modeling neural networks
play

Modeling Neural Networks Paul Nuytten CPSC 607 Outline Why model - PowerPoint PPT Presentation

Jan 17, 2024 •963 likes •1.22k views

Modeling Neural Networks Paul Nuytten CPSC 607 Outline Why model neural networks? A brief look at the neuron. A look at some current works. Adding an evolutionary strategy. Why Model Neural Networks? The nervous system is a

  1. Modeling Neural Networks Paul Nuytten CPSC 607

  2. Outline  Why model neural networks?  A brief look at the neuron.  A look at some current works.  Adding an evolutionary strategy.

  3. Why Model Neural Networks?  The nervous system is a very complex system with many hidden properties.  Many experiments cannot be performed in vivo without destroying the specimen; leaving many questions unanswered.  When looking at a model many of the redundant structures and processes can be removed leaving a more focused picture.  The nervous system is a very efficient and massively parallel computational device. Models may capture this property to solve a certain class of problems.

  4. The Neuron

  5. The Neuron  The neuron shares many of the same components as many other types of cells.  It’s the unique structures that make the neuron a powerful communication and computational device.

  6. The Neuron  The unique components are  The dendrites  The axon  The synapses

  7. The Dendrites  The dendrites are short strands that protrude from the cell body or the soma.  The dendrites are very receptive to connections from other neurons.  The dendrites carry signals from the synapses to the soma.

  8. The Axon  The axon is a long extension from the soma.  Each neuron only has one axon.  The axon is myelinated if it is insulated with Schwann cells.

  9. The Axon  If the axon is myelinated the action potential will travel much faster.  The axon carries action potentials from the soma to the synapses.

  10. The Synapse  The synapses are the connections made by an axon to another neuron.  When an action potential arrives at a synapse from the postsynaptic cell, neurotransmitter is released into the synaptic cleft.

  11. The Synapse  The neurotransmitter will interact with ion channels on the membrane of the postsynaptic cell causing them to open letting some ions into the cell while letting other ions escape.  A synapse is call excitatory if it raises the local membrane potential of the post synaptic cell.  Inhibitory if the potential is lowered.

  12. What level should be modeled?

  13. Some Current Works  NEURON  GENISIS  Neural Swarm  Evolutionary Artificial Neural Networks

  14. NEURON  NEURON is a simulation environment for neurons and neural networks.  The NEURON simulation allows a user to focus on the biological and biophysical aspects of a neurological system.  Great tool for biologists.

  15. NEURON

  16. GENISIS  GEneral NEural SImulation System  Provides a simulation environment for biologically realistic models.  Very similar to NEURON.  Allows for parallel processing.

  17. Neural Swarm  Uses the concepts of swarm intelligence when creating neurological models.  Still in its infancy.  Instead of designing the network and defining processes in mathematical terms, the network and processes are allowed to emerge from the simple interactions within the system.  The results are then compared to biologically observed results.

  18. Neural Swarm

  19. Evolutionary Artificial Neural Networks  Focuses more on the computational aspect of artificial neural networks (using them to solve problems).  Uses outgrowth and pruning rules to grow a neural network.  Spontaneous neural activity also contributes to the development of the network.  What is nice about this simulation is its ability to apply a genetic algorithm to the above rules and the network’s morphology to specialize the network to a given problem.

  20. Evolutionary Artificial Neural Networks

  21. Evolutionary Artificial Neural Networks

  22. Conclusion  When creating a simulation it is important to identify the level at which to model.  It is also important to identify the target audience and intended use of your simulation.  Start simple and gradually add complexity.  Collaborate.

  23. References F. Bloom, C. Nelson, A. Lazerson. Brain, Mind and Behavior Third  Edition. Worth Publishers, USA, 2001. N. Campbell. Biology Fourth Edition, pages 993-1009. The  Benjamins/Cummings Publishing Company, Inc., Menlo Park, California, 1996. R. Rojas. Neural Networks A Systematic Introduction. Springer-  Verlag, Berlin, 1996. Rust A.G., Adams R., Schilstra M. and Bolouri H. Evolving  computational neural systems using synthetic developmental mechanisms. 2003. http://www.rwc.uc.edu/koehler/biophys/4d.html  http://www.neuron.yale.edu/neuron/  http://www.genesis-sim.org/GENESIS/  http://strc.herts.ac.uk/bio/alistairr/neural_interests.html 

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

Outline Why model neural networks? Modeling Neural Networks A brief look at the neuron.

Outline Why model neural networks? Modeling Neural Networks A brief look at the neuron.

