 5: Computational Modeling of Neural Networks and Memory Simulation

The Hebbian Theory“Neurons that Fire Together, Wire Together”If activity of two neurons is correlated strong synaptic

connection

ON

ON

OFF

Strong Weak

Page 6: Computational Modeling of Neural Networks and Memory Simulation

The Hopfield NetworkHopfield Network

If stimulus activates single neuron, other related neurons in neural network will also become activated

NJGSSScience

s

School

Research

Friends

Projects

(Input)(Output

)

Page 7: Computational Modeling of Neural Networks and Memory Simulation

THE PROGRAMPaul

Paul Jr.Paul Jr. Jr.

Page 8: Computational Modeling of Neural Networks and Memory Simulation

Step 1: Process Images

101001...

Page 9: Computational Modeling of Neural Networks and Memory Simulation

Step 2: Memorize

W11 W12W13W14

W21 W22W23W24

W31 W32 W33W34

W41 W42W43W44

1 2

340 1

1-1

1 01-1

1 1 0-1

-1 -1-10

4 3

1 2

0 1 -1 -1

1 0 -1 -1

-1 -1 0 1

-1 -1 10

0 2 0 -2

2 0 0 -2

0 0 0 0

-2 -2 0 0

N1

N2

N3N4

N1

N2

N3N4

N1 N2 N3 N4 N1 N2 N3 N4

Page 10: Computational Modeling of Neural Networks and Memory Simulation

Step 3: Scramble

Page 11: Computational Modeling of Neural Networks and Memory Simulation

Step 4: RecallY(t) = W*Y(t-1)

Page 12: Computational Modeling of Neural Networks and Memory Simulation
Page 13: Computational Modeling of Neural Networks and Memory Simulation

Pictures Memorized vs. Accuracy of Recall

More pictures in the Memory

Performance =

Range from -1 to 1

Worse Recall

Page 14: Computational Modeling of Neural Networks and Memory Simulation

The Effect of Noise on Recall

More Noise

Worse Recall

Residual=

performance of output –

performance of input

Page 15: Computational Modeling of Neural Networks and Memory Simulation

ChallengesMemory of MATLABPicture similarity

Result: low resolution pictures and low performance

Page 16: Computational Modeling of Neural Networks and Memory Simulation

The Future of the Hopfield Model

- Brain Theory

- Artificial Intelligence

- Education

Page 17: Computational Modeling of Neural Networks and Memory Simulation

SPECIAL THANKS TO:Dr. KouhAaron LoetherHopfield and HebbDr. MiyamotoMs. Papier

BUT MOST OF ALL:Donors Who Helped Make NJGSS ‘11 Possible!!

Page 18: Computational Modeling of Neural Networks and Memory Simulation

Sources Cited• Anastasio T J. Tutorial on Neural Systems Modeling. Sunderland

(MA): Sinauer Associates Inc.; 2010. 583 p.• Gazzaniga M S. The Cognitive Neurosciences. Cambridge (MA):

Bradford; 1997. 1447 p.• Wells R B.Synaptic Weight Modulation and Adaptation. In:

University of Idaho MRCI [discussion list on the Internet]. 2003 May 15; [cited 2011 July]. 13 p. Available from: http://www.mrc.uidaho.edu/~rwells/techdocs/Synaptic%20Weight%20Modulation%20and%20Adaptation%20I.pdf

• Kandel E R. Principles of Neuroscience. New York (NY): McGraw-Hill; 2000. 1414 p.

• Dayhoff J. School of Computing [homepage on the Internet]. Leeds (UK): University of Leeds; 2003. [cited 2011]. Available from: http://www.comp.leeds.ac.uk/ai23/reading/Hopfield.pdf.