Outline Why model neural networks? Modeling Neural Networks A brief look at the neuron. A look at some current works. Adding an evolutionary strategy. Paul Nuytten CPSC 607 Why Model Neural Networks? The Neuron The nervous

697 views • 4 slides
Introduction to Recurrent Neural Networks Jakob Verbeek Modeling sequential data with Recurrent

Introduction to Recurrent Neural Networks Jakob Verbeek Modeling sequential data with Recurrent

Introduction to Recurrent Neural Networks Jakob Verbeek Modeling sequential data with Recurrent Neural Networks Compact schematic drawing of standard multi-layer perceptron (MLP) output hidden input Modeling sequential data So far we

796 views • 50 slides
NEURAL NETWORKS FOR MODELING AND CONTROL OF PARTICLE ACCELERATORS Auralee Edelen 2016-02-02

NEURAL NETWORKS FOR MODELING AND CONTROL OF PARTICLE ACCELERATORS Auralee Edelen 2016-02-02

NEURAL NETWORKS FOR MODELING AND CONTROL OF PARTICLE ACCELERATORS Auralee Edelen 2016-02-02 Advisors: Sandra Biedron and Stephen Milton Published Work Edelen, A. et al. Neural Networks for Modeling and Control of Particle Accelerators.

636 views • 35 slides
Recurrent Neural Networks CS 6956: Deep Learning for NLP Overview 1. Modeling sequences 2.

Recurrent Neural Networks CS 6956: Deep Learning for NLP Overview 1. Modeling sequences 2.

Recurrent Neural Networks CS 6956: Deep Learning for NLP Overview 1. Modeling sequences 2. Recurrent neural networks: An abstraction 3. Usage patterns for RNNs 4. BiDirectional RNNs 5. A concrete example: The Elman RNN 6. The vanishing

964 views • 18 slides
Recurrent Neural Networks CS 6956: Deep Learning for NLP Overview 1. Modeling sequences 2.

Recurrent Neural Networks CS 6956: Deep Learning for NLP Overview 1. Modeling sequences 2.

Recurrent Neural Networks CS 6956: Deep Learning for NLP Overview 1. Modeling sequences 2. Recurrent neural networks: An abstraction 3. Usage patterns for RNNs 4. BiDirectional RNNs 5. A concrete example: The Elman RNN 6. The vanishing

3.07k views • 30 slides
Recurrent Neural Networks CS 6956: Deep Learning for NLP Overview 1. Modeling sequences 2.

Recurrent Neural Networks CS 6956: Deep Learning for NLP Overview 1. Modeling sequences 2.

Recurrent Neural Networks CS 6956: Deep Learning for NLP Overview 1. Modeling sequences 2. Recurrent neural networks: An abstraction 3. Usage patterns for RNNs 4. BiDirectional RNNs 5. A concrete example: The Elman RNN 6. The vanishing

521 views • 33 slides
Recurrent Neural Networks CS 6956: Deep Learning for NLP Overview 1. Modeling sequences 2.

Recurrent Neural Networks CS 6956: Deep Learning for NLP Overview 1. Modeling sequences 2.

Recurrent Neural Networks CS 6956: Deep Learning for NLP Overview 1. Modeling sequences 2. Recurrent neural networks: An abstraction 3. Usage patterns for RNNs 4. BiDirectional RNNs 5. A concrete example: The Elman RNN 6. The vanishing

721 views • 60 slides
Outline Evolution of neurocomputing Artificial neural networks Feed forward

Outline Evolution of neurocomputing Artificial neural networks Feed forward

Introduction to Neural Networks and Deep Learning Ling Guan References: S. Haykin, Neural Networks , 2 nd Edition, New Jersey: Prentice Hall, 1. 2004. C. M. Bishop, Neural Networks for Pattern Re cognition, New York: 2. Oxford University

451 views • 17 slides
Recurrent Neural Networks for Language Modeling CSE392 - Spring 2019 Special Topic in CS Tasks

Recurrent Neural Networks for Language Modeling CSE392 - Spring 2019 Special Topic in CS Tasks

Recurrent Neural Networks for Language Modeling CSE392 - Spring 2019 Special Topic in CS Tasks Recurrent Neural Network and Language Modeling: Generate how? Sequence Models next word, sentence capture hidden representation of

674 views • 39 slides
Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling Authors: Junyoung

Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling Authors: Junyoung

Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling Authors: Junyoung Chung, Caglar Gulcehre, KyungHyun Cho and Yoshua Bengio Presenter: Yu-Wei Lin Background: Recurrent Neural Network Traditional RNNs encounter

229 views • 18 slides
Neural Networks for Machine Learning Lecture 7a Modeling sequences: A brief overview Geoffrey

Neural Networks for Machine Learning Lecture 7a Modeling sequences: A brief overview Geoffrey

Neural Networks for Machine Learning Lecture 7a Modeling sequences: A brief overview Geoffrey Hinton Nitish Srivastava, Kevin Swersky Tijmen Tieleman Abdel-rahman Mohamed Getting targets when modeling sequences When applying machine

719 views • 34 slides
Neural Networks 1. Introduction Fall 2017 Neural Networks are taking over! Neural networks

Neural Networks 1. Introduction Fall 2017 Neural Networks are taking over! Neural networks

Neural Networks 1. Introduction Fall 2017 Neural Networks are taking over! Neural networks have become one of the major thrust areas recently in various pattern recognition, prediction, and analysis problems In many problems they have

1.17k views • 91 slides
Neural Networks 0. Logistics Spring 2019 1 Neural Networks are taking over! Neural networks

Neural Networks 0. Logistics Spring 2019 1 Neural Networks are taking over! Neural networks

Neural Networks 0. Logistics Spring 2019 1 Neural Networks are taking over! Neural networks have become one of the major thrust areas recently in various pattern recognition, prediction, and analysis problems In many problems they have

852 views • 33 slides
Natural Language Processing with Deep Learning Language Modeling with Recurrent Neural Networks

Natural Language Processing with Deep Learning Language Modeling with Recurrent Neural Networks

Natural Language Processing with Deep Learning Language Modeling with Recurrent Neural Networks Navid Rekab-Saz navid.rekabsaz@jku.at Institute of Computational Perception Agenda Language Modeling with n- grams Recurrent Neural

667 views • 55 slides
C Crowd Counting and Behavior d C ti d B h i Modeling with Modeling with Convolutional Neural

C Crowd Counting and Behavior d C ti d B h i Modeling with Modeling with Convolutional Neural

C Crowd Counting and Behavior d C ti d B h i Modeling with Modeling with Convolutional Neural Networks Hongsheng Li Hongsheng Li 1 Dept. of Electronic Enigineering, 2 Multimedia Laboratory The Chinese University of Hong

666 views • 52 slides
The 3-pound universe we live in Cerebrum/Cerebral Cortex Thalamus Hypothalamus Pons

The 3-pound universe we live in Cerebrum/Cerebral Cortex Thalamus Hypothalamus Pons

CSE 473 Guest Lecture (Raj Rao): Neural Networks Outline: The 3-pound universe Those gray cells Input-Output transformation in neurons Modeling neurons Neural Networks Learning Networks Applications Corresponds

268 views • 15 slides
Course Introduction Neural Information Processing: Introduction Welcome and administration

Course Introduction Neural Information Processing: Introduction Welcome and administration

Course Introduction Neural Information Processing: Introduction Welcome and administration Matthias Hennig and Mark van Rossum Course outline and context A short neuroscience summary School of Informatics, University of Edinburgh January 2018

177 views • 5 slides
Statements and open sentences Statements: 2 is an even integer. 3 is an even integer.

Statements and open sentences Statements: 2 is an even integer. 3 is an even integer.

Statements and open sentences Statements: 2 is an even integer. 3 is an even integer. 4 is an even integer. . . . Statements and open sentences Statements: 2 is an even integer. 3 is an even integer. 4 is an even

782 views • 16 slides
Chapter 2 Structure and functions of cells of the nervous system Cell Organelles

Chapter 2 Structure and functions of cells of the nervous system Cell Organelles

Chapter 2 Structure and functions of cells of the nervous system Cell Organelles cellstissues-- systems Cell-- Small compartments that hold all the biological equipment necessary to keep an organism alive and

400 views • 22 slides
Building flexible and scalable applications Using CQRS and Axon Framework Allard Buijze

Building flexible and scalable applications Using CQRS and Axon Framework Allard Buijze

Building flexible and scalable applications Using CQRS and Axon Framework Allard Buijze abu@trifork.com @allardbz Allard Buijze CTO of Trifork Amsterdam ~ 15 years of web development experience Strong believer in DDD and CQRS

916 views • 45 slides
The cable equation A.K.A. the monodomain model Neurons Electric flow in neurons The neuron

The cable equation A.K.A. the monodomain model Neurons Electric flow in neurons The neuron

The cable equation A.K.A. the monodomain model Neurons Electric flow in neurons The neuron consists of three parts: Dendrite-tree, the input stage of the neuron, converges on the soma. Soma, the cell body, contain the normal

297 views • 17 slides
COMP304 Introduction to Neural Networks based on slides by: Christian Borgelt

COMP304 Introduction to Neural Networks based on slides by: Christian Borgelt

COMP304 Introduction to Neural Networks based on slides by: Christian Borgelt http://www.borgelt.net/ Christian Borgelt Introduction to Neural Networks 1 Motivation: Why (Artificial) Neural Networks? (Neuro-)Biology / (Neuro-)Physiology

609 views • 33 slides
The selective RNA-binding protein QKI: a key player in glia development and myelination

The selective RNA-binding protein QKI: a key player in glia development and myelination

The selective RNA-binding protein QKI: a key player in glia development and myelination Proliferation Differentiation Myelination QKI QKI Diseases relevant to QKI function: Myelin repair in multiple sclerosis White matter impairment in

147 views • 3 slides
NOTES FOR TEACHERS TO ACCOMPANY POWERPOINT PRESENTATION PSYCHOACTIVE MOLECULES FROM PLANTS SLIDE

NOTES FOR TEACHERS TO ACCOMPANY POWERPOINT PRESENTATION PSYCHOACTIVE MOLECULES FROM PLANTS SLIDE

NOTES FOR TEACHERS TO ACCOMPANY POWERPOINT PRESENTATION PSYCHOACTIVE MOLECULES FROM PLANTS SLIDE NOTES EXTENSION NUMBER SUGGESTIONS Introduce that everyday we consume plant extracts in our food, drinks and medications. Some of these contain

177 views • 4 slides

More recommend